Time Series Analysis for forecasting neonatal intensive care unit census and neonatal mortality

Time Series Analysis for forecasting neonatal intensive care unit census and neonatal mortality | 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 Time Series Analysis for forecasting neonatal intensive care unit census and neonatal mortality Hosein Dalili, Mamak Shariat, Leyla Sahebi This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4606104/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 3 You are reading this latest preprint version Abstract Background : Neonatal intensive care units(NICUs) play a crucial role in caring for premature or critically ill newborns, but challenges persist in managing patient volumes and addressing mortality. This study aims to analyze the time series of the NICU admission numbers, hospitalization days, and mortality proportion. Methods: We used seven years of retrospective daily NICU census data for model development (March 2016 - December 2022, N=7,216 infants). Best-fitting models of ARIMA and SARIMA were applied for forecasting admission number, long stay and mortality proportion in STATA.14 and SPSS.20. The accuracy of forecasting approved by root mean squared error (RMSE), mean absolute percentage error (MAPE). Results: We observed a decreasing trend in mortality proportion in the NICU, with more pronounced seasonal patterns in admission numbers (which increased during the winter season) and length of stay (which decreased during the winter season). Our regression time series analysis showed that as the length of stay in the hospital increases, the mortality proportion also increases. Conclusion: More extensive and well-designed studies are required to investigate the risk factors for prolonged stays in the NICU and how to manage them. Research should also concentrate on interventions that can effectively reduce long NICU stays and improve short- and long-term outcomes for newborns. Intensive Care Units Neonatal Time Series Analysis Forecasting Mortality Hospitalization 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 INTRODUCTION The investigation of the situation of medical cares, the monitoring of intensive care priorities and related indicators and the forecast of situation are challenges [ 1 ]. Neonatal intensive care units(NICUs) also face various demands, such as heavy costs, restricted resources, infection control, ethical problems, and staff exhaustion [ 2 , 3 ]Therefore, it is important, monitoring, evaluating and forecasting the performance and consequences of NICUs to identify gaps, and improve quality of care. NICU census is impacted by clinical route which can change dynamically over time. Forecasting NICU census and duration of hospital stay have great role on offer adequate and safe cares supported by appropriate resource planning, minimize discrepancies between expected and actual demand for health care resources, e.g., nurse to-patient ratios and hospital equipment management [ 4 , 5 ]. Based various studies suboptimal nurse staffing levels have been related with decrease in quality of care and neonates safety due to over- or understaffing (e.g., nosocomial infections) [ 6 – 10 ]. Increasing numbers of neonates to nurses in NICU has been shown to increase the risk of emotional burnout and dissatisfaction[ 11 ], and conversely low nurse-to-patient ratios have been associated with increased adverse patient outcomes, such as increased 30-day mortality and failure to rescue [ 11 ]. Neonatal mortality is a major public health problem worldwide. According to the World Health Organization (WHO), an estimated 2.4 million neonatal deaths occurred in 2019, accounting for 47% of all under-five deaths (1). The pooled proportion of mortality in a systematic review (on 24,995 neonates admitted to NICUs in Iran) was estimated to be 11.40% (4), also in a meta-analysis among very low birth weight (VLBW) newborns (1996–2016) in Eastern Mediterranean Region(EMR), pooled prevalence of mortality was obtained as 32.0%(CI 95%: 27.0 to 38.0) (5). The main causes of neonatal mortality are preterm birth complications, intrapartum-related events (birth asphyxia or trauma), infections, congenital anomalies, and neonatal sepsis (1, 2). Also some study reported survival in neonatal care for very low birth weight or preterm infants was related to proportion of nurses with neonatal qualifications per shift and length of hospitalization in NICU. [ 12 ] [ 13 , 14 ] Time series analysis is a statistical technique that analyzes data collected over time to examine the patterns, trends and making the respective forecasts of phenomenon. Time series analysis can help for prediction of census, duration of hospitalization and understand the dynamics of neonatal mortality in the NICU by revealing its seasonal and cyclical variations, detecting its trend and level changes, and forecasting its future values. Time series analysis can provide valuable information for decision-making and policy-making regarding neonatal health care in the NICU. The aim of this article is to predict the future census and duration of hospitalization at a large tertiary care referral level III NICU using past and current census as well as considering dynamic mortality changes by month and season in Tehran (capital of Iran) for first time by time series analysis. Methods and Materials This study was a retrospective cohort study that used data from the electronic NICU medical registry system (ENMRS) of Vali-asr Hospital (located in the capital of Iran) of the neonates admitted to the NICU from February 1, 2016 to December 31, 2022. The ENMRS contain information on the neonatal and maternal demographic, clinical, and outcome variables. The source population involved all neonates who were hospitalized to the NICU within the study period and had full data on the variables of interest. Neonates who were transferred to other medical centers or were excluded from the study. The study was approved by the Institutional Ethical Committee at Tehran University of Medical Sciences; IR.TUMS.IKHC.REC. 1402.090. Time series analysis was used to survey the patterns and forecasting of hospitalization census and duration of hospitalization, and neonatal mortality over time (month) at a large tertiary care referral level III NICU. Variables were forecasted for a period of 2.5 years (from January 2023 to September 2025). Time series analysis is a statistical technique that analyzes data collected over time to reveal its temporal components, such as trend, seasonality, cyclist, and irregularity[15]. Time series analysis can also be used to forecast future values of a variable based on its past behavior[15]. For this study, we used the following steps for time series analysis: Plot observed admission number, long stay and mortality proportion in NICU from March 2016 to December 2022 as time series variables. Transform variables in case of a non-stationary (e.g., linear trend over time). Fit several models to time series variable and estimate model parameters using dependency measured, e.g., Autocorrelation Function (ACF) and Partial Autocorrelation Function (PACF). Identify best models using fit criteria, e.g., Akaike’s Information Criterion (AIC), Bayesian Information Criterion (BIC), sigma, (Moving Average) MA and Autoregressive (AR) coefficients. Apply diagnostic tools to determine how well the models fit census data, e.g., Plot of standardized residuals and their normal Q-Q plot, and Forecast n months during 2023 to 2025 . Evaluate the accuracy of the forecasts provided by root mean squared error (RMSE), mean absolute percentage error (MAPE) [16]. The data were analyzed using SPSS-20 software (IBM, Armonk, NY, USA) and STATAMP 14 and a P-value of ≤0.05 was considered significant. RESULTS Pattern of the monthly admission, and mortality in NICU Between March 1st, 2016 and December 31st, 2022, a total of 7,216 infants were