Machine Learning Analysis of COVID19 Transmission Dynamics Demographic Risk and Contact Tracing Outcomes in Nigeria

Machine Learning Analysis of COVID19 Transmission Dynamics Demographic Risk and Contact Tracing Outcomes in Nigeria | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Machine Learning Analysis of COVID19 Transmission Dynamics Demographic Risk and Contact Tracing Outcomes in Nigeria Bolanle Adefowoke Ojokoh, Oluwafemi A. Sarumi, Sadura Priscilla Akinrinwa, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7932705/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 14 You are reading this latest preprint version Abstract The COVID-19 pandemic has posed significant challenges to developing countries like Nigeria due to limited resources. Accurate prediction of disease spread is crucial for effective containment measures. This study investigates the application of statistical and machine learning (ML) techniques in modelling and predicting COVID-19 cases in Nigeria, using data from January 2020 through December 2021. By analyzing demographic data (age, gender, location), symptom patterns, and contact tracing information, we seek to identify correlations and temporal trends associated with disease transmission. The datasets, obtained from the National Centre for Disease Control (NCDC), were cleaned before statistical analyses were carried out with Pearson’s Correlation, Analysis of Variance, and Cramer’s V Correlation. Prediction was carried out using the random forest (RF) classification model, implemented in Python's scikit learn library. Key findings include (1) 94.97% of confirmed contacts tested positive, underscoring high transmission rates; (2) occupations like healthcare workers and students were high-risk groups; and (3) the RF model achieved 87% accuracy in classifying source cases, though it struggled with minority classes. These can inform evidence-based policymaking and contribute to mitigating the impact of future outbreaks. A limitation of this study is the dependence on the accuracy of the NCDC data. COVID-19 transmission dynamics Machine learning prediction Demographic risk factors Nigeria pandemic response Contact tracing efficacy Public health policy optimization Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7 Figure 8 Figure 9 Figure 10 Figure 11 Figure 12 1. INTRODUCTION The COVID-19 pandemic has posed immense global health challenges, with transmission dynamics differing across regions and populations. Human-to-human transmission remains the primary driver for the rapid spread of the COVID-19 virus worldwide (Sankalpa et al., 2024 ). The situation is difficult in most African (developing) countries due to limited human, financial, and material resources, and this raises serious concerns about the crisis response strategy put in place to mitigate the effects of the virus (Elimian et al., 2020 ; Klein et al., 2021 ). Nigeria's distinct demographic, socio-economic, and environmental factors significantly impact the spread of the COVID-19 pandemic. The country's high urban population density, young demographic, diverse healthcare infrastructure, and socio-cultural practices shape the course of the COVID-19 pandemic (Oluwasanmi et al., 2021 ; Haque et al., 2021 ). Understanding these patterns is crucial for effective public health responses, particularly in densely populated, resource-limited areas. Nigeria’s healthcare system faces several challenges, including underreporting of cases, limited testing in the early stages of the pandemic, and difficulties in enforcing containment measures, making it harder to track and model COVID-19 transmission (Ilesanmi and Afolabi, 2020 ). Despite these issues, there remains a notable gap in studies focusing on the transmission dynamics in Nigeria (Utulu et al.,2022; Ojji et al., 2023 ). Most studies have concentrated on broader African trends or relied on data from other regions, leaving a significant gap in understanding Nigeria's unique context. Addressing this gap is crucial for developing targeted interventions, identifying country-specific risk factors, and improving resource allocation for current and future pandemics (Okonji et al., 2022 ). Due to the complexity and the large-scale nature of developing epidemiological models, machine learning (ML) has continuously gained attention for building outbreak prediction models. Several studies in Nigeria have employed ML techniques to predict and analyze COVID-19 transmission dynamics and outcomes. For instance, Ojo et al. ( 2021 ) utilized a decision tree algorithm to model the spread of COVID-19 in Nigeria, providing insights into potential future cases based on various socio-economic and demographic factors. Their model highlighted key predictors of COVID-19 transmission, demonstrating the potential of ML in informing public health strategies. Similarly, Folorunso et al. ( 2022 ) developed a machine learning model to forecast 14-day COVID-19 case trends in Nigeria, demonstrating that Support Vector Regressor (SVR) outperformed other algorithms in accuracy for public health planning 34. The study highlights the utility of ML in pandemic response by enabling data-driven predictions for government decision-making in Nigeria's unique epidemiological context. Moreover, Adebisi and Ogundipe ( 2022 ) employed support vector machines (SVM) to forecast COVID-19 cases in Nigeria, focusing on data from various states. This study revealed spatial variations in transmission rates and highlighted the importance of localized predictions for effective resource allocation. In Oke et al. ( 2023 ), a deterministic model was formulated to offer insight into the transmission dynamics of COVID-19 disease with the finding revealing that increasing vaccination coverage and decreasing vaccine waning rate facilitate the elimination of COVID-19. Additionally, Ojokoh et al. ( 2022b ) provides a comprehensive analysis of the COVID-19 pandemic across continents, including the techniques used to examine transmission patterns and evaluate intervention effectiveness. Their findings indicate that ML models can effectively predict COVID-19 cases, supporting public health strategies. Despite progress in research on COVID-19 transmission in Nigeria, notable gaps remain in the literature. A significant number of studies concentrate on specific regions or states, leading to a deficiency in comprehensive national models that account for the country's diverse demographics and socio-economic factors. Furthermore, there is a critical need to incorporate real-time data, such as mobility patterns and healthcare capacity, to enhance predictive accuracy. Additionally, while some research has explored the effects of various interventions, there is a lack of thorough evaluation regarding their long-term effectiveness utilizing ML frameworks. To address these gaps, this study investigates three core questions: (1) demographic and symptomatic risk factors, (2) temporal trends in transmission, and (3) the relationship between source cases and contacts. These questions aim to elucidate Nigeria-specific transmission dynamics to guide targeted interventions. Thus, this research aims to explore statistical and ML techniques in modelling and predicting COVID-19 cases in Nigeria. The study focuses on analyzing demographic data, symptom patterns, and contact tracing information to identify correlations and temporal trends related to disease transmission. By utilizing datasets from the National Centre for Disease Control (NCDC) using data from January 2020 through December 2021, and employing Pearson’s correlation, Analysis of Variance (ANOVA), Cramer’s V correlation, and the random forest (RF) classification model for prediction, the research seeks to enhance the understanding of COVID-19 spread and improve the effectiveness of containment measures in the context of Nigeria’s limited resources. 2. METHODS 2.1 ETHICAL APPROVAL AND DATA SOURCE Ethical clearance for this study was obtained from the National Health Research Ethics Committee (NHREC), Nigeria. Following approval, the dataset was provided by the Nigeria Centre for Disease Control (NCDC), the national public health authority responsible for detecting and managing infectious disease outbreaks in Nigeria. The dataset comprises COVID-19 cases reported from January 2020 to December 2021. The requirement for additional informed consent for this specific analysis was waived by the NHREC (ref #NHREC/01/01/2007-28/03/2023) because patients had previously provided written informed consent during their initial agreement, explicitly authorizing the use of their anonymized data for future research purposes. All data accessed were anonymized prior to analysis by removing all direct identifiers (including, but not limited to, names, addresses, medical record numbers, and exact dates of birth) and using unique study identifiers. This process ensured the authors could not access information that could identify individual participants. 2.2 DATA DESCRIPTION AND PREPROCESSING The COVID-19 database contains the following information: Contact ID, Classification of the source case (categorized as Confirmed case, Not yet classified, Probable case, Not a case, Suspect case), Disease, Contact classification (categorized as Confirmed, Unconfirmed and Not a Contact), Date of first contact, Date of last contact, Sex, Age, Date of the report, Responsible state, Responsible LGA, Responsible ward, Contact status (categorized as Active contact, Converted to the case, Dropped), Follow-up status, Type of occupation (categorized as Laboratory staff, Healthcare worker, Pupil/student, Farmer, Other, Businessman/woman, Child, Housewife, Working with animals, Miner, Transporter, Religious leader, Traditional/spiritual healer, Hunter/trader of game meat, and Butcher), and Symptoms at last cooperative visit further cleaned up into Temperature, Headache, Runny nose, Fever, Nausea, Muscle pain, Chest pain, Cough, Acute respiratory distress syndrome, Diarrhea, Abdominal pain, Fatigue/general weakness, Sore throat/pharyngitis, Difficulty breathing/Dyspnea, Joint pain or arthritis, sleepless night, dryness of mouth, General weakness, Hypertension, Cough with sputum, New loss of smell, Discomfort around the chest region, Arthritis, Chills or sweats, Malaise, Rapid breathing, nose bleeding and chest pain, red eyes, Conjunctivitis, and stuffy nose. To address missing values in the dataset, different strategies were employed based on the nature of the variable. For categorical variables, such as classification of source case, contact classification, occupation, and contact status, missing values were labeled as "Unknown." This ensures that all categories are represented, even if the specific information is missing, and allows for the inclusion of all data points in the analysis. For numerical variables, such as age and temperature, missing values were replaced with the mean of the respective columns. This approach preserves data distribution while minimizing bias. Missing values in location information were handled by filling them with the mode of the respective columns, as the mode represents the most frequently occurring value and is a suitable imputation method for categorical data. Additionally, Missing values in symptom columns were imputed using forward filling (FFill), which propagates the last observed value. It is particularly useful in time-series data or when the outcomes are likely to persist over consecutive observations. All analyses were conducted using Python 3.11, leveraging a range of libraries such as Matplotlib for data visualization, NumPy for numerical operations, Seaborn for statistical data visualization, and Pandas for data manipulation and analysis. Sociodemographic characteristics (variables) that are categorical, such as sex, location, and occupation, are described using frequencies and percentages (%). This approach provides a clear and concise summary of the distribution of these categorical variables across the dataset for continuous variables that follow a normal distribution, such as age, the mean and standard deviation (SD) are provided. These measures offer insights into the central tendency and variability of the data, respectively. 2.3 STATISTICAL ANALYSES Pearson correlation and ANOVA tests were carried out to assess the correlation between sex and temperature. Pearson Correlation Pearson correlation measures the linear relationship between two continuous variables. The formula for the Pearson correlation coefficient r is $$\:\:\:\:\:\:\:\:\:\:\:\:\:r=\frac{\sum\:({X}_{i}-X̅̅)({Y}_{i}-Y̅̅)}{\sqrt{\sum\:{({X}_{i}-X̅̅)}^{2}{\sum\:({Y}_{i}-Y̅̅)}^{2}}}\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\left(1\right)$$ where \(\:{X}_{i}\) ​ and \(\:{Y}_{i}\) are the individual sample points, and X̅ and Y̅ are the mean values of the sample points. The significance level (α) is set at 0.05 to determine if the correlation is statistically significant. ANOVA Test ANOVA compares the means of two or more groups to see if at least one differs significantly. The F-statistics in ANOVA is calculated as $$\:F=\frac{Between-group\:variability}{Within-group\:variability}$$ 2 The significance level (α) is set at 0.05 to determine if the differences between group means are statistically significant. Cramér's V Correlation Cramér's V measures the association between two categorical variables. The formula for Cramér's V is $$\:V\:=\:\sqrt{\frac{{x}^{2}/n}{min(k-1,r-1)}}$$ 3 Where \(\:{x}^{2}\) is the chi-squared statistic, \(\:n\) is the total sample size, \(\:k\) is the number of columns, and \(\:r\) is the number of rows. 2.4 MACHINE LEARNING PREDICTION The RF classification model was used to predict the source case classification and the contact classification features of COVID-19 cases based on the other variables. RF model was selected for this study due to its superior performance in handling the specific challenges of Nigeria’s COVID-19 dataset. RF excels in managing categorical and mixed data types (e.g., occupation, symptoms) without extensive preprocessing, which is critical given the dataset’s heterogeneity. It also addresses class imbalance—a common issue in epidemiological data—through bootstrap sampling and class weighting, ensuring robust predictions for minority classes like "Probable cases." Unlike models such as SVM or ANN, RF computational efficiency and interpretable feature importance scores, aligning with the study’s goal of identifying high-risk demographics and transmission drivers. Additionally, RF’s ensemble approach mitigates overfitting and noise, making it resilient to missing data and inconsistencies prevalent in Nigeria’s health records. These attributes make RF uniquely suited to model Nigeria’s COVID-19 dynamics while delivering actionable insights for public health strategies. Figure 1 describes the workflow of the RF algorithm. The dataset was split into training and test sets. A RF classifier was initialized and trained using the training set. The key parameter settings for the RF classifier include the number of Trees ( \(\:{n}_{estimators}\) ) set to 100, the random state (random_state) set to 42 to ensure reproducibility. To implement the RF algorithm as shown in Fig. 1 , the first step involves selecting random samples from the given dataset. In our use case, 70% of the data is designated for training, while the remaining 30% is reserved for testing. This division ensures that the model is trained on a substantial portion of the data while also having a separate set for evaluating its performance. Once the training set is established, the RF algorithm constructs a multitude of decision trees, each based on a random subset of the training data. Each decision tree is built by selecting random features and using them to create splits that best separate the data according to the target variable. This process of creating multiple decision trees from different random samples and feature sets ensures that the model captures a diverse range of patterns in the data, thereby enhancing its robustness and accuracy. After constructing the decision trees, the RF algorithm employs a voting mechanism to make predictions (Breiman, 2001 ). Each tree in the forest predicts a given input, and these predictions are then aggregated. The voting was performed by taking the average of the predictions of the most frequent predictions. This collective decision-making process helps to mitigate the biases of individual trees and leads to a more accurate and reliable final prediction. The final prediction is determined by the majority vote among all the trees, ensuring that the most commonly predicted outcome by the ensemble of trees is chosen as the final result. This method not only improves prediction accuracy but also provides robustness against overfitting, as it leverages the contribution of multiple models rather than relying on a single decision tree. 2.5 MODEL EVALUATION The model's performance was evaluated on the test set using standard performance metrics as described in Eq. 4 – 7 . The precision indicates the proportion of true positive predictions out of all positive predictions made, recall measures the proportion of actual positives that are correctly identified by the model. F1-score is the harmonic mean of precision and recall. $$\:Accuracy\:=\:\frac{TP\:+\:TN}{TP\:+\:TN\:+\:FP\:+\:FN}$$ 4 $$\:Precision\:=\:\frac{TP}{TP\:+\:FP}$$ 5 $$\:Recall\:=\:\frac{TP}{TP\:+\:FN}$$ 6 $$\:F1-Score\:=\:2\cdot\:\frac{Precision\:\cdot\:\:Recall}{Precision\:+\:Recall}$$ 7 where TP = True Positives, TN = True Negatives, FP = False Positives, and FN = False Negatives 3. RESULTS 3.1 DISTRIBUTION OF COVID-19 CASES ACROSS DEMOGRAPHICS There are 100,627 individual records in the dataset. 