admitted to the Neonatal Intensive Care Unit (NICU), and out of those, 478 passed away. The mortality proportion was highest in 2017, at 9.79%, followed by 2016 at 8.78%, as indicated in Table 1 . Table 1 Monthly frequency of admission and mortality proportion (%) on admitted neonates to NICU from 2016 to 2022. years 2016 2017 2018 2019 2020 2021 2022 total Months Admission. n Mortality .p Admission. n Mortality .p Admission. N Mortality .p Admission. n Mortality .p Admission. n Mortality .p Admission. n Mortality .p Admission. n Mortality .p Admission. n Mortality. p Jan - 76 17.11 94 7.45 120 4.17 111 5.41 119 4.2 111 6.31 631 7.44 Feb - 53 9.43 62 11.29 88 11.36 76 9.21 97 4.12 117 3.42 493 8.14 Mar 13 7.69 54 3.7 75 12 91 12.09 38 10.53 121 2.48 113 6.19 505 7.81 Apr 58 15.52 62 9.68 83 7.23 76 7.89 43 6.98 108 3.7 109 7.34 539 8.33 May 75 9.33 77 9.09 80 5 86 5.81 89 2.25 91 6.59 105 8.57 603 6.66 Jun 78 6.41 98 6.12 76 5.26 91 6.59 78 10.26 115 5.22 79 7.59 615 6.78 Jul 65 6.15 76 9.21 77 7.79 71 1.41 81 8.64 100 3 79 6.33 549 6.08 Aug 71 2.82 108 8.33 75 12 81 3.7 63 3.17 119 7.56 111 3.6 628 5.88 Sep 67 8.96 63 11.11 96 9.38 85 3.53 88 5.68 111 4.5 96 3.13 606 6.61 Oct 78 12.82 81 12.35 97 10.31 93 5.38 116 1.72 122 7.38 102 1.96 689 7.42 Nov 78 11.54 68 14.71 96 7.29 94 5.32 76 1.32 142 5.63 85 3.53 639 7.05 Dec 91 6.59 90 6.67 93 10.75 100 4 115 4.35 111 1.8 119 4.2 719 5.48 Total 674 8.78 906 9.79 1004 8.81 1076 5.94 974 5.79 1356 4.68 1226 5.18 7216 7 Figures 1 , 2 , and 3 show the time series of NICU admission numbers, hospitalization days, and mortality proportion from 2016 to 2022 respectively. The horizontal axis in figures indicates the days from March 1, 2016, to December 31, 2022, while the vertical axis shows the daily census in Fig. 1 , the long stay in the hospital in Fig. 2 , and the mortality proportion in Fig. 3 . The NICU census time series exhibits both increasing and decreasing patterns with multiple peaks (Fig. 1 ). The admission number in January and December month (2017–2022; we didn't have data for January and December of 2016) is notable with a count of 631 and 628, respectively (Table 1 ). Additionally, the admissions in December and October months are higher than in other months, with 719 and 689 cases, respectively (2016–2022) (Table 1 ). The hospitalization days between 2016 and 2022 varied from each other and ranged between 10.57 to 13.84 days. The mean (SD) of hospitalization days was 12.42(1.15). Hospitalization days mean were highest in June and July with 14.19 and 13.81 days, respectively, and lowest in December with 10.54 days. The hospitalization days mean in 2016 were 13.18, in 2017 13.84, in 2018 13.45, in 2019 11.81, in 2020 11.72, in 2021 10.57, and in 2022 12.35. Additionally, the hospitalization days by month from January (1) to December (12) were as follows: (1) 11.94, (2) 10.74, (3) 12.29, (4) 13.76, (5) 11.65, (6) 14.19, (7) 13.35, (8) 13.81, (9) 12.42, (10) 12.51, (11) 11.88, and (12) 10.54 days. The highest mortality proportion (%) was calculated at 8.33 in April (from 2016–2022), without considering data in 2016 (with a lack of January and February data). The February and April had the most prevalent mortality proportion (%) (8.14 and 7.83, respectively) from 2017–2022. The time series of mortality proportion (%) is shown in Fig. 3 . Preparing time series variables for modeling Before developing the ARIMA model, smoothing was applied to variables (admission number, hospitalization days, and mortality proportion) by calculating a moving average (uniformly weighted moving average with a window size of 4 (average each point data with the previous 3-point data) to reduce noise and highlight underlying trends. We took natural Logarithm(LN) to stabilize variance too. The MacKinnon approximate test was used to analyze stationary time series. The results showed that the admission census and mortality proportion time series have a high probability of stationarity (P-values < 0.05). However, the hospitalization days’ variable showed a low probability of stationarity (P-value = 0.193). All three variables showed a linear trend, which is a characteristic of a non-stationary series (P-value < 0.001). Therefore, before model fitting, a data transformation was necessary. Differencing was used to make series stationary and remove trends. Time series modelling We have developed ARIMA and SARIMA models to forecast the future NICU census, hospitalization duration, and mortality proportion (%). The ARIMA (p,d,q) model comprises autoregressive and moving average components p and q, as well as an ordinary difference component d. Furthermore, the SARIMA (PDQ)s model includes seasonal autoregressive and moving average components P, Q, a seasonal difference component D, and the order of seasonal lag s. Autoregression refers to predicting the present value of a time series based on its past values. Seasonality refers to any pattern in the data that repeats with a known periodicity. The variable of NICU census exhibits a slowly decaying autocorrelation function (ACF) structure with a trend and statistically significant autocorrelation still present at lags up to 40 (Fig. 4 ). Additionally, the partial Autocorrelation function (PACF) suggests possible non-stationary behavior (Fig. 5 ). Hospitalization days’ variable exhibit persistent and decaying autocorrelation structure, with statistically significant lags in the ACF and PACF. Additionally, a seasonality pattern is evident (see Figs. 6 and 7 ). Mortality proportion (%) exhibited a decaying autocorrelation structure, with statistically significant in AC and PACF (Fig. 8 , 9 ) Based on the ACF and PACF graphs shown in Figs. 4 and 5 , it appears that the most suitable model for the admission number variable would be an ARIMA model with a range of 1–4 for the ACF and 1–2 for the PACF, with two differences. Additionally, a SARIMA model with lags of 1 and 3 for both ACF and PACF should also be considered. The best-fitting model was identified as ARIMA (1,2,1) SARIMA(1,0,1,4) through the use of various evaluation metrics such as Akaike Information Criterion (AIC), Bayesian Information Criterion (BIC), sigma coefficient, Log-likelihood, coefficients of Autoregressive (AR), and Moving Average (MA). Table 2 lists models with similar goodness-of-fit measurements (Table 2 ). Once the model was fitted, diagnosis tools were used to evaluate the goodness of fit. These tools included a normal Q-Q plot of standardized residuals (Fig. 1 s), eigenvalue stability(Fig. 2 s), and Portmanteau test for the test of white noise(P-Value = 0.58). Table 2 Comparison of log-likelihood, AIC, BIC, Autocorrelation, moving average, and sigma coefficients of different models for selecting the best-fitted model in forecasting admission numbers. Log likelihood AR (SE) MA (SE) Seasonal Sigma (SE) AIC BIC AR (SE) MA (SE) D2.ln. smooth admission number = ARIMA (1,2,1) SARIMA (1,0,1,4) 69.65 0.939 (0.172) -0.829 (0.229) 0.116 (0.149) -0.799 (0.195) 0.101 (0.006) -105.54 -93.54 D2.ln.smooth admission number = ARIMA(4,2,1)SARIMA(1,0,1,4) 65.25 -0.885 ( 0.142) 0.999 (0.109) -0.921 (0.129) 0.771 (0 .233 0.096 (0.931) -140.49 -95.33824 D2.ln.smooth admission number = ARIMA(1,2,1)SARIMA(4,0,1,4) 60.19 0.908 (0.205) -0.032 (0.0693) 0.099 (0.007) 0.498 (0 .663) 0.108 (0.693) -107.38 -95.83 D2.ln.smooth admission number ARIMA(1,2,4) SARIMA(1,0,1,4) 67.25 − .489 (0.565) -0.756 (0.289) -0.917 (0 .149) 0.779 (0 .301) 0.099 (0.025) -118.35 -99.50 *Akaike Information Criterion (AIC), Bayesian Information Criterion (BIC) The ACF and PACF graphs (as shown in Fig. 6 and Fig. 7 ) indicated that the hospitalization days' variable would be best modeled with an ARIMA of lags of 1–3 for ACF and 1–2 for PACF and one difference. Additionally, the graphs suggested using a SARIMA with lags 1 and 4 (for both ACF and PACF). After comparing the goodness of fit measurement (some close values