76.69% were confirmed cases of COVID-19, 6.55% were Not a case, 3.21% were suspect cases, 0.17% (170/100,627) were Probable cases, 0.14% were Not yet classified, and 13.23% had missing values. The data distribution regarding contacts with current COVID-19 cases showed that 65.3% of the participants were confirmed contacts, 34.3% were unconfirmed contacts and 0.38% were not a contact category Figures 2a and 2b show the distribution of the sex from the data. Males accounted for 51.3% and 51.8% of the confirmed COVID-19 cases. Females comprised 47.0% and 46.5% of the confirmed cases. Figure 3 is a visualization of the age distributions of the data. Ages ranged from 0 to 120 years. The mean age of the study participants was 36.8 years and the mean age of persons with confirmed COVID-19 was 37.5 years. Figure 4 illustrates the age distribution of the participants as contacts of COVID-19 cases. Figures 5 and 6 are multivariate visualizations of the age distributions and other features of the COVID-19 data. Figure 5 depicts the frequency of the source case classification by age, while Fig. 6 depicts the frequency of the contact case classification by age. Based on Figs. 5 and 6, the large number of confirmed cases shown in Fig. 5 , alongside the high number of confirmed contacts in Fig. 6, suggests a significant overlap between the two categories. This may indicate that many of the confirmed COVID-19 cases were indeed previously identified as confirmed contacts, highlighting the importance of contact tracing in identifying and managing cases of the virus. The strong presence of confirmed contacts leading to confirmed cases emphasizes the effectiveness of tracing as a critical tool in controlling the spread of infection. The distribution of participants with confirmed COVID-19 cases by their occupation is depicted in Fig. 7 and summarized as follows: The Other category makes up 18.5% of the confirmed cases in the study participants. Pupils / students made up 13.6% of the confirmed COVID-19 cases. Healthcare workers accounted for 9.39% of the confirmed cases. Businessmen / women accounted for 4.59% of the confirmed cases. Housewives had 2.62%, Children had 2.24%, Farmers 2.10%. Laboratory staff 0.32%, Transporters 0.2%, animal workers 0.18%, Religious leader 0.14%, Hunter / trader of game meat 0.04%, Butcher 0.03% Traditional / spiritual healer 0.023%, and Miner 0.009%, accounted for 0.94% of the confirmed cases. There were 46% missing entries in the occupation field. 3.2 SYMPTOM FREQUENCY ACROSS AGE GROUPS Figure 8 highlights the symptoms associated with COVID-19 as reported by participants. The most commonly reported symptoms at diagnosis included fever, cough, fatigue or general weakness and difficulty breathing or dyspnea. Other symptoms reported included headache, sore throat, muscle pain, and loss of taste or smell. The fever is more common to the 0–18 and 36–50 age group. Cough is more common to the 66 + age group, while headache is higher in the 0–18 age group, and less common among the other age groups. 3.3 MULTIVARIATE ANALYSIS OF THE TEMPERATURE AND SEX FEATURES The temperature distribution, as shown in Figs. 9 (a) and (b) are quite similar for both Females and Males. Both groups have a minimum temperature of 35.0°C, median temperature of 36.2°C and a typical range of temperatures between 35°C and 38°C. Outliers indicate that there are a few individuals, particularly in the Male group, with temperatures above 39°C, suggesting potential cases of higher fever in the male group. These cases are reduced in the Confirmed cases indicating that fevers of higher than 39°C may not be COVID-19 cases. The Pearson correlation coefficient between sex and temperature is approximately − 0.0027, indicating a very weak negative correlation. This implies that there is almost no linear relationship between sex and temperature in the dataset. The ANOVA test yielded a p-value of 0.716, indicating no significant difference between sex and temperature. In other words, the variation in temperature does not appear to be significantly associated with the categories of sex in the dataset. Therefore, based on the available data, there is no evidence to suggest that the average temperature differs significantly between different sexes. Therefore, based on the ANOVA test result, we cannot confidently conclude that there is a relationship between sex and temperature in the dataset. 3.4 CORRELATION BETWEEN SEX AND OCCUPATION Table 1 shows the count of people by sex and occupation. Each row represents an occupation, and each column represents the counts of individuals based on sex. The categories "Other," "Pupil / student," and "Healthcare worker" have the highest counts, with both males and females significantly represented. For most occupations, Male category seems to have slightly higher or similar counts to females, except for Health care workers and "Housewife," which have higher numbers of females. Occupations like "Butcher," "Working with animals," and "Miner" have very few individuals represented. Table 1 Distribution of participants by sex and occupation in confirmed COVID-19 cases Occupation Female Male Other Unknown Businessman/woman 1575 1956 0 13 Butcher 1 20 0 1 Child 823 901 0 5 Farmer 438 1178 1 2 Healthcare worker 4385 2843 0 23 Housewife 1908 112 0 3 Hunter / trader of game meat 16 15 0 0 Laboratory staff 126 120 0 0 Miner 2 5 0 0 Other 5237 9011 0 32 Pupil / student 5040 5394 2 27 Religious leader 14 91 0 0 Traditional / spiritual healer 6 12 0 0 Transporter 13 141 0 1 Working with animals 7 131 0 0 The correlation matrix in Table 2 shows the relationship between the counts of people for each sex in each occupation. There is a strong positive correlation (0.89) between the counts of females and males across occupations. This suggests that occupations with a higher count of females also tend to have a higher count of males, and vice versa. Similarly, there is a high number of correlations between the Male and Unknown and the Female and Unknown sex groups indicating that occupations with high numbers of male also show high numbers of female and Unknown. Table 2 Correlation matrix by sex for different occupations Sex Female Male Other Unknown Female 1 0.892942 0.430255 0.973726 Male 0.892942 1 0.375904 0.940313 Other 0.430255 0.375904 1 0.396836 Unknown 0.973726 0.940313 0.396836 1 The correlation value of 4402.3445 for Cramér's V between sex and occupation indicates a strong association between the sex and occupational variables. Therefore, this further suggests that there is a significant relationship between sex and occupation in the dataset. 3.5 CORRELATION BETWEEN OCCUPATION AND TEMPERATURE FOR CONFIRMED CONTACTS Figure 11 shows the distribution of temperature across occupations. For most occupations, the median temperatures are between 36°C and 37°C, indicating a similar central tendency for body temperature across different jobs. “Working with animals" shows a lower median temperature, while occupations like “Businessman / women", “Pupil / student” and "Farmer” have high spread in temperature values, with more pronounced outliers. "Transporter" and "Traditional / spiritual healer", “Butcher” and "Hunter / trader of game meat” appear to have slightly higher median temperatures compared to other occupations, potentially indicating a variation in body temperature trends within these groups. Certain occupations, such as "Butcher" and "Traditional / spiritual healer," show narrow interquartile ranges, suggesting less variability in body temperature for these groups. Table 3 Distribution of the temperature across various occupations Occupation Median IQR Min Max Outliers Businessman/woman 36.4 0.7 34.95 37.75 43 Butcher 36.6 0.2 36.15 36.95 1 Child 36.2 0.8 34.5 37.7 4 Farmer 36.3 1.1 33.95 38.35 1 Healthcare worker 36.3 0.725 34.7875 37.6875 11 Housewife 36.3 1 34.2 38.2 1 Hunter/trader of game meat 36.55 0.575 35.4625 37.7625 0 Laboratory staff 36.35 0.675 34.9125 37.6125 0 Miner 36.4 0.6 35.325 37.725 1 Other 36.3 0.8 34.6 37.8 11 Pupil / student 36.3 0.8 34.6 37.8 16 Religious leader 36.1 0.625 34.8375 37.3375 0 Traditional / spiritual healer 36.45 0.225 35.9625 36.8625 0 Transporter 36.5 0.9 34.65 38.25 0 Working with animals 35.5 0.4 34.7 36.3 4 An analysis of the occupation and temperature features for confirmed contacts of COVID-19 was done with Kruskal-Wallis H test. The p-value obtained from the Kruskal-Wallis H test is 3.28 × 10 − 28 , suggesting that there is a significant difference in the distribution of temperature across different categories of occupation, therefore, variation in temperature is associated with the categories of occupation in the dataset. 3.6 DISTRIBUTION OF CLASSIFICATION OF CONTACTS BY CLASSIFICATION OF SOURCE CASES Table 4 illustrates the association between "classification of source cases" and "classification of contacts" in COVID-19 cases. The majority of confirmed contacts were categorized as confirmed cases, totaling 58,160. The numbers of confirmed contacts in other categories were considerably lower, with 2,264 classified as not a case, 606 as suspect cases, and 156 as probable cases. Among unconfirmed contacts, a significant portion were identified as confirmed cases 18,704 and suspect cases 2,615, with additional classifications including 4,309 as not a case, 14 as probable cases, and 84 as not yet classified. For the not a contact category, there were 309 confirmed cases, 27 classified as not a case, and 5 as suspect cases. Table 4 Distribution of classification of contacts by classification of source cases. Classification of the source case Confirmed case Not a case Not yet classified Probable case Suspect case Contact classification Confirmed contact 58160 2264 56 156 606 Not a contact 309 27 0 0 5 Unconfirmed contact 18704 4309 84 14 2615 3.7 RESULTS ON THE RANDOM FOREST MODEL PREDICTIONS FOR SOURCE CASE CLASSIFICATION Table 5 shows the confusion matrix of RF model predictions for source case classification while Table 6 gives the classification report of the model in predicting the source case classes with accuracy of 87%. The classification report provides the metrics to evaluate the performance of the RF classifier. Table 5 Confusion matrix of random forest model predictions for source case classification Confusion Matrix: Actual Confirmed case 22079 439 3 2 300 375 Suspect case 992 742 0 0 182 53 Probable case 22 4 5 0 2 1 Not yet classified 26 2 0 24 0 1 Not a case 299 151 0 0 477 15 Unknown 1018 20 1 0 4 2949 Confirmed case Suspect case Probable case Not yet classified Not a case Unknown Predicted Table 6 Classification report of the random forest model in predicting source case classification of COVID-19. Classification Report Precision Recall F1-score Support Confirmed case 0.9 0.95 0.93 23198 Suspect case 0.55 0.38 0.45 1969 Probable case 0.56 0.15 0.23 34 Not yet classified 0.92 0.45 0.61 53 Not a case 0.49 0.51 0.5 942 Unknown 0.87 0.74 0.8 3992 accuracy 0.87 30188 macro average 0.72 0.53 0.59 30188 weighted average 0.86 0.87 0.86 30188 The classification report provides the metrics to evaluate the performance of the RF classifier. Support shows the number of actual occurrences of each class in the test set. The Confirmed case class has the largest number of participants (23,198). The model achieves 90% precision and 95% recall for this class, indicating robust performance.. Precision: 0.90, Recall: 0.95, F1-score: 0.93. The Suspect case class has 1969 participants. The precision indicates that 55% of the predictions for this class are correct, but the recall is relatively low (38%), suggesting that the model misses many actual instances of this class. Precision: 0.55, Recall: 0.38, F1-score: 0.45. The Probable case class has 34 participants. The model exhibits a low recall (15%) for this class, likely due to data scarcity. Precision: 0.56, Recall: 0.15, F1-score: 0.23. The Not yet classified class has 53 participants. The model has a high precision (92%) but a much lower recall (45%), indicating that it is good at predicting this class when it does, but it often fails to recognize actual instances. Precision: 0.92, Recall: 0.45, F1-score: 0.61. The Not a case class has 942 participants. This class is balanced in terms of precision and recall, but both are relatively low, suggesting room for improvement. Precision: 0.49, Recall: 0.51, F1-score: 0.50. This Unknown class has 3992 participants. The model performs reasonably well on this class, with both precision and recall being above 70%. Precision: 0.87, Recall: 0.74, F1-score: 0.80 Overall, the accuracy of 87% was obtained. The weighted precision, recall, and F1-score are 0.86, 0.87, 0.86, indicating that overall performance is quite good, mainly due to the high number of confirmed case participants in the data. Thus, the model performs well on the majority class (confirmed case), but struggles with some minority classes (e.g., Probable case and Not yet classified). 3.9 TEMPORAL TRENDS IN THE COVID-19 CASES Figure 12 shows how the number of COVID-19 cases fluctuated over time, starting from mid-2019 and ending in early 2022. In the initial period between 2019-05 to 2020-01, there was little to no activity until early 2020, reflecting the pre-pandemic period when COVID-19 cases were not reported, or the disease had not yet widely spread. The first surge noted was between 2020-05 and 2020-10 where a significant spike in cases is seen in 2020-06, peaking around the third quarter of 2020. The number of cases rapidly increased, reaching over 4000 cases at the peak. A decline and fluctuation was noted from 2020-10 to 2021-01. After reaching its peak, there was a steep drop in the number of cases towards the end of 2020 and the beginning of 2021, though some small peaks are still observed during this period. Another increase is visible around early 2021, which led to the second wave between 2021-01 and 2021-05, leading to another peak in 2021-03 reaching about 2000 cases. There is noticeable fluctuation during 2021, with periodic increases and decreases, suggesting possible effects of new variants, waves, or public health measures being applied and lifted. A decline was observed toward the end of 2021, between 2021-09 and 2022-01. The number of cases continued to fall towards the end of 2021 and reached close to zero by early 2022. 