of goodness of fit measurements are listed in Table 3 ), the SARIMA (4,0,1,4) model was identified as the best for hospitalization days. The model was then fitted and diagnostic tools were used to evaluate the goodness of fit (portmanteau test P-Value = 0.46) (Figs. 3 s, 4 s). Table 3 Comparison of log-likelihood, AIC, BIC, Autocorrelation, moving average, and sigma coefficients of different models for selecting the best-fitted model in forecasting Hospitalization days Log likelihood Ar(SE) Ma(SE) Sigma(SE) AIC BIC LN. smooth long stay SARIMA (1,0,4,4) 51.17 0.563 (0.173) 0.487(0.58) .119 (0.530) -88.342 -71.33 LN. smooth long staySARIMA (4,0,1,4) 48.91 0.563 (0.173) − .426 (0.99) .0.113 (0.530) -83.82 -66.80 LN. smooth long stay SARIMA (1,0,1,4) 45.88 -0.153 (0.454) 0.462 (0.376) 0.139 (.013) -83.77 -74.04 LN. smooth long stay SARIMA (4,1,4,4) 54.09 − .519 (0.225) 0.179 (0.523) 0.0958 (0.029) -92.19 -73.14 LN. smooth long stay SARIMA (4,1,1,4) 49.26 -0.294 (0.163) -1.000009 3121.368 0.118 (0.592) -84.501 -67.839 LN. smooth long stay SARIMA (1,1,1,4) 45.44 0.125 (0.127) -1 .128 (0.011) -84.88 -77.74 LN. smooth long stay SARIMA (1,1,4,4) 51.17 -0.789 (0.258) -0.426 (0.1) .119 (0.530) -86.29 -71.99 *Akaike Information Criterion (AIC), Bayesian Information Criterion (BIC) The AC and PACF graphs displayed in Figs. 8 and 9 indicate that an ARIMA (1, 1, 4) model is suitable for the mortality proportion (some models that were similar by goodness of fit measurements are listed in Table 4 ), based on the considered indices (portmanteau test P-Value = 0.69) (Figs. 5 s, 6 s). Table 4 Comparison of log-likelihood, AIC, BIC, Autocorrelation, moving average, and sigma coefficients of different models for selecting the best-fitted model in forecasting mortality proportion models Log likelihood AR (SE) MA (SE) Sigma (SE) AIC BIC D1.ln. smooth mortality ARIMA (1,1,1) 64.54 0.889 (0.039) − .0078 (0.094) 0.111 (0.005) -129.09 -114.37 D1.ln. smooth mortality ARIMA (1,1,4) 72.03 0.886 (0.1) -0.416 (0.269) .0995 (0.912) -130.07 -113.05 D1.ln. smooth mortality ARIMA (4,1,1) 72.07 0.743 (0.139) 0.99 (NC)* 0.099 (0.006) -132.14 -117.56 D1.ln. smooth mortality ARIMA (4,1,4) 73.03 0.795 (0.255) -0.411 (NC)* 0.097 (0.69) -128.07 -106.19 *Akaike Information Criterion (AIC), Bayesian Information Criterion (BIC), NC = no calculated Forecasting of time series variables The estimated monthly forecasted NICU admission census for the period of January 2023 to September 2025 ranges from 93 to 105 cases, as shown in Table 5 . Furthermore, the monthly admissions to NICU have decreased during this period, as depicted in Fig. 7 , with a trend coefficient of -0.222 and a P-Value of 0.002. However, when we consider the trend from 2016 to 2023, there is a slight rise, but it is not statistically significant, with a trend coefficient of 0.36 and a P-Value of 0.163, as shown in Fig. 10 (2016–2025). Table 5 The forecasted number of admissions, hospitalization days, and mortality proportion using ARIMA (1,2,1) SARIMA (1,0,1,4), SARIMA (4,0,1,4), and ARIMA (1,1,4), respectively, Time Predicted value admissions number ; ARIMA(1,2,1)SARIMA(1,0,1,4) hospitalization days; SARIMA (4,0,1,4) mortality proportion; ARIMA(1,1,4) 2023m1 94.86262 12.47947 3.193621 2023m2 104.7546 12.24222 3.15402 2023m3 101.673 11.61682 3.789941 2023m4 105.1995 11.91629 4.09831 2023m5 101.2042 11.91629 4.15157 2023m6 102.636 12.19027 4.05896 2023m7 102.8402 12.853 3.702393 2023m8 102.6626 13.13674 3.371494 2023m9 102.6687 12.67798 3.162202 2023m10 102.3177 12.53526 3.009127 2023m11 102.4759 12.46693 2.980458 2023m12 102.0668 12.17485 3.001916 2024m1 101.8813 11.98417 2.99346 2024m2 101.4768 12.10709 2.9725 2024m3 101.282 12.23928 2.893365 2024m4 100.8444 12.04398 2.769386 2024m5 100.8444 12.14263 2.650515 2024m6 100.4837 12.23709 2.533159 2024m7 100.0233 12.43997 2.437697 2024m8 99.63045 12.52246 2.370777 2024m9 99.13049 12.40494 2.310666 2024m10 98.64646 12.36318 2.256401 2024m11 98.1105 12.34774 2.199562 2024m12 98.1105 12.27391 2.130691 2025m1 96.42227 12.20712 2.057809 2025m2 95.80264 12.23792 1.982477 2025m3 95.17403 12.26797 1.907469 2025m4 94.51074 12.20298 1.839173 2025m5 93.83088 12.23394 1.775703 2025m6 93.12 12.26516 1.716126 Long hospitalizations in the NICU ranged from 11 to 13 days(Table 5 ). Mortality proportion forecasted ranged 1.72 to 4.15 cases in month. with mean(SD) equals at 2.79(0.72) (Fig. 11 ). In the case of the forecasted mortality proportion from 2016 to September 2025, it is expected that the probability of mortality proportion will decrease by -0.027 per unit increase in time (month) with a P-value of less than 0.001 (Fig. 12 ). Validation of forecasting To evaluate the accuracy of our forecasts, we used two metrics: the mean absolute percentage error (MAPE) and the root mean square error (RMSE). According to Muge Capan's literature[ 5 ], a MAPE value of less than 10% indicates highly accurate forecasting. The Table 6 provides the MAPE and RMSE values for all of the variables that were forecasted. Table 6 Accuracy of forecasts by mean absolute percentage error (MAPE) and the root mean square error (RMSE) Models MAPE RMSE admissions number ; ARIMA(1,2,1)SARIMA(1,0,1,4) 4.73 0.869 hospitalization days; SARIMA (4,0,1,4) 4.35 0.89 mortality proportion; ARIMA(1,1,4) 2.03 0.021 Regression analysis on time series variables According to the regression time series analysis, there exists an inverse linear relationship between the number of hospitalizations per month and the duration of hospital stay. The coefficient of linear regression was estimated − 2.58, and the P-value was less than 0.001. Also, it has been observed that for every unit (day) increase in length of stay in NICU, the proportion of mortality increase by 0.339 (with a P-value = 0.018) from 2016 to 2022 (B (SE) = 0.339(0.139)), adjusted by admission number variable. Discussion This is the first study in Iran to use time series analysis to mathematically model and predict admissions and mortality in the NICU. The study forecasted admission numbers, length of hospitalization, and mortality proportions in the NICU over the last 7 years for a period of 2.5 years (from January 2023 to September 2025). In the present study, the admission census was higher during the winter season, while the mean length of hospitalization days decreased during the same period. In the regression time series analysis, an inverse relationship was found between admission census and length of hospitalization (P-Value < 0.01). After conducting primary analysis and making necessary data adjustments, we used ARIMA models for forecasting, which are considered to be one of the most appropriate tools. There detected trend for admission number and mortality proportion. Also seasonal pattern was clear in admission number and hospitalization days in NICU. We selected an ARIMA (1,2,1) and SARIMA (1,0,1,4) for admissions number, SARIMA (4,0,1,4) for hospitalization days, and ARIMA (1,1,4) for mortality proportion in NICU as the best fitting models after model assessment. The goodness of fit and accuracy tests showed that the models can adequately explain the fluctuations in admission number, hospitalization days, and mortality proportion in NICU, and there was good matching between the observed values and the fitted values. Accurate prediction of admission numbers, length of hospital stays, and mortality proportion is crucial for maintaining high-quality care, effective resource planning, and ensuring employee satisfaction in healthcare systems. Relying on a fixed value based on the previous year’s average daily census does not account for the dynamic nature of patient admissions over time. By forecasted findings from January 2023 to September 2025, the admission numbers appear to have decreased relatively (R= -0.222 and a P-Value of 0.002). However, no specific trend was observed in general from March 2016 to September 2025 (p > 0.05). There has been a significant decrease in the incidence of mortality in neonates in the NICU. The highest mortality proportion in the NICU was recorded in February and April. A positive relationship was found between neonatal mortality and length of stay in the hospital (B = 0.339) in the regression time series analysis. Fu (2023) identified critical risk factors affecting prolonged NICU stay, including birth weight, gestational age, sepsis, Necrotizing enterocolitis (NEC), bronchopulmonary dysplasia (BPD), and retinopathy of prematurity (ROM)[ 14 ]. On the other hand, with the increase in length of stay in the hospital, the possibility of nosocomial infection and mortality increases[ 14 ]. In Dalili's study, Mortality proportion was calculated 37% in neonates with acinetobacter boumani infection (from 2016 to 2022)[ 17 ]. The generalizability of these findings may be low. Additionally, this study only considered variations in admission numbers and mortality, without taking into account other impacting factors such as age, gender, socioeconomic status, environment, and politics. Nonetheless, the methodology and analyses could be used to improve decision-making, proper allocation, and use of health resources to further reduce the rate of deaths in the NICU. Conclusion In this time series study, a downward trend was observed in mortality proportion, and seasonality patterns were more evident in admission numbers (increasing during the winter season) and hospitalization days (decreasing during the winter season) in the NICU. Regression time series appears while the length of stay in the hospital increases and, mortality proportion increases. Further extensive and well-designed studies are needed to investigate risk factors for long stays in the NICU and its management. Studies should also focus on interventions to effectively reduce long stays in the NICU and improve short- and long-term newborn outcomes Declarations Acknowledgments We would like to acknowledge of Maternal-Fetal and neonatal research center, Tehran university of Medical sciences and all co-operator in the hospital registration system for collecting data and supervising. Ethics approval and consent to participate The study was approved by the Research Ethics Committee of Tehran University of Medical Sciences (IR.TUMS.IKHC.REC. REC.1402.090), Tehran, Iran. All methods were performed in accordance with the relevant guidelines and regulations by including a statement in ethical approval contract and in accordance with the declarations of Helsinki. The information documented by the hospital registry system was used for the study and waived the need for informed consent by ethics committee of biomedical research, Imam Khomeini hospital complex, Tehran University of medical sciences. Consent for publication Not applicable Availability of data and materials The datasets and outputs used during the current study available from the corresponding author ( Leyla Sahebi/ [email protected] ) on reasonable request. Competing interests Not aplicable Funding Not aplicable Authors’ contributions H.D and L.S designed the study. L.S and M.Sh collected data L.S modeled and analyzed data. L.S and H.D wrote the initial draft of the manuscript which was subsequently modified by M.Sh. All authors read and edited the manuscript for important intellectual content. All authors have seen and approved the final version of the manuscript. Author information Hosein Dalili, Professor. Maternal-Fetal and Neonatal Research Center, Family Health Research Institute, Imam Khomeini Hospital Complex . Tehran University of Medical Sciences, Tehran, Iran. Mamak Shariat, Professor. Vali-E-Asr Reproductive Health Research Center, Family Health Research Institute, Imam Khomeini Hospital Complex .Tehran University of Medical Sciences. Tehran, Iran Leyla Sahebi*, Corresponding author.Ph.D. Maternal-Fetal and Neonatal Research Center, Family Health Research Institute, Imam Khomeini Hospital Complex. Tehran University of Medical Science, Tehran, Iran References Silva ABD, et al. Auto-Regressive Integrated Moving Average Model (ARIMA): conceptual and methodological aspects and applicability in infant mortality. Revista Brasileira de Saúde Materno Infantil. 2021;21:647–56. Gudayu T, Zeleke E, Molla A. Time to Death and its Predictors among Neonates Admitted in the Intensive Care Unit of the University of Gondar Comprehensive Specialized Hospital, Northwest Ethiopia. Volume 10. Research and Reports in Neonatology; 2020. pp. 1–10. Wesenu M, Kulkarni S, Tilahun T. Modeling Determinants of Time-To-Death in Premature Infants Admitted to Neonatal Intensive Care Unit in Jimma University Specialized Hospital. Annals Data Sci, 2017. 4. Murray LL, et al. Forecasting ICU Census by Combining Time Series and Survival Models. Crit Care Explor. 2023;5(5):e0912. Capan M, et al. Time Series Analysis for Forecasting Hospital Census: Application to the Neonatal Intensive Care Unit. Appl Clin Inf. 2016;7(2):275–89. Sankar MJ, et al. When do newborns die? A systematic review of timing of overall and cause-specific neonatal deaths in developing countries. J Perinatol. 2016;36(Suppl 1):S1–11. Jehan I, et al. Neonatal mortality, risk factors and causes: a prospective population-based cohort study in urban Pakistan. Bull World Health Organ. 2009;87(2):130–8. Rogowski JA, et al. Nurse staffing and NICU infection rates. JAMA Pediatr. 2013;167(5):444–50. Jakuskiene R, et al. Neonatal outcomes of very preterm infants admitted to a tertiary center in Lithuania between the years 2003 and 2005. Eur J Pediatr. 2011;170(10):1293–303. Penoyer DA. Nurse staffing and patient outcomes in critical care: a concise review. Crit Care Med, 2010. 38(7): pp. 1521-8; quiz 1529. Sheward L, et al. The relationship between UK hospital nurse staffing and emotional exhaustion and job dissatisfaction. J Nurs Manag. 2005;13(1):51–60. Aiken LH, et al. Hospital nurse staffing and patient mortality, nurse burnout, and job dissatisfaction. JAMA. 2002;288(16):1987–93. Tarnow-Mordi WO, et al. Hospital mortality in relation to staff workload: a 4-year study in an adult intensive-care unit. Lancet. 2000;356(9225):185–9. Fu M et al. Risk factors for length of NICU stay of newborns: A systematic review. Front Pead, 2023. 11. Sheikhtaheri A, et al. Prediction of neonatal deaths in NICUs: development and validation of machine learning models. BMC Med Inf Decis Mak. 2021;21(1):131. Bekele T et al. Predictors of mortality among neonates hospitalized with neonatal sepsis: a case control study from southern Ethiopia. BMC Pediatr, 2022. 22. Hosein Dalili M, Shariat L, Sahebi et al. Survival and causes of death in infants admitted in NICU in Tehran (a retrospective cohort study 2016–2022), 08 January 2024, PREPRINT (Version 1).under review. available at Research Square [ https://doi.org/10.21203/rs.3.rs-3831825/v1] . Additional Declarations No competing interests reported. Supplementary Files supfigures.docx Cite Share Download PDF Status: Under Review Version 1 posted Editor assigned by journal 21 Jun, 2024 Submission checks completed at journal 21 Jun, 2024 First submitted to journal 19 Jun, 2024 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-4606104","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":317456119,"identity":"749b6634-c839-4764-a195-c3b933f5c93b","order_by":0,"name":"Hosein Dalili","email":"","orcid":"","institution":"Family Health Research Institute, Imam Khomeini Hospital Complex, Tehran University of Medical Sciences","correspondingAuthor":false,"prefix":"","firstName":"Hosein","middleName":"","lastName":"Dalili","suffix":""},{"id":317456120,"identity":"ce0fd761-d96d-428e-94c9-c2669a455351","order_by":1,"name":"Mamak Shariat","email":"","orcid":"","institution":"Tehran University of Medical Sciences","correspondingAuthor":false,"prefix":"","firstName":"Mamak","middleName":"","lastName":"Shariat","suffix":""},{"id":317456121,"identity":"233f762c-cc40-4bea-ba55-5900c989a74a","order_by":2,"name":"Leyla