4. DISCUSSION This study examined the demographic and occupational risk factors, temporal trends and policy implications, and source-contact dynamics and ML utility linked to COVID-19 infection rates and mortality in Nigeria. The findings from this study provide important insights into the dynamics of COVID-19 transmission within Nigeria and highlight the critical role that underscore the significance of using ML techniques for disease outbreak prediction and containment. Nigeria’s unique socio demographic landscape, characterized by a youthful population (median age of 36.8 years), high urban density, and uneven healthcare access—shaped the uneven distribution of COVID-19 cases. The concentration of infections among younger age groups (10–39 years) aligns with the country’s demographic profile, where over 60% of the population is under 25. However, this contrasts with global patterns where older adults faced higher risks, suggesting that Nigeria’s younger population may have experienced greater exposure due to urban crowding, informal work dependencies, or reduced adherence to containment measures. Occupations such as healthcare workers (9.39% of cases) and students (13.6%) emerged as high-risk groups, likely due to prolonged exposure in hospitals and crowded educational institutions. These findings mirror studies by Adepoju ( 2020 ), who linked urban density in Lagos and Kano to rapid transmission. Symptom patterns further revealed gaps in surveillance: while fever and cough were widely reported, atypical markers like anosmia (loss of smell) were underrecognized, potentially delaying diagnosis. This underscores the need for symptom screening protocols tailored to Nigeria’s resource-limited clinics, where rapid testing remains scarce. The temporal analysis identified two distinct COVID-19 waves: a mid-2020 surge (peaking at 4,000 + cases) and a smaller 2021 resurgence, followed by a decline to near-zero cases by early 2022. The first wave coincided with Nigeria’s initial lockdown relaxation in June 2020, which prioritized economic recovery over sustained restrictions—a trade-off common in low-income countries. The second wave aligned with the global spread of the Delta variant and seasonal gatherings (e.g., December holidays), highlighting the vulnerability of Nigeria’s under-vaccinated population (only 3% fully vaccinated by late 2021). The sharp decline by 2022 likely reflects natural immunity from prior infections rather than vaccination success, given Nigeria’s slow rollout. These trends emphasize the need for adaptive public health policies: aggressive containment during surges (e.g., targeted lockdowns, mask mandates) and post-peak investments in healthcare infrastructure to mitigate future outbreaks. The findings emphasized the importance of balancing economic and health priorities in Nigeria’s pandemic response. The strong link between confirmed contacts and cases (94.97% positivity) validates contact tracing as a critical tool in Nigeria’s response, consistent with WHO guidelines (2020). However, the 309 confirmed cases in the “not a contact” category signal pervasive community transmission, likely exacerbated by underreporting and limited testing in rural areas. The RF model achieved 87% accuracy in predicting source classifications, demonstrating machine learning’s potential to optimize contact tracing in resource-constrained settings. However, its poor performance on minority classes (e.g., Probable cases : 15% recall) reflects challenges common to Nigerian datasets: imbalanced classes, missing occupation data (35,542 entries), and inconsistent reporting. To enhance predictive power, future models could integrate real-time mobility data or employ synthetic oversampling techniques (e.g., SMOTE) for underrepresented classes. These improvements could help policymakers prioritize testing in high-risk occupations or regions, as suggested by Ojokoh et al. ( 2022a ) in their continental analysis of contact tracing efficacy. 5. CONCLUSION This study highlights COVID-19 transmission dynamics in Nigeria through statistical analyses and machine learning, addressing three research questions critical to understanding the pandemic’s unique trajectory in a resource-limited setting. First, demographic analysis revealed that younger age groups (10–39 years) and occupations such as healthcare workers (9.39% of cases) and students (13.6%) faced heightened risks, likely due to Nigeria’s youthful population density and exposure in high-contact environments like schools and hospitals. Symptom patterns further highlighted gaps in screening protocols, with fever and cough dominating reports, while atypical markers like loss of smell were underrecognized. Second, temporal trends identified two distinct waves: a mid-2020 surge peaking at over 4,000 cases, likely tied to early pandemic unpreparedness, and a smaller 2021 resurgence coinciding with variant emergence and relaxed restrictions. By early 2022, cases declined sharply, reflecting cumulative immunity from vaccination and prior infections. Third, the relationship between source cases and contacts was rigorously analyzed using a RF model, which achieved 87% accuracy in classifying confirmed cases. However, its limitations in predicting minority classes (e.g., 15% recall for Probable cases) underscored challenges posed by imbalanced data. Strikingly, 94.97% of confirmed contacts tested positive, validating contact tracing’s efficacy, while 309 cases in the “not a contact” category signaled pervasive community transmission. These findings advance Nigeria-specific pandemic insights by prioritizing high-risk demographics, linking transmission peaks to policy gaps, and demonstrating machine learning’s potential in outbreak prediction despite data constraints. Practical implications include prioritizing healthcare workers and students for testing, dynamically adjusting public health measures during surges, and improving data quality to refine predictive models. Future work should integrate mobility patterns, genomic surveillance, and socioeconomic variables to enhance real-time modeling, while community engagement campaigns could address underreporting in rural areas. Further tuning, such as adjusting class weights or using different techniques for imbalanced data, could help improve performance for the minority classes. By bridging gaps in localized transmission analytics, this study underscores the value of tailored, data-driven strategies to mitigate COVID-19’s burden in resource-constrained settings and offers a framework for future pandemic preparedness. Declarations Funding: This work was supported by the Nigerian Tertiary Education Trust Fund (TETFund) through the National Research Fund [Grant Number NRF/SETI/ICT/00029]. Clinical trial registration: Not applicable. Data availability: This work utilizes data from the Nigeria Centre for Disease Control and Prevention (NCDCP). Due to data sharing restrictions, the raw data cannot be disseminated by the authors. However, individuals or institutions seeking access may submit a formal request to the NCDCP for approval. Authors’ contributions: Bolanle Adefowoke Ojokoh, Oluwafemi A. Sarumi, Sadura Priscilla Akinrinwa, and Abimbola H. Afolayan made substantial contributions to the conception or design of the work, or the acquisition, analysis, or interpretation of data for the work. Bolanle Adefowoke Ojokoh, Oluwafemi A. Sarumi, and Tobore V. Igbe contributed to drafting the work or revising the draft critically for important intellectual content Uchechukwu M. Chukwuocha helped with the ethical clearance process. Competing interests: The authors have no competing interests in declaring for this study. References Adebisi, A. A., & Ogundipe, A. E. (2022). Forecasting COVID-19 cases in Nigeria using support vector machines. Nigerian Journal of Computer Science, 10 (1), 52–64. Available at:https://doi.org/10.2139/njcs.2022.1.5 Adepoju, P. (2020). "Nigeria’s COVID-19 response: The Lagos and Kano experience." The Lancet Global Health, 8(10), e1240-e1241. Available at: DOI: 10.1016/S2214-109X(20)30315-6 Breiman, L. (2001). Random forests. Machine Learning, 45 (1), 5–32. Available at: https://doi.org/10.1023/A:1010933404324 Elimian, K. O., Ochu, C. L., Ebhodaghe, B., Myles, P., Crawford, E. E., Igumbor, E., Ukponu, W., Olayinka, A., Aruna, O., Dan-Nwafor, C., Olawepo, O. A., Ogunbode, O., Atteh, R., Nwachukwu, W., Venkatesan, S., Obagha, C., Ngishe, S., Suleiman, K., Usman, M., Yusuff, H. A., Nwadiuto, I., Mohammed, A. A., Usman, R., Mba, N., Aderinola, O., Ilori, E., Oladejo, J., Abubakar, I., & Ihekweazu, C. (2020). Patient characteristics associated with COVID-19 positivity and fatality in Nigeria: Retrospective cohort study. BMJ Open, 10 , e044079. Available at: https://doi.org/10.1136/bmjopen-2020-044079 Folorunso, S. O., Ogundepo, E. A., Awotunde, J. B., Ayo, F. E., Banjo, O. O., & Taiwo, A. I. (2022). A multi-step predictive model for COVID-19 cases in Nigeria using machine learning. In Decision Sciences for COVID-19: Learning Through Case Studies (pp. 107-136). Cham: Springer International Publishing. Available at: DOI: 10.1007/978-3-030-87019-5_7 Haque, M., Abubakar, A., Ogunleye, O., Sani, I., Sefah, I., Kurdi, A., et al. (2021). Changes in availability, utilization, and prices of medicines and protection equipment for COVID-19 in an urban population of Northern Nigeria. Journal of Research in Pharmacy Practice, 10 (1), 17. Available at:https://doi.org/10.4103/jrpp.JRPP_20_92 Ilesanmi, O. S., & Afolabi, A. A. (2020)."Learning from the challenges of COVID-19 in Nigeria: A systematic review of the country’s response and lessons for future pandemics." International Journal of Infectious Diseases, 101, 316-323. Available at: DOI: 10.1016/j.ijid.2020.09.1462 Klein, H., Asseo, K., Karni, N., Benjamini, Y., Nir-Paz, R., Muszkat, M., Israel, S., & Niv, M. Y. (2021). Onset, duration, and unresolved symptoms, including smell and taste changes, in mild COVID-19 infection: A cohort study in Israeli patients. Clinical Microbiology and Infection, 27 , 769–774. Available at: https://doi.org/10.1016/j.cmi.2021.02.008 Oluwasanmi, O. O., Akinokun, R. T., Ilesanmi, O. S., & Akinyemi, J. O. (2021). "COVID-19 in Nigeria: A disease of inequality and the struggle for containment in a weak health system." Journal of Global Health, 11, 03063. Available at: DOI: 10.7189/jogh.11.03063 Ojji, D. B., Shedul, G. L., Orji, I. A., Abu, J., Akor, B., Ripiye, N., & Huffman, M. D. (2023). Nigeria healthcare worker SARS-CoV-2 serology study: Results from a prospective, longitudinal cohort. PLOS Global Public Health . Available at:https://doi.org/10.1371/journal.pgph.0000549 Ojo, J. A., Owoeye, O. D., & Olawale, J. K. (2021). Predicting COVID-19 transmission in Nigeria using machine learning techniques. Journal of Health Informatics in Developing Countries, 14 (2), 115–126. Available at:https://doi.org/10.21633/jhidc.v14i2.825 Ojokoh, B. A., Aribisala, B., Sarumi, O. A., Gabriel, A. J., Omisore, O., Taiwo, A. E., & …, Afolabi, O. (2022a). Contact tracing strategies for COVID-19 prevention and containment: A scoping review. Big Data and Cognitive Computing, 6 (4), 111. Available at:https://doi.org/10.3390/bdcc6040111 Ojokoh, B. A., Sarumi, O. A., Salako, K. V., Gabriel, A. J., Taiwo, A. E., Johnson, O. V., & Babalola, O. T. (2022b). Modelling and predicting the spread of COVID-19: A continental analysis. In Data Science for COVID-19 (pp. 299–317). Academic Press. Available at: https://doi.org/10.1016/B978-0-323-90769-9.00039-6 Oke, I. I., Idisi, T. T., Yusuf, K. M., Owolabi, B. A., & Ojokoh, B.A. (2023). A bifurcation analysis and model of COVID-19 transmission dynamics with post-vaccination infection impact. Healthcare Analytics, 3 , 100157. Available at: https://doi.org/10.1016/j.health.2023.100157 Okonji, E. F., Okonji, O. C., Mukumbang, F. C., & Van Wyk, B. (2022)."Understanding the varying COVID-19 mortality rates across Africa: A comparative analysis of South Africa, Egypt, and Nigeria." BMC Public Health, 22, 1817. Available at: DOI: 10.1186/s12889-022-14236-z Sankalpa, D., Dhou, S., Pasquier, M., & Sagahyroon, A. (2024). Predicting the spread of a pandemic using machine learning: a case study of COVID-19 in the UAE. Applied Sciences , 14 (10), 4022. Available at: https://doi.org/10.3390/app14104022 Utulu, R., Ajayi, I. O., Bello, S., Balogun, M. S., Madubueze, U. C., Adeyemi, I. T., Omoju, O. T., Adeke, A. S., Adenekan, A. O., & Iyare, O. (2022). Risk factors for COVID-19 infection and disease severity in Nigeria: A case-control study. Pan African Medical Journal, 41 (317). Available at: https://www.panafrican-med-journal.com//content/article/41/317/full World Health Organization. (2020). Contact tracing in the context of COVID-19. Retrieved fromhttps://www.who.int/publications/i/item/contact-tracing-in-the-context-of-covid-19 Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 01 Mar, 2026 Reviews received at journal 12 Feb, 2026 Reviewers agreed at journal 05 Feb, 2026 Reviews received at journal 21 Jan, 2026 Reviewers agreed at journal 16 Jan, 2026 Reviewers agreed at journal 07 Jan, 2026 Reviews received at journal 17 Dec, 2025 Reviewers agreed at journal 17 Dec, 2025 Reviewers agreed at journal 11 Dec, 2025 Reviewers invited by journal 09 Dec, 2025 Editor assigned by journal 02 Dec, 2025 Editor invited by journal 30 Nov, 2025 Submission checks completed at journal 26 Nov, 2025 First submitted to journal 26 Nov, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-7932705","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":558707390,"identity":"7a7dd702-e344-4d07-8b0a-50ff076fac9b","order_by":0,"name":"Bolanle Adefowoke Ojokoh","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA7UlEQVRIiWNgGAWjYBACAzA+wJDAz3wALMDYQLQWybYEsGritDCAtBgcI1aLOfvhAwUfztjkGR/jMX/wg8FGdsMB3sMv8Gmx7ElLMJxxI63Y7BiPYWMPQ5rxhgN8aRZ4HXYgx8CY58PhxG33ewwbeBgOJ244wGNmgFfL+TcQLZvbgLb8YfhPhJYbIFtuAA1n4zFs5mE4ANJi/ACvX2Y8A/rlTFrijGNshbNlDJKNZx7mMcOng8GcP/mYwYdjNon9bcwbPr6psJPtO95j/AGvHgYGNiSXg5jMDGwSBLQwY7icmZAto2AUjIJRMLIAAMDJUs5q7qzlAAAAAElFTkSuQmCC","orcid":"","institution":"Federal University of Technology","correspondingAuthor":true,"prefix":"","firstName":"Bolanle","middleName":"Adefowoke","lastName":"Ojokoh","suffix":""},{"id":558707391,"identity":"9ab216be-0c15-4715-94e5-ec0579825f08","order_by":1,"name":"Oluwafemi A. Sarumi","email":"","orcid":"","institution":"University of Marburg","correspondingAuthor":false,"prefix":"","firstName":"Oluwafemi","middleName":"A.","lastName":"Sarumi","suffix":""},{"id":558707393,"identity":"c8e0e373-db39-426a-accb-d03722b5db45","order_by":2,"name":"Sadura Priscilla Akinrinwa","email":"","orcid":"","institution":"Federal University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Sadura","middleName":"Priscilla","lastName":"Akinrinwa","suffix":""},{"id":558707400,"identity":"f5da8e35-0e0a-454c-ab14-797187166d2a","order_by":3,"name":"Abimbola H. Afolayan","email":"","orcid":"","institution":"Federal University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Abimbola","middleName":"H.","lastName":"Afolayan","suffix":""},{"id":558707408,"identity":"ecb7ccf6-b410-4d30-a1cb-e7b6ce89fad6","order_by":4,"name":"Tobore V. Igbe","email":"","orcid":"","institution":"University of Virginia","correspondingAuthor":false,"prefix":"","firstName":"Tobore","middleName":"V.","lastName":"Igbe","suffix":""},{"id":558707410,"identity":"c160e937-f898-426e-bcbc-e55a2e8b2d37","order_by":5,"name":"Abiola Ezekiel Taiwo","email":"","orcid":"","institution":"Mangosuthu University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Abiola","middleName":"Ezekiel","lastName":"Taiwo","suffix":""},{"id":558707427,"identity":"dfce384f-d334-4ed9-9683-318f8a0c15e5","order_by":6,"name":"Uchechukwu M. Chukwuocha","email":"","orcid":"","institution":"Federal University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Uchechukwu","middleName":"M.","lastName":"Chukwuocha","suffix":""}],"badges":[],"createdAt":"2025-10-23 13:38:24","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7932705/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7932705/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":98429448,"identity":"f1b36847-fb37-48bc-bfab-d89057fb0e82","added_by":"auto","created_at":"2025-12-17 16:43:29","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":602980,"visible":true,"origin":"","legend":"","description":"","filename":"manuscriptediteddiscoverhealth.docx","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/937e35f87b0e6733bf8f8f0d.docx"},{"id":98074485,"identity":"5253a587-a40d-4684-9172-78fbb7730cbf","added_by":"auto","created_at":"2025-12-12 13:27:42","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":8526,"visible":true,"origin":"","legend":"","description":"","filename":"0fa17e18298a43459df4e7c7b905dc51.json","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/a76297e9811a8c6b75dc1147.json"},{"id":98429836,"identity":"f9b7ac49-3fa0-4f19-89af-7d89080206f0","added_by":"auto","created_at":"2025-12-17 16:44:12","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":119745,"visible":true,"origin":"","legend":"","description":"","filename":"0fa17e18298a43459df4e7c7b905dc511enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/94d1f13e2c1dc14ccadf3bae.xml"},{"id":98428618,"identity":"012bc03b-a8f3-4867-9dcf-5f69a0ebbfd4","added_by":"auto","created_at":"2025-12-17 16:42:12","extension":"jpeg","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":145421,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/8cfee68e505ebaed61b5540f.jpeg"},{"id":98429069,"identity":"9b7a971c-2a78-4d1a-95f2-232f17b315a8","added_by":"auto","created_at":"2025-12-17 16:42:44","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":79485,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage10.png","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/a5cdab618ee0134a28807a25.png"},{"id":98429008,"identity":"0f1f78ea-8c8a-4a94-bafa-36e5d2b84e40","added_by":"auto","created_at":"2025-12-17 16:42:41","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":86819,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage11.png","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/a8f478846807e23e8b9508bd.png"},{"id":98074498,"identity":"5e04f5ee-c157-41c7-877b-18c5a4b95c20","added_by":"auto","created_at":"2025-12-12 13:27:42","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":48582,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage12.png","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/09ab2becd495e5f6f859ac3c.png"},{"id":98074501,"identity":"52361ea1-77cc-4eb8-97bf-b812e8768202","added_by":"auto","created_at":"2025-12-12 13:27:42","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":20365,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/d997ed14eb5fa600f964780d.png"},{"id":98429063,"identity":"623419f4-85ec-4fa0-9aa0-37d849f20951","added_by":"auto","created_at":"2025-12-17 16:42:44","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":34784,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/55adb141628423938932a5ab.png"},{"id":98429380,"identity":"26e5a996-aa02-411c-87ee-66fa0083586a","added_by":"auto","created_at":"2025-12-17 16:43:17","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":53910,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/b44a690504a95e0217467422.png"},{"id":98429124,"identity":"00ecc1d4-97f3-422f-ad60-57119343d030","added_by":"auto","created_at":"2025-12-17 16:42:49","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":51101,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/077c89a53936f003ef92d149.png"},{"id":98074507,"identity":"a59f8184-b02c-4cbc-9017-3d740dc00ff3","added_by":"auto","created_at":"2025-12-12 13:27:43","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":48838,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/221cd956b622ef6345d2bd26.png"},{"id":98074508,"identity":"f8ffe17b-1956-4c87-82fc-57a2139f34b1","added_by":"auto","created_at":"2025-12-12 13:27:43","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":129911,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/a5274cf4e6f93f14cca68188.png"},{"id":98429147,"identity":"71baf9d7-1783-44e8-8d2f-dd93530005dc","added_by":"auto","created_at":"2025-12-17 16:42:52","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":30084,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/8c9c3274d3a0abe3e2985188.png"},{"id":98429481,"identity":"b346fe25-c680-457c-b64f-2f900c3793d0","added_by":"auto","created_at":"2025-12-17 16:43:32","extension":"jpeg","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":87614,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage9.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/98cc5a91a2c8baa0ed8237cd.jpeg"},{"id":98428553,"identity":"87124b37-8f07-4fad-81b1-9e943143a771","added_by":"auto","created_at":"2025-12-17 16:42:08","extension":"jpeg","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":43935,"visible":true,"origin":"","legend":"","description":"","filename":"groupimage1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/ec9093e05f2bda9e7055945d.jpeg"},{"id":98074513,"identity":"a84ae0c0-3c29-4460-86db-ae418db57172","added_by":"auto","created_at":"2025-12-12 13:27:43","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":40503,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/06fdef9a18a53d1fd2f126af.png"},{"id":98429668,"identity":"134a8357-aa78-418a-b424-bae801ff8da7","added_by":"auto","created_at":"2025-12-17 16:43:59","extension":"png","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":16845,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage10.png","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/2af64d52a0e91ec8750bf0c6.png"},{"id":98429311,"identity":"ebd485c0-e153-4e3f-b978-448cf08c65cd","added_by":"auto","created_at":"2025-12-17 16:43:12","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":21382,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage11.png","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/01ce49edb02dcacb93bb2257.png"},{"id":98429591,"identity":"a8768cb0-9789-4cea-a3b4-71a2c61a2d49","added_by":"auto","created_at":"2025-12-17 16:43:48","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":13722,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage12.png","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/89ed10c090d925e9b5fd3fdc.png"},{"id":98074510,"identity":"4a4875ce-92e0-4b0b-bfc9-910322a8e534","added_by":"auto","created_at":"2025-12-12 13:27:43","extension":"png","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7783,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/f3a3f74dd18e76929f96cf2e.png"},{"id":98074515,"identity":"869e6e32-00c1-466b-9966-532bd35d7d9c","added_by":"auto","created_at":"2025-12-12 13:27:43","extension":"png","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":10774,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/089334595f81d28c554f6a4c.png"},{"id":98074511,"identity":"04de7589-5d5a-4e8f-ab00-532d30c5e136","added_by":"auto","created_at":"2025-12-12 13:27:43","extension":"png","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":13229,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/7d9716b8802de8b7880dd8a2.png"},{"id":98074512,"identity":"93c76959-8293-4be4-a361-2798390af3a9","added_by":"auto","created_at":"2025-12-12 13:27:43","extension":"png","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":12077,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/b818cdbc19b58bc8cb3c7b88.png"},{"id":98426740,"identity":"f3d06558-8774-42a0-ae26-cacf15e48ff0","added_by":"auto","created_at":"2025-12-17 16:38:28","extension":"png","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":12787,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/b4a69e23b7d2445d07b054ed.png"},{"id":98074516,"identity":"eafc1974-aa25-4186-9c75-6dec85f890ad","added_by":"auto","created_at":"2025-12-12 13:27:43","extension":"png","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":34469,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/c74c403ccc08ba77477be4c3.png"},{"id":98074518,"identity":"dc3996d6-aad5-4c0c-830d-9607161420c8","added_by":"auto","created_at":"2025-12-12 13:27:43","extension":"png","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":8187,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/1c4ceb3652a91beb6b74220a.png"},{"id":98429193,"identity":"08854b6b-fe5f-4a5b-99e3-4d8f71d9f7b4","added_by":"auto","created_at":"2025-12-17 16:42:57","extension":"png","order_by":27,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":17691,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/a304da44eff203a19317ad44.png"},{"id":98428960,"identity":"dd604868-5e99-4e2f-bc40-1cf337ee97b5","added_by":"auto","created_at":"2025-12-17 16:42:37","extension":"png","order_by":28,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":20881,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinegroupimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/e7aaa700bb508d6e8387a28f.png"},{"id":98074519,"identity":"3f8e99da-ef51-459f-88cf-1dac3d94c2e0","added_by":"auto","created_at":"2025-12-12 13:27:43","extension":"xml","order_by":29,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":116872,"visible":true,"origin":"","legend":"","description":"","filename":"0fa17e18298a43459df4e7c7b905dc511structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/0b78e5d82cdbef3d2b7df28c.xml"},{"id":98074523,"identity":"4e1da6dc-ab7a-41ba-827a-733230dd77ee","added_by":"auto","created_at":"2025-12-12 13:27:43","extension":"html","order_by":30,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":129022,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/9d6bc6296b3997c4b4bf3367.html"},{"id":98074482,"identity":"7460c959-0bf4-40f5-951d-6b7f686f5327","added_by":"auto","created_at":"2025-12-12 13:27:42","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":35239,"visible":true,"origin":"","legend":"\u003cp\u003eSystematic diagram describing the random forest algorithm workflow from data preprocessing to the final predictions.\u003c/p\u003e","description":"","filename":"1.png","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/999c072681cc72b6fa714f31.png"},{"id":98429054,"identity":"9b59bfad-3ec7-45e8-9ff1-32b4fc7afb17","added_by":"auto","created_at":"2025-12-17 16:42:43","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":72606,"visible":true,"origin":"","legend":"\u003cp\u003ePercentage of the sex distribution for \u003cstrong\u003e(a)\u003c/strong\u003e total data set \u003cstrong\u003e(b)\u003c/strong\u003e confirmed cases.\u003c/p\u003e","description":"","filename":"2.png","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/4d55c5baab03e54f2984ce25.png"},{"id":98074483,"identity":"0e3dc047-0538-4aa4-a220-f46095955631","added_by":"auto","created_at":"2025-12-12 13:27:42","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":28479,"visible":true,"origin":"","legend":"\u003cp\u003eFrequency of the age distribution from the complete data before analysis.\u003c/p\u003e","description":"","filename":"3.png","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/02363a058d3fee54a01d2a39.png"},{"id":98429048,"identity":"7b6fbd9b-f0b3-43ba-8404-29617d780d7d","added_by":"auto","created_at":"2025-12-17 16:42:43","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":66932,"visible":true,"origin":"","legend":"\u003cp\u003eAge distribution in confirmed, not contact and unconfirmed contacts.\u003c/p\u003e","description":"","filename":"4.png","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/c2c80eb12d39a547f63e16a6.png"},{"id":98429052,"identity":"d34b7b59-1638-4117-9209-4bf3c34e56e7","added_by":"auto","created_at":"2025-12-17 16:42:43","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":103796,"visible":true,"origin":"","legend":"\u003cp\u003eComposite bar chart showing the frequency of source cases grouped by age.\u003c/p\u003e","description":"","filename":"5.png","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/944b15e2864a3f884f6893ba.png"},{"id":98074492,"identity":"ff5d736c-010f-4940-b396-57c073250257","added_by":"auto","created_at":"2025-12-12 13:27:42","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":88462,"visible":true,"origin":"","legend":"\u003cp\u003eComposite bar chart showing the frequency of contacts grouped by age.\u003c/p\u003e","description":"","filename":"6.png","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/9de5298cac63ec34d560d381.png"},{"id":98429466,"identity":"26031bd7-0e4d-4813-9f4c-a48ae6e60637","added_by":"auto","created_at":"2025-12-17 16:43:30","extension":"png","order_by":7,"title":"Figure 7","display":"","copyAsset":false,"role":"figure","size":54458,"visible":true,"origin":"","legend":"\u003cp\u003eDistribution of confirmed cases from top 10 occupation/profession.\u003c/p\u003e","description":"","filename":"7.png","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/149d5beeacb9a2da09829deb.png"},{"id":98074499,"identity":"ae6d52c3-fc86-41ae-9b50-78ac9071ab2e","added_by":"auto","created_at":"2025-12-12 13:27:42","extension":"png","order_by":8,"title":"Figure 8","display":"","copyAsset":false,"role":"figure","size":198848,"visible":true,"origin":"","legend":"\u003cp\u003eSymptoms and age distribution.\u003c/p\u003e","description":"","filename":"8.png","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/325eaca6a6774256695e33e1.png"},{"id":98429261,"identity":"f3c3399b-b344-43c3-8d0d-1570a9fb1e81","added_by":"auto","created_at":"2025-12-17 16:43:03","extension":"png","order_by":9,"title":"Figure 9","display":"","copyAsset":false,"role":"figure","size":40784,"visible":true,"origin":"","legend":"\u003cp\u003eBoxplot analysis description of temperature for male and female \u003cstrong\u003e(a)\u003c/strong\u003eunconfirmed cases \u003cstrong\u003e(b) \u003c/strong\u003econfirmed cases.\u003c/p\u003e","description":"","filename":"9.png","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/fee893a808bccbe7ceceab41.png"},{"id":98074488,"identity":"2e44aa18-ac72-4ce0-b4d9-0fec213c1585","added_by":"auto","created_at":"2025-12-12 13:27:42","extension":"png","order_by":10,"title":"Figure 10","display":"","copyAsset":false,"role":"figure","size":88604,"visible":true,"origin":"","legend":"\u003cp\u003eDistribution of occupation by sex features.\u003c/p\u003e","description":"","filename":"10.png","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/612a29d81fe77399e5772a53.png"},{"id":98429512,"identity":"ce363fd3-4bce-47be-b208-ffeebca45619","added_by":"auto","created_at":"2025-12-17 16:43:35","extension":"png","order_by":11,"title":"Figure 11","display":"","copyAsset":false,"role":"figure","size":93605,"visible":true,"origin":"","legend":"\u003cp\u003eDistribution of temperature by occupation feature.\u003c/p\u003e","description":"","filename":"11.png","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/240eca01649ee6268ad66f5f.png"},{"id":98074504,"identity":"4ab752a3-47b0-48fb-8636-2a66e4da0253","added_by":"auto","created_at":"2025-12-12 13:27:43","extension":"png","order_by":12,"title":"Figure 12","display":"","copyAsset":false,"role":"figure","size":109812,"visible":true,"origin":"","legend":"\u003cp\u003eTemporal trends in the COVID-19 case.\u003c/p\u003e","description":"","filename":"12.png","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/60d99f0360a53d32a1619af4.png"},{"id":98444705,"identity":"ebcc03fe-357f-4067-9947-3fc403067513","added_by":"auto","created_at":"2025-12-17 17:17:00","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1856544,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7932705/v1/33efea1a-5cc2-4ddd-b20b-3419c4bf95bf.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Machine Learning Analysis of COVID19 Transmission Dynamics Demographic Risk and Contact Tracing Outcomes in Nigeria","fulltext":[{"header":"1. INTRODUCTION","content":"\u003cp\u003eThe COVID-19 pandemic has posed immense global health challenges, with transmission dynamics differing across regions and populations. Human-to-human transmission remains the primary driver for the rapid spread of the COVID-19 virus worldwide (Sankalpa et al., \u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e2024\u003c/span\u003e). The situation is difficult in most African (developing) countries due to limited human, financial, and material resources, and this raises serious concerns about the crisis response strategy put in place to mitigate the effects of the virus (Elimian et al., \u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e2020\u003c/span\u003e; Klein et al., \u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e2021\u003c/span\u003e).\u003c/p\u003e\u003cp\u003eNigeria's distinct demographic, socio-economic, and environmental factors significantly impact the spread of the COVID-19 pandemic. The country's high urban population density, young demographic, diverse healthcare infrastructure, and socio-cultural practices shape the course of the COVID-19 pandemic (Oluwasanmi et al., \u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e2021\u003c/span\u003e; Haque et al., \u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e2021\u003c/span\u003e). Understanding these patterns is crucial for effective public health responses, particularly in densely populated, resource-limited areas. Nigeria\u0026rsquo;s healthcare system faces several challenges, including underreporting of cases, limited testing in the early stages of the pandemic, and difficulties in enforcing containment measures, making it harder to track and model COVID-19 transmission (Ilesanmi and Afolabi, \u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e2020\u003c/span\u003e).\u003c/p\u003e\u003cp\u003eDespite these issues, there remains a notable gap in studies focusing on the transmission dynamics in Nigeria (Utulu et al.,2022; Ojji et al., \u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e2023\u003c/span\u003e). Most studies have concentrated on broader African trends or relied on data from other regions, leaving a significant gap in understanding Nigeria's unique context. Addressing this gap is crucial for developing targeted interventions, identifying country-specific risk factors, and improving resource allocation for current and future pandemics (Okonji et al., \u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e2022\u003c/span\u003e).