Sahebi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA7UlEQVRIiWNgGAWjYFACHgZmBgMLBjZ2BsYHDAwHiNYiwcDGzMBsQIIWBgkGIMkmQZQW+fazBx8XFEjI8TEzP6vmqbkjx8/A/PDRDTxaDM7kJRvPMJAwZmNmM7vNc+yZsWQDm7FxDj4tDDlm0jwGEoltzAxALWyHEzcc4GGTxqdFvv+N+W+glvo2ZvZvxTz/iNDCcCPHjBmoJYGNmceMmbeNCC0GN94YSwP9YtjGzFMsObfvsLFkMwG/yPfnGH4u+GMjL9/evvHDm2+H5fjZmx8+xuswZMDEAyKZiVUOAow/SFE9CkbBKBgFIwYAAEu/QdxB0z9VAAAAAElFTkSuQmCC","orcid":"","institution":"Family Health Research Institute, Imam Khomeini Hospital Complex, Tehran University of Medical Sciences","correspondingAuthor":true,"prefix":"","firstName":"Leyla","middleName":"","lastName":"Sahebi","suffix":""}],"badges":[],"createdAt":"2024-06-19 13:09:11","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4606104/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4606104/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":60617605,"identity":"7233a618-c860-4d65-9eb9-2d827f8ded7d","added_by":"auto","created_at":"2024-07-18 20:31:05","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":8985,"visible":true,"origin":"","legend":"\u003cp\u003etime series of NICU admission numbers from 2016 to 2022\u003c/p\u003e","description":"","filename":"1.png","url":"https://assets-eu.researchsquare.com/files/rs-4606104/v1/aa155fadc97fe5076570e277.png"},{"id":60618744,"identity":"ca7107d3-c574-4860-8759-bf4e83a1629e","added_by":"auto","created_at":"2024-07-18 20:39:05","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":9459,"visible":true,"origin":"","legend":"\u003cp\u003etime series of hospitalization days from 2016 to 2022\u003c/p\u003e","description":"","filename":"2.png","url":"https://assets-eu.researchsquare.com/files/rs-4606104/v1/2cff8937535bd28118a58628.png"},{"id":60617609,"identity":"04b5a1ad-687e-4c7c-a6d7-397189739794","added_by":"auto","created_at":"2024-07-18 20:31:05","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":8969,"visible":true,"origin":"","legend":"\u003cp\u003etime series of mortality proportion from 2016 to 2022\u003c/p\u003e","description":"","filename":"3.png","url":"https://assets-eu.researchsquare.com/files/rs-4606104/v1/6c6b4a17a39b85eae963fa29.png"},{"id":60619825,"identity":"6a5efc4f-34fd-4565-b49d-0d22fa372ffd","added_by":"auto","created_at":"2024-07-18 20:47:05","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":42456,"visible":true,"origin":"","legend":"\u003cp\u003eAutocorrelation function of NICU census variable\u003c/p\u003e","description":"","filename":"4.png","url":"https://assets-eu.researchsquare.com/files/rs-4606104/v1/c2d90fd35cbcea0dd8300c24.png"},{"id":60619824,"identity":"cefdf3cf-80e9-45de-9ba1-299b7a39c583","added_by":"auto","created_at":"2024-07-18 20:47:05","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":11867,"visible":true,"origin":"","legend":"\u003cp\u003ePartial autocorrelation function of NICU census variable\u003c/p\u003e","description":"","filename":"5.png","url":"https://assets-eu.researchsquare.com/files/rs-4606104/v1/de6623ca90f296dd510bcf38.png"},{"id":60617618,"identity":"cfdbe6e4-f5da-4a88-bccb-a81725292bf9","added_by":"auto","created_at":"2024-07-18 20:31:06","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":12466,"visible":true,"origin":"","legend":"\u003cp\u003eAutocorrelation function of hospitalization days\u003c/p\u003e","description":"","filename":"6.png","url":"https://assets-eu.researchsquare.com/files/rs-4606104/v1/2e2933c118ced4b9f5539cfb.png"},{"id":60618746,"identity":"1d0cfc3d-1188-41af-a528-fd1dd6b0d682","added_by":"auto","created_at":"2024-07-18 20:39:05","extension":"png","order_by":7,"title":"Figure 7","display":"","copyAsset":false,"role":"figure","size":12618,"visible":true,"origin":"","legend":"\u003cp\u003ePartial Autocorrelation function of hospitalization days\u003c/p\u003e","description":"","filename":"7.png","url":"https://assets-eu.researchsquare.com/files/rs-4606104/v1/d4098a64f1fbd58e13093cf1.png"},{"id":60617611,"identity":"44e7b172-a4c6-4ad0-bcfb-596b09298eec","added_by":"auto","created_at":"2024-07-18 20:31:05","extension":"png","order_by":8,"title":"Figure 8","display":"","copyAsset":false,"role":"figure","size":12420,"visible":true,"origin":"","legend":"\u003cp\u003eAutocorrelation function of mortality proportion\u003c/p\u003e","description":"","filename":"8.png","url":"https://assets-eu.researchsquare.com/files/rs-4606104/v1/845d5c31a24ba936e7d1a204.png"},{"id":60617617,"identity":"7a0a8cdc-fc10-4bc9-bb22-8223354193e6","added_by":"auto","created_at":"2024-07-18 20:31:06","extension":"png","order_by":9,"title":"Figure 9","display":"","copyAsset":false,"role":"figure","size":11568,"visible":true,"origin":"","legend":"\u003cp\u003epartial Autocorrelation function of mortality proportion\u003c/p\u003e","description":"","filename":"9.png","url":"https://assets-eu.researchsquare.com/files/rs-4606104/v1/e3a35270fdff1660ff74ddd7.png"},{"id":60617615,"identity":"ade51edd-a7e7-436d-8471-7ebcab6308d9","added_by":"auto","created_at":"2024-07-18 20:31:06","extension":"png","order_by":10,"title":"Figure 10","display":"","copyAsset":false,"role":"figure","size":52728,"visible":true,"origin":"","legend":"\u003cp\u003eforecasted values of admission number for 2023 to2026\u003c/p\u003e","description":"","filename":"10.png","url":"https://assets-eu.researchsquare.com/files/rs-4606104/v1/fa591f7ab1e7d2f405f7dff0.png"},{"id":60617614,"identity":"bbe843d5-4662-447e-b24e-679d1cf428c7","added_by":"auto","created_at":"2024-07-18 20:31:05","extension":"png","order_by":11,"title":"Figure 11","display":"","copyAsset":false,"role":"figure","size":14818,"visible":true,"origin":"","legend":"\u003cp\u003eforecasted values of hospitalization days for 2023 to2026\u003c/p\u003e","description":"","filename":"11.png","url":"https://assets-eu.researchsquare.com/files/rs-4606104/v1/cb043f3d57c8a995d32abcc3.png"},{"id":60618749,"identity":"f399925d-e7cd-423d-ab1a-4f416b823613","added_by":"auto","created_at":"2024-07-18 20:39:06","extension":"png","order_by":12,"title":"Figure 12","display":"","copyAsset":false,"role":"figure","size":13749,"visible":true,"origin":"","legend":"\u003cp\u003eforecasted values of mortality proportion for 2023 to2026\u003c/p\u003e","description":"","filename":"12.png","url":"https://assets-eu.researchsquare.com/files/rs-4606104/v1/c578bf904791460eed288d2c.png"},{"id":60620811,"identity":"9b5f6617-dbd4-4b83-bb1b-317e3f6393c0","added_by":"auto","created_at":"2024-07-18 20:55:06","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1081540,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4606104/v1/b32d9e64-b1fa-44df-9f62-fbc74219e384.pdf"},{"id":60617606,"identity":"78fa2c9e-5dc5-4efd-a4ce-55622897f007","added_by":"auto","created_at":"2024-07-18 20:31:05","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":431227,"visible":true,"origin":"","legend":"","description":"","filename":"supfigures.docx","url":"https://assets-eu.researchsquare.com/files/rs-4606104/v1/2361b18b12b34c74adb74135.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Time Series Analysis for forecasting neonatal intensive care unit census and neonatal mortality","fulltext":[{"header":"INTRODUCTION","content":"\u003cp\u003eThe investigation of the situation of medical cares, the monitoring of intensive care priorities and related indicators and the forecast of situation are challenges [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]. Neonatal intensive care units(NICUs) also face various demands, such as heavy costs, restricted resources, infection control, ethical problems, and staff exhaustion [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e, \u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]Therefore, it is important, monitoring, evaluating and forecasting the performance and consequences of NICUs to identify gaps, and improve quality of care.