\u003c/p\u003e\u003cp\u003eDue to the complexity and the large-scale nature of developing epidemiological models, machine learning (ML) has continuously gained attention for building outbreak prediction models. Several studies in Nigeria have employed ML techniques to predict and analyze COVID-19 transmission dynamics and outcomes. For instance, Ojo et al. (\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e2021\u003c/span\u003e) utilized a decision tree algorithm to model the spread of COVID-19 in Nigeria, providing insights into potential future cases based on various socio-economic and demographic factors. Their model highlighted key predictors of COVID-19 transmission, demonstrating the potential of ML in informing public health strategies. Similarly, Folorunso et al. (\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e2022\u003c/span\u003e) developed a machine learning model to forecast 14-day COVID-19 case trends in Nigeria, demonstrating that Support Vector Regressor (SVR) outperformed other algorithms in accuracy for public health planning 34. The study highlights the utility of ML in pandemic response by enabling data-driven predictions for government decision-making in Nigeria's unique epidemiological context. Moreover, Adebisi and Ogundipe (\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e2022\u003c/span\u003e) employed support vector machines (SVM) to forecast COVID-19 cases in Nigeria, focusing on data from various states. This study revealed spatial variations in transmission rates and highlighted the importance of localized predictions for effective resource allocation. In Oke et al. (\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e2023\u003c/span\u003e), a deterministic model was formulated to offer insight into the transmission dynamics of COVID-19 disease with the finding revealing that increasing vaccination coverage and decreasing vaccine waning rate facilitate the elimination of COVID-19. Additionally, Ojokoh et al. (\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e2022b\u003c/span\u003e) provides a comprehensive analysis of the COVID-19 pandemic across continents, including the techniques used to examine transmission patterns and evaluate intervention effectiveness. Their findings indicate that ML models can effectively predict COVID-19 cases, supporting public health strategies. Despite progress in research on COVID-19 transmission in Nigeria, notable gaps remain in the literature. A significant number of studies concentrate on specific regions or states, leading to a deficiency in comprehensive national models that account for the country's diverse demographics and socio-economic factors. Furthermore, there is a critical need to incorporate real-time data, such as mobility patterns and healthcare capacity, to enhance predictive accuracy. Additionally, while some research has explored the effects of various interventions, there is a lack of thorough evaluation regarding their long-term effectiveness utilizing ML frameworks. To address these gaps, this study investigates three core questions: (1) demographic and symptomatic risk factors, (2) temporal trends in transmission, and (3) the relationship between source cases and contacts. These questions aim to elucidate Nigeria-specific transmission dynamics to guide targeted interventions. Thus, this research aims to explore statistical and ML techniques in modelling and predicting COVID-19 cases in Nigeria. The study focuses on analyzing demographic data, symptom patterns, and contact tracing information to identify correlations and temporal trends related to disease transmission. By utilizing datasets from the National Centre for Disease Control (NCDC) using data from January 2020 through December 2021, and employing Pearson\u0026rsquo;s correlation, Analysis of Variance (ANOVA), Cramer\u0026rsquo;s V correlation, and the random forest (RF) classification model for prediction, the research seeks to enhance the understanding of COVID-19 spread and improve the effectiveness of containment measures in the context of Nigeria\u0026rsquo;s limited resources.\u003c/p\u003e"},{"header":"2. METHODS","content":"\u003cp\u003e\u003cb\u003e2.1\tETHICAL APPROVAL AND DATA SOURCE\u003c/b\u003e\u003c/p\u003e\u003cp\u003e Ethical clearance for this study was obtained from the National Health Research Ethics Committee (NHREC), Nigeria. Following approval, the dataset was provided by the Nigeria Centre for Disease Control (NCDC), the national public health authority responsible for detecting and managing infectious disease outbreaks in Nigeria. The dataset comprises COVID-19 cases reported from January 2020 to December 2021. The requirement for additional informed consent for this specific analysis was waived by the NHREC (ref #NHREC/01/01/2007-28/03/2023) because patients had previously provided written informed consent during their initial agreement, explicitly authorizing the use of their anonymized data for future research purposes. All data accessed were anonymized prior to analysis by removing all direct identifiers (including, but not limited to, names, addresses, medical record numbers, and exact dates of birth) and using unique study identifiers. This process ensured the authors could not access information that could identify individual participants.\u003c/p\u003e\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e\u003ch2\u003e2.2 DATA DESCRIPTION AND PREPROCESSING\u003c/h2\u003e\u003cp\u003eThe COVID-19 database contains the following information: Contact ID, Classification of the source case (categorized as Confirmed case, Not yet classified, Probable case, Not a case, Suspect case), Disease, Contact classification (categorized as Confirmed, Unconfirmed and Not a Contact), Date of first contact, Date of last contact, Sex, Age, Date of the report, Responsible state, Responsible LGA, Responsible ward, Contact status (categorized as Active contact, Converted to the case, Dropped), Follow-up status, Type of occupation (categorized as Laboratory staff, Healthcare worker, Pupil/student, Farmer, Other, Businessman/woman, Child, Housewife, Working with animals, Miner, Transporter, Religious leader, Traditional/spiritual healer, Hunter/trader of game meat, and Butcher), and Symptoms at last cooperative visit further cleaned up into Temperature, Headache, Runny nose, Fever, Nausea, Muscle pain, Chest pain, Cough, Acute respiratory distress syndrome, Diarrhea, Abdominal pain, Fatigue/general weakness, Sore throat/pharyngitis, Difficulty breathing/Dyspnea, Joint pain or arthritis, sleepless night, dryness of mouth, General weakness, Hypertension, Cough with sputum, New loss of smell, Discomfort around the chest region, Arthritis, Chills or sweats, Malaise, Rapid breathing, nose bleeding and chest pain, red eyes, Conjunctivitis, and stuffy nose.\u003c/p\u003e\u003cp\u003eTo address missing values in the dataset, different strategies were employed based on the nature of the variable. For categorical variables, such as classification of source case, contact classification, occupation, and contact status, missing values were labeled as \"Unknown.\" This ensures that all categories are represented, even if the specific information is missing, and allows for the inclusion of all data points in the analysis. For numerical variables, such as age and temperature, missing values were replaced with the mean of the respective columns. This approach preserves data distribution while minimizing bias.\u003c/p\u003e\u003cp\u003eMissing values in location information were handled by filling them with the mode of the respective columns, as the mode represents the most frequently occurring value and is a suitable imputation method for categorical data. Additionally, Missing values in symptom columns were imputed using forward filling (FFill), which propagates the last observed value. It is particularly useful in time-series data or when the outcomes are likely to persist over consecutive observations.\u003c/p\u003e\u003cp\u003eAll analyses were conducted using Python 3.11, leveraging a range of libraries such as Matplotlib for data visualization, NumPy for numerical operations, Seaborn for statistical data visualization, and Pandas for data manipulation and analysis. Sociodemographic characteristics (variables) that are categorical, such as sex, location, and occupation, are described using frequencies and percentages (%). This approach provides a clear and concise summary of the distribution of these categorical variables across the dataset for continuous variables that follow a normal distribution, such as age, the mean and standard deviation (SD) are provided. These measures offer insights into the central tendency and variability of the data, respectively.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec4\" class=\"Section2\"\u003e\u003ch2\u003e2.3 STATISTICAL ANALYSES\u003c/h2\u003e\u003cp\u003ePearson correlation and ANOVA tests were carried out to assess the correlation between sex and temperature.\u003c/p\u003e\u003cp\u003e\u003cstrong\u003ePearson Correlation\u003c/strong\u003e\u003cp\u003ePearson correlation measures the linear relationship between two continuous variables. The formula for the Pearson correlation coefficient r is\u003c/p\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv id=\"Equa\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equa\" name=\"EquationSource\"\u003e\n$$\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:r=\\frac{\\sum\\:({X}_{i}-X̅̅)({Y}_{i}-Y̅̅)}{\\sqrt{\\sum\\:{({X}_{i}-X̅̅)}^{2}{\\sum\\:({Y}_{i}-Y̅̅)}^{2}}}\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\:\\left(1\\right)$$\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003ewhere \u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{X}_{i}\\)\u003c/span\u003e\u003c/span\u003e​ and \u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{Y}_{i}\\)\u003c/span\u003e\u003c/span\u003e are the individual sample points, and X̅ and Y̅ are the mean values of the sample points. The significance level (α) is set at 0.05 to determine if the correlation is statistically significant.\u003c/p\u003e\u003cp\u003e\u003cstrong\u003eANOVA Test\u003c/strong\u003e\u003cp\u003eANOVA compares the means of two or more groups to see if at least one differs significantly. The F-statistics in ANOVA is calculated as\u003c/p\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv id=\"Equ1\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ1\" name=\"EquationSource\"\u003e\n$$\\:F=\\frac{Between-group\\:variability}{Within-group\\:variability}$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e2\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003eThe significance level (α) is set at 0.05 to determine if the differences between group means are statistically significant.\u003c/p\u003e\u003cp\u003e\u003cstrong\u003eCram\u0026eacute;r's V Correlation\u003c/strong\u003e\u003cp\u003eCram\u0026eacute;r's V measures the association between two categorical variables. The formula for Cram\u0026eacute;r's V is\u003c/p\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv id=\"Equ2\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ2\" name=\"EquationSource\"\u003e\n$$\\:V\\:=\\:\\sqrt{\\frac{{x}^{2}/n}{min(k-1,r-1)}}$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e3\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003eWhere \u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{x}^{2}\\)\u003c/span\u003e\u003c/span\u003e is the chi-squared statistic, \u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:n\\)\u003c/span\u003e\u003c/span\u003e is the total sample size, \u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:k\\)\u003c/span\u003e\u003c/span\u003e is the number of columns, and \u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:r\\)\u003c/span\u003e\u003c/span\u003e is the number of rows.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec5\" class=\"Section2\"\u003e\u003ch2\u003e2.4 MACHINE LEARNING PREDICTION\u003c/h2\u003e\u003cp\u003eThe RF classification model was used to predict the source case classification and the contact classification features of COVID-19 cases based on the other variables. RF model was selected for this study due to its superior performance in handling the specific challenges of Nigeria\u0026rsquo;s COVID-19 dataset. RF excels in managing categorical and mixed data types (e.g., occupation, symptoms) without extensive preprocessing, which is critical given the dataset\u0026rsquo;s heterogeneity. It also addresses class imbalance\u0026mdash;a common issue in epidemiological data\u0026mdash;through bootstrap sampling and class weighting, ensuring robust predictions for minority classes like \"Probable cases.\" Unlike models such as SVM or ANN, RF computational efficiency and interpretable feature importance scores, aligning with the study\u0026rsquo;s goal of identifying high-risk demographics and transmission drivers. Additionally, RF\u0026rsquo;s ensemble approach mitigates overfitting and noise, making it resilient to missing data and inconsistencies prevalent in Nigeria\u0026rsquo;s health records. These attributes make RF uniquely suited to model Nigeria\u0026rsquo;s COVID-19 dynamics while delivering actionable insights for public health strategies. Figure\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e describes the workflow of the RF algorithm.\u003c/p\u003e\u003cp\u003eThe dataset was split into training and test sets. A RF classifier was initialized and trained using the training set. The key parameter settings for the RF classifier include the number of Trees (\u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{n}_{estimators}\\)\u003c/span\u003e\u003c/span\u003e) set to 100, the random state (random_state) set to 42 to ensure reproducibility.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003eTo implement the RF algorithm as shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e, the first step involves selecting random samples from the given dataset. In our use case, 70% of the data is designated for training, while the remaining 30% is reserved for testing. This division ensures that the model is trained on a substantial portion of the data while also having a separate set for evaluating its performance. Once the training set is established, the RF algorithm constructs a multitude of decision trees, each based on a random subset of the training data. Each decision tree is built by selecting random features and using them to create splits that best separate the data according to the target variable. This process of creating multiple decision trees from different random samples and feature sets ensures that the model captures a diverse range of patterns in the data, thereby enhancing its robustness and accuracy.\u003c/p\u003e\u003cp\u003eAfter constructing the decision trees, the RF algorithm employs a voting mechanism to make predictions (Breiman, \u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e2001\u003c/span\u003e). Each tree in the forest predicts a given input, and these predictions are then aggregated. The voting was performed by taking the average of the predictions of the most frequent predictions. This collective decision-making process helps to mitigate the biases of individual trees and leads to a more accurate and reliable final prediction. The final prediction is determined by the majority vote among all the trees, ensuring that the most commonly predicted outcome by the ensemble of trees is chosen as the final result. This method not only improves prediction accuracy but also provides robustness against overfitting, as it leverages the contribution of multiple models rather than relying on a single decision tree.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec6\" class=\"Section2\"\u003e\u003ch2\u003e2.5 MODEL EVALUATION\u003c/h2\u003e\u003cp\u003eThe model's performance was evaluated on the test set using standard performance metrics as described in Eq.\u0026nbsp;\u003cspan refid=\"Equ3\" class=\"InternalRef\"\u003e4\u003c/span\u003e\u0026ndash;\u003cspan refid=\"Equ6\" class=\"InternalRef\"\u003e7\u003c/span\u003e. The precision indicates the proportion of true positive predictions out of all positive predictions made, recall measures the proportion of actual positives that are correctly identified by the model. F1-score is the harmonic mean of precision and recall.\u003cdiv id=\"Equ3\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ3\" name=\"EquationSource\"\u003e\n$$\\:Accuracy\\:=\\:\\frac{TP\\:+\\:TN}{TP\\:+\\:TN\\:+\\:FP\\:+\\:FN}$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e4\u003c/div\u003e\u003c/div\u003e\u003cdiv id=\"Equ4\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ4\" name=\"EquationSource\"\u003e\n$$\\:Precision\\:=\\:\\frac{TP}{TP\\:+\\:FP}$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e5\u003c/div\u003e\u003c/div\u003e\u003cdiv id=\"Equ5\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ5\" name=\"EquationSource\"\u003e\n$$\\:Recall\\:=\\:\\frac{TP}{TP\\:+\\:FN}$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e6\u003c/div\u003e\u003c/div\u003e\u003cdiv id=\"Equ6\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ6\" name=\"EquationSource\"\u003e\n$$\\:F1-Score\\:=\\:2\\cdot\\:\\frac{Precision\\:\\cdot\\:\\:Recall}{Precision\\:+\\:Recall}$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e7\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003ewhere TP\u0026thinsp;=\u0026thinsp;True Positives, TN\u0026thinsp;=\u0026thinsp;True Negatives, FP\u0026thinsp;=\u0026thinsp;False Positives, and FN\u0026thinsp;=\u0026thinsp;False Negatives\u003c/p\u003e\u003c/div\u003e"},{"header":"3. RESULTS","content":"\u003cdiv id=\"Sec8\" class=\"Section2\"\u003e\u003ch2\u003e3.1 DISTRIBUTION OF COVID-19 CASES ACROSS DEMOGRAPHICS\u003c/h2\u003e\u003cp\u003eThere are 100,627 individual records in the dataset. 76.69% were confirmed cases of COVID-19, 6.55% were Not a case, 3.21% were suspect cases, 0.17% (170/100,627) were Probable cases, 0.14% were Not yet classified, and 13.23% had missing values.\u003c/p\u003e\u003cp\u003eThe data distribution regarding contacts with current COVID-19 cases showed that 65.3% of the participants were confirmed contacts, 34.3% were unconfirmed contacts and 0.38% were not a contact category\u003c/p\u003e\u003cp\u003eFigures 2a and 2b show the distribution of the sex from the data. Males accounted for 51.3% and 51.8% of the confirmed COVID-19 cases. Females comprised 47.0% and 46.5% of the confirmed cases.\u003c/p\u003e\u003cp\u003eFigure \u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e3\u003c/span\u003e is a visualization of the age distributions of the data. Ages ranged from 0 to 120 years. The mean age of the study participants was 36.8 years and the mean age of persons with confirmed COVID-19 was 37.5 years. Figure\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e4\u003c/span\u003e illustrates the age distribution of the participants as contacts of COVID-19 cases.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003eFigures \u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e5\u003c/span\u003e and 6 are multivariate visualizations of the age distributions and other features of the COVID-19 data. Figure\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e5\u003c/span\u003e depicts the frequency of the source case classification by age, while Fig.\u0026nbsp;6 depicts the frequency of the contact case classification by age. Based on Figs.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e5\u003c/span\u003e and 6, the large number of confirmed cases shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e5\u003c/span\u003e, alongside the high number of confirmed contacts in Fig.\u0026nbsp;6, suggests a significant overlap between the two categories. This may indicate that many of the confirmed COVID-19 cases were indeed previously identified as confirmed contacts, highlighting the importance of contact tracing in identifying and managing cases of the virus. The strong presence of confirmed contacts leading to confirmed cases emphasizes the effectiveness of tracing as a critical tool in controlling the spread of infection.\u003c/p\u003e\u003cp\u003eThe distribution of participants with confirmed COVID-19 cases by their occupation is depicted in Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e7\u003c/span\u003e and summarized as follows: The Other category makes up 18.5% of the confirmed cases in the study participants. Pupils / students made up 13.6% of the confirmed COVID-19 cases. Healthcare workers accounted for 9.39% of the confirmed cases. Businessmen / women accounted for 4.59% of the confirmed cases. Housewives had 2.62%, Children had 2.24%, Farmers 2.10%. Laboratory staff 0.32%, Transporters 0.2%, animal workers 0.18%, Religious leader 0.14%, Hunter / trader of game meat 0.04%, Butcher 0.03% Traditional / spiritual healer 0.023%, and Miner 0.009%, accounted for 0.94% of the confirmed cases. There were 46% missing entries in the occupation field.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec9\" class=\"Section2\"\u003e\u003ch2\u003e3.2 SYMPTOM FREQUENCY ACROSS AGE GROUPS\u003c/h2\u003e\u003cp\u003eFigure \u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e8\u003c/span\u003e highlights the symptoms associated with COVID-19 as reported by participants. The most commonly reported symptoms at diagnosis included fever, cough, fatigue or general weakness and difficulty breathing or dyspnea. Other symptoms reported included headache, sore throat, muscle pain, and loss of taste or smell. The fever is more common to the 0\u0026ndash;18 and 36\u0026ndash;50 age group. Cough is more common to the 66\u0026thinsp;+\u0026thinsp;age group, while headache is higher in the 0\u0026ndash;18 age group, and less common among the other age groups.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec10\" class=\"Section2\"\u003e\u003ch2\u003e3.3 MULTIVARIATE ANALYSIS OF THE TEMPERATURE AND SEX FEATURES\u003c/h2\u003e\u003cp\u003eThe temperature distribution, as shown in Figs.\u0026nbsp;\u003cspan refid=\"Fig7\" class=\"InternalRef\"\u003e9\u003c/span\u003e (a) and (b) are quite similar for both Females and Males. Both groups have a minimum temperature of 35.0\u0026deg;C, median temperature of 36.2\u0026deg;C and a typical range of temperatures between 35\u0026deg;C and 38\u0026deg;C. Outliers indicate that there are a few individuals, particularly in the Male group, with temperatures above 39\u0026deg;C, suggesting potential cases of higher fever in the male group. These cases are reduced in the Confirmed cases indicating that fevers of higher than 39\u0026deg;C may not be COVID-19 cases.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003eThe Pearson correlation coefficient between sex and temperature is approximately \u0026minus;\u0026thinsp;0.0027, indicating a very weak negative correlation. This implies that there is almost no linear relationship between sex and temperature in the dataset. The ANOVA test yielded a p-value of 0.716, indicating no significant difference between sex and temperature. In other words, the variation in temperature does not appear to be significantly associated with the categories of sex in the dataset.\u003c/p\u003e\u003cp\u003eTherefore, based on the available data, there is no evidence to suggest that the average temperature differs significantly between different sexes. Therefore, based on the ANOVA test result, we cannot confidently conclude that there is a relationship between sex and temperature in the dataset.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec11\" class=\"Section2\"\u003e\u003ch2\u003e3.4 CORRELATION BETWEEN SEX AND OCCUPATION\u003c/h2\u003e\u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e shows the count of people by sex and occupation. Each row represents an occupation, and each column represents the counts of individuals based on sex. The categories \"Other,\" \"Pupil / student,\" and \"Healthcare worker\" have the highest counts, with both males and females significantly represented. For most occupations, Male category seems to have slightly higher or similar counts to females, except for Health care workers and \"Housewife,\" which have higher numbers of females. Occupations like \"Butcher,\" \"Working with animals,\" and \"Miner\" have very few individuals represented.\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eDistribution of participants by sex and occupation in confirmed COVID-19 cases\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"5\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eOccupation\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eFemale\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eMale\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eOther\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eUnknown\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eBusinessman/woman\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1575\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e1956\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e13\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eButcher\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e20\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eChild\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e823\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e901\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e5\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eFarmer\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e438\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e1178\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e2\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eHealthcare worker\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e4385\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e2843\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e23\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eHousewife\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1908\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e112\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e3\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eHunter / trader of game meat\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e16\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e15\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLaboratory staff\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e126\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e120\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMiner\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eOther\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e5237\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e9011\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e32\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePupil / student\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e5040\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e5394\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e27\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eReligious leader\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e14\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e91\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eTraditional / spiritual healer\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e12\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eTransporter\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e13\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e141\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eWorking with animals\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e131\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003eThe correlation matrix in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e shows the relationship between the counts of people for each sex in each occupation. There is a strong positive correlation (0.89) between the counts of females and males across occupations. This suggests that occupations with a higher count of females also tend to have a higher count of males, and vice versa. Similarly, there is a high number of correlations between the Male and Unknown and the Female and Unknown sex groups indicating that occupations with high numbers of male also show high numbers of female and Unknown.\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eCorrelation matrix by sex for different occupations\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"5\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSex\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eFemale\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eMale\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eOther\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eUnknown\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eFemale\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.892942\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.430255\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.973726\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eMale\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.892942\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.375904\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.940313\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eOther\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.430255\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.375904\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.396836\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eUnknown\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.973726\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.940313\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.396836\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003eThe correlation value of 4402.3445 for Cram\u0026eacute;r's V between sex and occupation indicates a strong association between the sex and occupational variables. Therefore, this further suggests that there is a significant relationship between sex and occupation in the dataset.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec12\" class=\"Section2\"\u003e\u003ch2\u003e3.5 CORRELATION BETWEEN OCCUPATION AND TEMPERATURE FOR CONFIRMED CONTACTS\u003c/h2\u003e\u003cp\u003eFigure \u003cspan refid=\"Fig9\" class=\"InternalRef\"\u003e11\u003c/span\u003e shows the distribution of temperature across occupations. For most occupations, the median temperatures are between 36\u0026deg;C and 37\u0026deg;C, indicating a similar central tendency for body temperature across different jobs.\u003c/p\u003e\u003cp\u003e\u0026ldquo;Working with animals\" shows a lower median temperature, while occupations like \u0026ldquo;Businessman / women\", \u0026ldquo;Pupil / student\u0026rdquo; and \"Farmer\u0026rdquo; have high spread in temperature values, with more pronounced outliers. \"Transporter\" and \"Traditional / spiritual healer\", \u0026ldquo;Butcher\u0026rdquo; and \"Hunter / trader of game meat\u0026rdquo; appear to have slightly higher median temperatures compared to other occupations, potentially indicating a variation in body temperature trends within these groups. Certain occupations, such as \"Butcher\" and \"Traditional / spiritual healer,\" show narrow interquartile ranges, suggesting less variability in body temperature for these groups.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eDistribution of the temperature across various occupations\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"6\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eOccupation\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eMedian\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eIQR\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eMin\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eMax\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003eOutliers\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eBusinessman/woman\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e36.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e34.95\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e37.75\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e43\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eButcher\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e36.6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e36.15\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e36.95\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eChild\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e36.2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.8\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e34.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e37.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e4\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eFarmer\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e36.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e1.1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e33.95\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e38.35\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eHealthcare worker\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e36.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.725\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e34.7875\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e37.6875\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e11\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eHousewife\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e36.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e34.2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e38.2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eHunter/trader of game meat\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e36.55\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.575\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e35.4625\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e37.7625\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLaboratory staff\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e36.35\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.675\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e34.9125\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e37.6125\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMiner\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e36.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e35.325\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e37.725\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eOther\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e36.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.8\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e34.6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e37.8\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e11\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePupil / student\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e36.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.8\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e34.6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e37.8\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e16\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eReligious leader\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e36.1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.625\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e34.8375\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e37.3375\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eTraditional / spiritual healer\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e36.45\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.225\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e35.9625\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e36.8625\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eTransporter\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e36.