\u003c/p\u003e \u003cp\u003eNICU census is impacted by clinical route which can change dynamically over time. Forecasting NICU census and duration of hospital stay have great role on offer adequate and safe cares supported by appropriate resource planning, minimize discrepancies between expected and actual demand for health care resources, e.g., nurse to-patient ratios and hospital equipment management [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e, \u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e]. Based various studies suboptimal nurse staffing levels have been related with decrease in quality of care and neonates safety due to over- or understaffing (e.g., nosocomial infections) [\u003cspan additionalcitationids=\"CR7 CR8 CR9\" citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e]. Increasing numbers of neonates to nurses in NICU has been shown to increase the risk of emotional burnout and dissatisfaction[\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e], and conversely low nurse-to-patient ratios have been associated with increased adverse patient outcomes, such as increased 30-day mortality and failure to rescue [\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eNeonatal mortality is a major public health problem worldwide. According to the World Health Organization (WHO), an estimated 2.4\u0026nbsp;million neonatal deaths occurred in 2019, accounting for 47% of all under-five deaths (1).\u003c/p\u003e \u003cp\u003eThe pooled proportion of mortality in a systematic review (on 24,995 neonates admitted to NICUs in Iran) was estimated to be 11.40% (4), also in a meta-analysis among very low birth weight (VLBW) newborns (1996\u0026ndash;2016) in Eastern Mediterranean Region(EMR), pooled prevalence of mortality was obtained as 32.0%(CI 95%: 27.0 to 38.0) (5).\u003c/p\u003e \u003cp\u003eThe main causes of neonatal mortality are preterm birth complications, intrapartum-related events (birth asphyxia or trauma), infections, congenital anomalies, and neonatal sepsis (1, 2). Also some study reported survival in neonatal care for very low birth weight or preterm infants was related to proportion of nurses with neonatal qualifications per shift and length of hospitalization in NICU. [\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e] [\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e, \u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e]\u003c/p\u003e \u003cp\u003eTime series analysis is a statistical technique that analyzes data collected over time to examine the patterns, trends and making the respective forecasts of phenomenon. Time series analysis can help for prediction of census, duration of hospitalization and understand the dynamics of neonatal mortality in the NICU by revealing its seasonal and cyclical variations, detecting its trend and level changes, and forecasting its future values. Time series analysis can provide valuable information for decision-making and policy-making regarding neonatal health care in the NICU. The aim of this article is to predict the future census and duration of hospitalization at a large tertiary care referral level III NICU using past and current census as well as considering dynamic mortality changes by month and season in Tehran (capital of Iran) for first time by time series analysis.\u003c/p\u003e"},{"header":"Methods and Materials","content":"\u003cp\u003eThis study was a retrospective cohort study that used data from the electronic NICU medical registry system (ENMRS) of Vali-asr Hospital (located in the capital of Iran) of the neonates admitted to the NICU from February 1, 2016 to December 31, 2022.\u003c/p\u003e\n\u003cp\u003eThe ENMRS contain information on the neonatal and maternal demographic, clinical, and outcome variables. The source population involved all neonates who were hospitalized to the NICU within the study period and had full data on the variables of interest. Neonates who were transferred to other medical centers or were excluded from the study.\u003c/p\u003e\n\u003cp\u003eThe study was approved by the Institutional Ethical Committee at Tehran University of Medical Sciences; IR.TUMS.IKHC.REC. 1402.090.\u003c/p\u003e\n\u003cp\u003eTime series analysis was used to survey the patterns and forecasting of hospitalization census and duration of hospitalization, and neonatal mortality over time (month) at a large tertiary care referral level III NICU. Variables were forecasted for a period of 2.5 years (from January 2023 to September 2025).\u003c/p\u003e\n\u003cp\u003eTime series analysis is a statistical technique that analyzes data collected over time to reveal its temporal components, such as trend, seasonality, cyclist, and irregularity[15]. Time series analysis can also be used to forecast future values of a variable based on its past behavior[15]. \u003c/p\u003e\n\u003cp\u003eFor this study, we used the following steps for time series analysis:\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003ePlot observed admission number, long stay and mortality proportion in NICU from March 2016 to December 2022 as time series variables.\u003c/li\u003e\n\u003cli\u003eTransform variables in case of a non-stationary (e.g., linear trend over time). \u003c/li\u003e\n\u003cli\u003eFit several models to time series variable and estimate model parameters using dependency measured, e.g., Autocorrelation Function (ACF) and Partial Autocorrelation Function (PACF).\u003c/li\u003e\n\u003cli\u003eIdentify best models using fit criteria, e.g., Akaike’s Information Criterion (AIC), Bayesian Information Criterion (BIC), sigma, (Moving Average) MA and Autoregressive (AR) coefficients. \u003c/li\u003e\n\u003cli\u003eApply diagnostic tools to determine how well the models fit census data, e.g., Plot of standardized residuals and their normal Q-Q plot, and Forecast n months during 2023 to 2025 .\u003c/li\u003e\n\u003cli\u003eEvaluate the accuracy of the forecasts provided by root mean squared error (RMSE), mean absolute percentage error (MAPE) [16]. \u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eThe data were analyzed using SPSS-20 software (IBM, Armonk, NY, USA) and STATAMP 14 and a P-value of ≤0.05 was considered significant. \u003c/p\u003e"},{"header":"RESULTS","content":"\u003cdiv id=\"Sec4\" class=\"Section2\"\u003e\n \u003ch2\u003ePattern of the monthly admission, and mortality in NICU\u003c/h2\u003e\n \u003cp\u003eBetween March 1st, 2016 and December 31st, 2022, a total of 7,216 infants were admitted to the Neonatal Intensive Care Unit (NICU), and out of those, 478 passed away. The mortality proportion was highest in 2017, at 9.79%, followed by 2016 at 8.78%, as indicated in Table \u003cspan class=\"InternalRef\"\u003e1\u003c/span\u003e.\u003c/p\u003e\n \u003cdiv class=\"gridtable\"\u003e\u0026nbsp;\u003ctable id=\"Tab1\" border=\"1\"\u003e\n \u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eMonthly frequency of admission and mortality proportion (%) on admitted neonates to NICU from 2016 to 2022.