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e34.65\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e38.25\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eWorking with animals\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e35.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e34.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e36.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e4\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003eAn analysis of the occupation and temperature features for confirmed contacts of COVID-19 was done with Kruskal-Wallis H test. The p-value obtained from the Kruskal-Wallis H test is 3.28 \u0026times; 10\u003csup\u003e\u0026minus;\u0026thinsp;28\u003c/sup\u003e, suggesting that there is a significant difference in the distribution of temperature across different categories of occupation, therefore, variation in temperature is associated with the categories of occupation in the dataset.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec13\" class=\"Section2\"\u003e\u003ch2\u003e3.6 DISTRIBUTION OF CLASSIFICATION OF CONTACTS BY CLASSIFICATION OF SOURCE CASES\u003c/h2\u003e\u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e illustrates the association between \"classification of source cases\" and \"classification of contacts\" in COVID-19 cases. The majority of confirmed contacts were categorized as confirmed cases, totaling 58,160. The numbers of confirmed contacts in other categories were considerably lower, with 2,264 classified as not a case, 606 as suspect cases, and 156 as probable cases. Among unconfirmed contacts, a significant portion were identified as confirmed cases 18,704 and suspect cases 2,615, with additional classifications including 4,309 as not a case, 14 as probable cases, and 84 as not yet classified. For the not a contact category, there were 309 confirmed cases, 27 classified as not a case, and 5 as suspect cases.\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab4\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 4\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eDistribution of classification of contacts by classification of source cases.\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"7\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colspan=\"5\" nameend=\"c7\" namest=\"c3\"\u003e\u003cp\u003eClassification of the source case\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eConfirmed case\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eNot a case\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eNot yet classified\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eProbable case\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eSuspect case\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e\u003cp\u003e\u003cb\u003eContact classification\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cb\u003eConfirmed contact\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e58160\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e2264\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e56\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e156\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e606\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cb\u003eNot a contact\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e309\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e27\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e5\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cb\u003eUnconfirmed contact\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e18704\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e4309\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e84\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e14\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e2615\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cb\u003e3.7 RESULTS ON THE RANDOM FOREST MODEL PREDICTIONS FOR SOURCE CASE CLASSIFICATION\u003c/b\u003e\u003c/p\u003e\u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab5\" class=\"InternalRef\"\u003e5\u003c/span\u003e shows the confusion matrix of RF model predictions for source case classification while Table\u0026nbsp;\u003cspan refid=\"Tab6\" class=\"InternalRef\"\u003e6\u003c/span\u003e gives the classification report of the model in predicting the source case classes with accuracy of 87%. The classification report provides the metrics to evaluate the performance of the RF classifier.\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab5\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 5\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eConfusion matrix of random forest model predictions for source case classification\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"1\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colspan=\"8\" nameend=\"c8\" namest=\"c1\"\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"No\" id=\"Taba\" border=\"1\"\u003e\u003ccolgroup cols=\"8\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colspan=\"8\" nameend=\"c8\" namest=\"c1\"\u003e\u003cp\u003eConfusion Matrix:\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"5\" rowspan=\"6\"\u003e\u003cp\u003eActual\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eConfirmed case\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e22079\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e439\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e300\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e375\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eSuspect case\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e992\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e742\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e182\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e53\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eProbable case\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e22\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eNot yet classified\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e26\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e24\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eNot a case\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e299\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e151\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e477\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e15\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eUnknown\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e1018\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e20\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e2949\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eConfirmed case\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eSuspect case\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eProbable case\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eNot yet classified\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eNot a case\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eUnknown\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colspan=\"6\" nameend=\"c8\" namest=\"c3\"\u003e\u003cp\u003ePredicted\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab6\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 6\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eClassification report of the random forest model in predicting source case classification of COVID-19.\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"5\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colspan=\"5\" nameend=\"c5\" namest=\"c1\"\u003e\u003cp\u003eClassification Report\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003ePrecision\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eRecall\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eF1-score\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eSupport\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eConfirmed case\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.95\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.93\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e23198\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSuspect case\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.55\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.38\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.45\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e1969\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eProbable case\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.56\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.15\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.23\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e34\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNot yet classified\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.92\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.45\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.61\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e53\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNot a case\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.49\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.51\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e942\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eUnknown\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.87\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.74\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.8\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e3992\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eaccuracy\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.87\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e30188\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003emacro average\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.72\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.53\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.59\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e30188\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eweighted average\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.86\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.87\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.86\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e30188\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003eThe classification report provides the metrics to evaluate the performance of the RF classifier. Support shows the number of actual occurrences of each class in the test set.\u003c/p\u003e\u003cp\u003eThe Confirmed case class has the largest number of participants (23,198). The model achieves 90% precision and 95% recall for this class, indicating robust performance.. Precision: 0.90, Recall: 0.95, F1-score: 0.93. The Suspect case class has 1969 participants. The precision indicates that 55% of the predictions for this class are correct, but the recall is relatively low (38%), suggesting that the model misses many actual instances of this class. Precision: 0.55, Recall: 0.38, F1-score: 0.45. The Probable case class has 34 participants. The model exhibits a low recall (15%) for this class, likely due to data scarcity. Precision: 0.56, Recall: 0.15, F1-score: 0.23. The Not yet classified class has 53 participants. The model has a high precision (92%) but a much lower recall (45%), indicating that it is good at predicting this class when it does, but it often fails to recognize actual instances. Precision: 0.92, Recall: 0.45, F1-score: 0.61. The Not a case class has 942 participants. This class is balanced in terms of precision and recall, but both are relatively low, suggesting room for improvement. Precision: 0.49, Recall: 0.51, F1-score: 0.50. This Unknown class has 3992 participants. The model performs reasonably well on this class, with both precision and recall being above 70%. Precision: 0.87, Recall: 0.74, F1-score: 0.80\u003c/p\u003e\u003cp\u003eOverall, the accuracy of 87% was obtained. The weighted precision, recall, and F1-score are 0.86, 0.87, 0.86, indicating that overall performance is quite good, mainly due to the high number of confirmed case participants in the data. Thus, the model performs well on the majority class (confirmed case), but struggles with some minority classes (e.g., Probable case and Not yet classified).\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec14\" class=\"Section2\"\u003e\u003ch2\u003e3.9 TEMPORAL TRENDS IN THE COVID-19 CASES\u003c/h2\u003e\u003cp\u003eFigure \u003cspan refid=\"Fig10\" class=\"InternalRef\"\u003e12\u003c/span\u003e shows how the number of COVID-19 cases fluctuated over time, starting from mid-2019 and ending in early 2022. In the initial period between 2019-05 to 2020-01, there was little to no activity until early 2020, reflecting the pre-pandemic period when COVID-19 cases were not reported, or the disease had not yet widely spread. The first surge noted was between 2020-05 and 2020-10 where a significant spike in cases is seen in 2020-06, peaking around the third quarter of 2020. The number of cases rapidly increased, reaching over 4000 cases at the peak. A decline and fluctuation was noted from 2020-10 to 2021-01. After reaching its peak, there was a steep drop in the number of cases towards the end of 2020 and the beginning of 2021, though some small peaks are still observed during this period. Another increase is visible around early 2021, which led to the second wave between 2021-01 and 2021-05, leading to another peak in 2021-03 reaching about 2000 cases. There is noticeable fluctuation during 2021, with periodic increases and decreases, suggesting possible effects of new variants, waves, or public health measures being applied and lifted. A decline was observed toward the end of 2021, between 2021-09 and 2022-01. The number of cases continued to fall towards the end of 2021 and reached close to zero by early 2022.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e"},{"header":"4. DISCUSSION","content":"\u003cp\u003eThis study examined the demographic and occupational risk factors, temporal trends and policy implications, and source-contact dynamics and ML utility linked to COVID-19 infection rates and mortality in Nigeria. The findings from this study provide important insights into the dynamics of COVID-19 transmission within Nigeria and highlight the critical role that underscore the significance of using ML techniques for disease outbreak prediction and containment.\u003c/p\u003e\u003cp\u003eNigeria\u0026rsquo;s unique socio demographic landscape, characterized by a youthful population (median age of 36.8 years), high urban density, and uneven healthcare access\u0026mdash;shaped the uneven distribution of COVID-19 cases. The concentration of infections among younger age groups (10\u0026ndash;39 years) aligns with the country\u0026rsquo;s demographic profile, where over 60% of the population is under 25. However, this contrasts with global patterns where older adults faced higher risks, suggesting that Nigeria\u0026rsquo;s younger population may have experienced greater exposure due to urban crowding, informal work dependencies, or reduced adherence to containment measures. Occupations such as healthcare workers (9.39% of cases) and students (13.6%) emerged as high-risk groups, likely due to prolonged exposure in hospitals and crowded educational institutions. These findings mirror studies by Adepoju (\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2020\u003c/span\u003e), who linked urban density in Lagos and Kano to rapid transmission. Symptom patterns further revealed gaps in surveillance: while fever and cough were widely reported, atypical markers like anosmia (loss of smell) were underrecognized, potentially delaying diagnosis. This underscores the need for symptom screening protocols tailored to Nigeria\u0026rsquo;s resource-limited clinics, where rapid testing remains scarce.