\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\n \u003ccolgroup cols=\"17\"\u003e\u003c/colgroup\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eyears\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003e2016\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003e2017\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003e2018\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003e2019\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003e2020\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003e2021\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003e2022\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003etotal\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMonths\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAdmission. n\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMortality .p\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAdmission. n\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMortality .p\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAdmission. N\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMortality .p\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAdmission. n\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMortality .p\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAdmission. n\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMortality .p\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAdmission. n\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMortality .p\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAdmission. n\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMortality .p\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAdmission. n\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMortality. p\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eJan\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e76\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e17.11\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e94\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e7.45\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e120\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e4.17\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e111\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e5.41\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e119\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e4.2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e111\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e6.31\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e631\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e7.44\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eFeb\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e53\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e9.43\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e62\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e11.29\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e88\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e11.36\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e76\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e9.21\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e97\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e4.12\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e117\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e3.42\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e493\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e8.14\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMar\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e13\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e7.69\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e54\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e3.7\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e75\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e12\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e91\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e12.09\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e38\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e10.53\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e121\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2.48\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e113\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e6.19\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e505\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e7.81\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eApr\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e58\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e15.52\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e62\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e9.68\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e83\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e7.23\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e76\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e7.89\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e43\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e6.98\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e108\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e3.7\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e109\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e7.34\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e539\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e8.33\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMay\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e75\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e9.33\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e77\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e9.09\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e80\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e86\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e5.81\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e89\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2.25\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e91\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e6.59\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e105\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e8.57\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e603\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e6.66\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eJun\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e78\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e6.41\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e98\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e6.12\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e76\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e5.26\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e91\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e6.59\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e78\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e10.26\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e115\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e5.22\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e79\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e7.59\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e615\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e6.78\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eJul\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e65\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e6.15\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e76\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e9.21\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e77\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e7.79\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e71\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1.41\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e81\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e8.64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e100\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e79\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e6.33\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e549\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e6.08\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAug\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e71\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2.82\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e108\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e8.33\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e75\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e12\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e81\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e3.7\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e63\