\u003c/p\u003e\u003cp\u003eThe temporal analysis identified two distinct COVID-19 waves: a mid-2020 surge (peaking at 4,000\u0026thinsp;+\u0026thinsp;cases) and a smaller 2021 resurgence, followed by a decline to near-zero cases by early 2022. The first wave coincided with Nigeria\u0026rsquo;s initial lockdown relaxation in June 2020, which prioritized economic recovery over sustained restrictions\u0026mdash;a trade-off common in low-income countries. The second wave aligned with the global spread of the Delta variant and seasonal gatherings (e.g., December holidays), highlighting the vulnerability of Nigeria\u0026rsquo;s under-vaccinated population (only 3% fully vaccinated by late 2021). The sharp decline by 2022 likely reflects natural immunity from prior infections rather than vaccination success, given Nigeria\u0026rsquo;s slow rollout. These trends emphasize the need for adaptive public health policies: aggressive containment during surges (e.g., targeted lockdowns, mask mandates) and post-peak investments in healthcare infrastructure to mitigate future outbreaks. The findings emphasized the importance of balancing economic and health priorities in Nigeria\u0026rsquo;s pandemic response.\u003c/p\u003e\u003cp\u003e The strong link between confirmed contacts and cases (94.97% positivity) validates contact tracing as a critical tool in Nigeria\u0026rsquo;s response, consistent with WHO guidelines (2020). However, the 309 confirmed cases in the \u0026ldquo;not a contact\u0026rdquo; category signal pervasive community transmission, likely exacerbated by underreporting and limited testing in rural areas. The RF model achieved 87% accuracy in predicting source classifications, demonstrating machine learning\u0026rsquo;s potential to optimize contact tracing in resource-constrained settings. However, its poor performance on minority classes (e.g., \u003cem\u003eProbable cases\u003c/em\u003e: 15% recall) reflects challenges common to Nigerian datasets: imbalanced classes, missing occupation data (35,542 entries), and inconsistent reporting. To enhance predictive power, future models could integrate real-time mobility data or employ synthetic oversampling techniques (e.g., SMOTE) for underrepresented classes. These improvements could help policymakers prioritize testing in high-risk occupations or regions, as suggested by Ojokoh et al. (\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e2022a\u003c/span\u003e) in their continental analysis of contact tracing efficacy.\u003c/p\u003e"},{"header":"5. CONCLUSION","content":"\u003cp\u003eThis study highlights COVID-19 transmission dynamics in Nigeria through statistical analyses and machine learning, addressing three research questions critical to understanding the pandemic\u0026rsquo;s unique trajectory in a resource-limited setting. First, demographic analysis revealed that younger age groups (10\u0026ndash;39 years) and occupations such as healthcare workers (9.39% of cases) and students (13.6%) faced heightened risks, likely due to Nigeria\u0026rsquo;s youthful population density and exposure in high-contact environments like schools and hospitals. Symptom patterns further highlighted gaps in screening protocols, with fever and cough dominating reports, while atypical markers like loss of smell were underrecognized. Second, temporal trends identified two distinct waves: a mid-2020 surge peaking at over 4,000 cases, likely tied to early pandemic unpreparedness, and a smaller 2021 resurgence coinciding with variant emergence and relaxed restrictions. By early 2022, cases declined sharply, reflecting cumulative immunity from vaccination and prior infections. Third, the relationship between source cases and contacts was rigorously analyzed using a RF model, which achieved 87% accuracy in classifying confirmed cases. However, its limitations in predicting minority classes (e.g., 15% recall for Probable cases) underscored challenges posed by imbalanced data. Strikingly, 94.97% of confirmed contacts tested positive, validating contact tracing\u0026rsquo;s efficacy, while 309 cases in the \u0026ldquo;not a contact\u0026rdquo; category signaled pervasive community transmission.\u003c/p\u003e\u003cp\u003eThese findings advance Nigeria-specific pandemic insights by prioritizing high-risk demographics, linking transmission peaks to policy gaps, and demonstrating machine learning\u0026rsquo;s potential in outbreak prediction despite data constraints. Practical implications include prioritizing healthcare workers and students for testing, dynamically adjusting public health measures during surges, and improving data quality to refine predictive models. Future work should integrate mobility patterns, genomic surveillance, and socioeconomic variables to enhance real-time modeling, while community engagement campaigns could address underreporting in rural areas. Further tuning, such as adjusting class weights or using different techniques for imbalanced data, could help improve performance for the minority classes. By bridging gaps in localized transmission analytics, this study underscores the value of tailored, data-driven strategies to mitigate COVID-19\u0026rsquo;s burden in resource-constrained settings and offers a framework for future pandemic preparedness.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eFunding:\u003c/strong\u003e This work was supported by the Nigerian Tertiary Education Trust Fund (TETFund) through the National Research Fund [Grant Number NRF/SETI/ICT/00029].\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eClinical trial registration:\u003c/strong\u003e Not applicable.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eData availability:\u003c/strong\u003e This work utilizes data from the Nigeria Centre for Disease Control and Prevention (NCDCP). Due to data sharing restrictions, the raw data cannot be disseminated by the authors. However, individuals or institutions seeking access may submit a formal request to the NCDCP for approval.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthors’ contributions:\u003c/strong\u003e Bolanle Adefowoke Ojokoh, Oluwafemi A. Sarumi, Sadura Priscilla Akinrinwa, and Abimbola H. Afolayan \u0026nbsp;made substantial contributions to the conception or design of the work, or the acquisition, analysis, or interpretation of data for the work.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eBolanle Adefowoke Ojokoh, Oluwafemi A. Sarumi, and Tobore V. Igbe contributed to drafting the work or revising the draft critically for important intellectual content\u003c/p\u003e\n\u003cp\u003eUchechukwu M. Chukwuocha helped with the ethical clearance process.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCompeting interests:\u003c/strong\u003e The authors have no competing interests in declaring for this study.\u003c/p\u003e"},{"header":"References","content":"\u003cp\u003eAdebisi, A. A., \u0026amp; Ogundipe, A. E. (2022). Forecasting COVID-19 cases in Nigeria using support vector machines. \u003cem\u003eNigerian Journal of Computer Science, 10\u003c/em\u003e(1), 52–64. Available at:https://doi.org/10.2139/njcs.2022.1.5\u003c/p\u003e\n\u003cp\u003eAdepoju, P. (2020). \"Nigeria’s COVID-19 response: The Lagos and Kano experience.\" The Lancet Global Health, 8(10), e1240-e1241. Available at: DOI: 10.1016/S2214-109X(20)30315-6\u003c/p\u003e\n\u003cp\u003eBreiman, L. (2001). Random forests. \u003cem\u003eMachine Learning, 45\u003c/em\u003e(1), 5–32. Available at: https://doi.org/10.1023/A:1010933404324\u003c/p\u003e\n\u003cp\u003eElimian, K. O., Ochu, C. L., Ebhodaghe, B., Myles, P., Crawford, E. E., Igumbor, E., Ukponu, W., Olayinka, A., Aruna, O., Dan-Nwafor, C., Olawepo, O. A., Ogunbode, O., Atteh, R., Nwachukwu, W., Venkatesan, S., Obagha, C., Ngishe, S., Suleiman, K., Usman, M., Yusuff, H. A., Nwadiuto, I., Mohammed, A. A., Usman, R., Mba, N., Aderinola, O., Ilori, E., Oladejo, J., Abubakar, I., \u0026amp; Ihekweazu, C. (2020). Patient characteristics associated with COVID-19 positivity and fatality in Nigeria: Retrospective cohort study. \u003cem\u003eBMJ Open, 10\u003c/em\u003e, e044079. Available at: https://doi.org/10.1136/bmjopen-2020-044079\u003c/p\u003e\n\u003cp\u003eFolorunso, S. O., Ogundepo, E. A., Awotunde, J. B., Ayo, F. E., Banjo, O. O., \u0026amp; Taiwo, A. I. (2022). A multi-step predictive model for COVID-19 cases in Nigeria using machine learning. In Decision Sciences for COVID-19: Learning Through Case Studies (pp. 107-136). Cham: Springer International Publishing. Available at: DOI: 10.1007/978-3-030-87019-5_7\u003c/p\u003e\n\u003cp\u003eHaque, M., Abubakar, A., Ogunleye, O., Sani, I., Sefah, I., Kurdi, A., et al. (2021). Changes in availability, utilization, and prices of medicines and protection equipment for COVID-19 in an urban population of Northern Nigeria. \u003cem\u003eJournal of Research in Pharmacy Practice, 10\u003c/em\u003e(1), 17. Available at:https://doi.org/10.4103/jrpp.JRPP_20_92\u003c/p\u003e\n\u003cp\u003eIlesanmi, O. S., \u0026amp; Afolabi, A. A. (2020).\"Learning from the challenges of COVID-19 in Nigeria: A systematic review of the country’s response and lessons for future pandemics.\" International Journal of Infectious Diseases, 101, 316-323. Available at: DOI: 10.1016/j.ijid.2020.09.1462\u003c/p\u003e\n\u003cp\u003eKlein, H., Asseo, K., Karni, N., Benjamini, Y., Nir-Paz, R., Muszkat, M., Israel, S., \u0026amp; Niv, M. Y. (2021). Onset, duration, and unresolved symptoms, including smell and taste changes, in mild COVID-19 infection: A cohort study in Israeli patients. \u003cem\u003eClinical Microbiology and Infection, 27\u003c/em\u003e, 769–774. Available at: https://doi.org/10.1016/j.cmi.2021.02.008\u003c/p\u003e\n\u003cp\u003eOluwasanmi, O. O., Akinokun, R. T., Ilesanmi, O. S., \u0026amp; Akinyemi, J. O. (2021). \"COVID-19 in Nigeria: A disease of inequality and the struggle for containment in a weak health system.\" Journal of Global Health, 11, 03063. Available at: DOI: 10.7189/jogh.11.03063\u003c/p\u003e\n\u003cp\u003eOjji, D. B., Shedul, G. L., Orji, I. A., Abu, J., Akor, B., Ripiye, N., \u0026amp; Huffman, M. D. (2023). Nigeria healthcare worker SARS-CoV-2 serology study: Results from a prospective, longitudinal cohort. \u003cem\u003ePLOS Global Public Health\u003c/em\u003e. Available at:https://doi.org/10.1371/journal.pgph.0000549\u003c/p\u003e\n\u003cp\u003eOjo, J. A., Owoeye, O. D., \u0026amp; Olawale, J. K. (2021). Predicting COVID-19 transmission in Nigeria using machine learning techniques. \u003cem\u003eJournal of Health Informatics in Developing Countries, 14\u003c/em\u003e(2), 115–126. Available at:https://doi.org/10.21633/jhidc.v14i2.825\u003c/p\u003e\n\u003cp\u003eOjokoh, B. A., Aribisala, B., Sarumi, O. A., Gabriel, A. J., Omisore, O., Taiwo, A. E., \u0026amp; …, Afolabi, O. (2022a). Contact tracing strategies for COVID-19 prevention and containment: A scoping review. \u003cem\u003eBig Data and Cognitive Computing, 6\u003c/em\u003e(4), 111. Available at:https://doi.org/10.3390/bdcc6040111\u003c/p\u003e\n\u003cp\u003eOjokoh, B. A., Sarumi, O. A., Salako, K. V., Gabriel, A. J., Taiwo, A. E., Johnson, O. V., \u0026amp; Babalola, O. T. (2022b). Modelling and predicting the spread of COVID-19: A continental analysis. In \u003cem\u003eData Science for COVID-19\u003c/em\u003e (pp. 299–317). Academic Press. Available at: https://doi.org/10.1016/B978-0-323-90769-9.00039-6\u003c/p\u003e\n\u003cp\u003eOke, I. I., Idisi, T. T., Yusuf, K. M., Owolabi, B. A., \u0026amp; Ojokoh, B.A. (2023). A bifurcation analysis and model of COVID-19 transmission dynamics with post-vaccination infection impact. \u003cem\u003eHealthcare Analytics, 3\u003c/em\u003e, 100157. Available at: https://doi.org/10.1016/j.health.2023.100157 \u003c/p\u003e\n\u003cp\u003eOkonji, E. F., Okonji, O. C., Mukumbang, F. C., \u0026amp; Van Wyk, B. (2022).\"Understanding the varying COVID-19 mortality rates across Africa: A comparative analysis of South Africa, Egypt, and Nigeria.\" BMC Public Health, 22, 1817. Available at: DOI: 10.1186/s12889-022-14236-z\u003c/p\u003e\n\u003cp\u003eSankalpa, D., Dhou, S., Pasquier, M., \u0026amp; Sagahyroon, A. (2024). Predicting the spread of a pandemic using machine learning: a case study of COVID-19 in the UAE. \u003cem\u003eApplied Sciences\u003c/em\u003e, \u003cem\u003e14\u003c/em\u003e(10), 4022. Available at: https://doi.org/10.3390/app14104022\u003c/p\u003e\n\u003cp\u003eUtulu, R., Ajayi, I. O., Bello, S., Balogun, M. S., Madubueze, U. C., Adeyemi, I. T., Omoju, O. T., Adeke, A. S., Adenekan, A. O., \u0026amp; Iyare, O. (2022). Risk factors for COVID-19 infection and disease severity in Nigeria: A case-control study. \u003cem\u003ePan African Medical Journal, 41\u003c/em\u003e(317). Available at: https://www.panafrican-med-journal.com//content/article/41/317/full\u003c/p\u003e\n\u003cp\u003eWorld Health Organization. (2020). Contact tracing in the context of COVID-19. Retrieved fromhttps://www.who.int/publications/i/item/contact-tracing-in-the-context-of-covid-19\u003c/p\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"discover-public-health","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Discover Public Health](https://link.springer.com/journal/12982)","snPcode":"12982","submissionUrl":"https://submission.springernature.com/new-submission/12982/3","title":"Discover Public Health","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Discover Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"COVID-19 transmission dynamics, Machine learning prediction, Demographic risk factors, Nigeria pandemic response, Contact tracing efficacy, Public health policy optimization","lastPublishedDoi":"10.21203/rs.3.rs-7932705/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7932705/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe COVID-19 pandemic has posed significant challenges to developing countries like Nigeria due to limited resources. Accurate prediction of disease spread is crucial for effective containment measures. This study investigates the application of statistical and machine learning (ML) techniques in modelling and predicting COVID-19 cases in Nigeria, using data from January 2020 through December 2021. By analyzing demographic data (age, gender, location), symptom patterns, and contact tracing information, we seek to identify correlations and temporal trends associated with disease transmission. The datasets, obtained from the National Centre for Disease Control (NCDC), were cleaned before statistical analyses were carried out with Pearson\u0026rsquo;s Correlation, Analysis of Variance, and Cramer\u0026rsquo;s V Correlation. Prediction was carried out using the random forest (RF) classification model, implemented in Python's scikit learn library. Key findings include (1) 94.97% of confirmed contacts tested positive, underscoring high transmission rates; (2) occupations like healthcare workers and students were high-risk groups; and (3) the RF model achieved 87% accuracy in classifying source cases, though it struggled with minority classes. These can inform evidence-based policymaking and contribute to mitigating the impact of future outbreaks. A limitation of this study is the dependence on the accuracy of the NCDC data.\u003c/p\u003e","manuscriptTitle":"Machine Learning Analysis of COVID19 Transmission Dynamics Demographic Risk and Contact Tracing Outcomes in Nigeria","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-12 13:27:35","doi":"10.21203/rs.3.rs-7932705/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-03-01T12:17:25+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-12T20:43:36+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"104354838731917272188357537314699385990","date":"2026-02-06T04:59:43+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-01-21T19:30:59+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"284432935105691095558743121176808084640","date":"2026-01-16T08:25:50+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"34891213334103052359633473412147699454","date":"2026-01-07T14:06:46+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-17T13:24:26+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"301964946037586657712299543714383991818","date":"2025-12-17T12:54:37+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"45742788351616361510772383931934124606","date":"2025-12-11T09:03:26+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-12-09T08:50:54+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-12-02T12:32:55+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-11-30T11:43:08+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-11-26T11:27:02+00:00","index":"","fulltext":""},{"type":"submitted","content":"Discover Public Health","date":"2025-11-26T11:22:31+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"discover-public-health","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Discover Public Health](https://link.springer.com/journal/12982)","snPcode":"12982","submissionUrl":"https://submission.springernature.com/new-submission/12982/3","title":"Discover Public Health","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Discover Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"fc2bd3e7-4865-439e-9fa5-16c6f4a551e3","owner":[],"postedDate":"December 12th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-05T04:08:26+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-12 13:27:35","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7932705","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7932705","identity":"rs-7932705","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}