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e3.17\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e119\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e7.56\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e111\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e3.6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e628\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e5.88\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eSep\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e67\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e8.96\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e63\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e11.11\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e96\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e9.38\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e85\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e3.53\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e88\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e5.68\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e111\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e4.5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e96\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e3.13\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e606\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e6.61\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eOct\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e78\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e12.82\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e81\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e12.35\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e97\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e10.31\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e93\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e5.38\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e116\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1.72\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e122\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e7.38\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e102\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1.96\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e689\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e7.42\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNov\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e78\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e11.54\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e68\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e14.71\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e96\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e7.29\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e94\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e5.32\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e76\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1.32\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e142\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e5.63\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e85\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e3.53\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e639\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e7.05\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eDec\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e91\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e6.59\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e90\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e6.67\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e93\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e10.75\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e100\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e115\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e4.35\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e111\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1.8\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e119\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e4.2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e719\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e5.48\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eTotal\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e674\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e8.78\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e906\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e9.79\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1004\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e8.81\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1076\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e5.94\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e974\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e5.79\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1356\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e4.68\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1226\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e5.18\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e7216\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e7\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003c/table\u003e\n \u003c/div\u003e\n \u003cp\u003eFigures \u003cspan class=\"InternalRef\"\u003e1\u003c/span\u003e, \u003cspan class=\"InternalRef\"\u003e2\u003c/span\u003e, and \u003cspan class=\"InternalRef\"\u003e3\u003c/span\u003e show the time series of NICU admission numbers, hospitalization days, and mortality proportion from 2016 to 2022 respectively. The horizontal axis in figures indicates the days from March 1, 2016, to December 31, 2022, while the vertical axis shows the daily census in Fig. \u003cspan class=\"InternalRef\"\u003e1\u003c/span\u003e, the long stay in the hospital in Fig. \u003cspan class=\"InternalRef\"\u003e2\u003c/span\u003e, and the mortality proportion in Fig. \u003cspan class=\"InternalRef\"\u003e3\u003c/span\u003e.\u003c/p\u003e\n \u003cp\u003eThe NICU census time series exhibits both increasing and decreasing patterns with multiple peaks (Fig. \u003cspan class=\"InternalRef\"\u003e1\u003c/span\u003e). The admission number in January and December month (2017\u0026ndash;2022; we didn\u0026apos;t have data for January and December of 2016) is notable with a count of 631 and 628, respectively (Table \u003cspan class=\"InternalRef\"\u003e1\u003c/span\u003e). Additionally, the admissions in December and October months are higher than in other months, with 719 and 689 cases, respectively (2016\u0026ndash;2022) (Table \u003cspan class=\"InternalRef\"\u003e1\u003c/span\u003e).\u003c/p\u003e\n \u003cp\u003eThe hospitalization days between 2016 and 2022 varied from each other and ranged between 10.57 to 13.84 days. The mean (SD) of hospitalization days was 12.42(1.15). Hospitalization days mean were highest in June and July with 14.19 and 13.81 days, respectively, and lowest in December with 10.54 days. The hospitalization days mean in 2016 were 13.18, in 2017 13.84, in 2018 13.45, in 2019 11.81, in 2020 11.72, in 2021 10.57, and in 2022 12.35. Additionally, the hospitalization days by month from January (1) to December (12) were as follows: (1) 11.94, (2) 10.74, (3) 12.29, (4) 13.76, (5) 11.65, (6) 14.19, (7) 13.35, (8) 13.81, (9) 12.42, (10) 12.51, (11) 11.88, and (12) 10.54 days.\u003c/p\u003e\n \u003cp\u003eThe highest mortality proportion (%) was calculated at 8.33 in April (from 2016\u0026ndash;2022), without considering data in 2016 (with a lack of January and February data). The February and April had the most prevalent mortality proportion (%) (8.14 and 7.83, respectively) from 2017\u0026ndash;2022. The time series of mortality proportion (%) is shown in Fig.\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e3\u003c/span\u003e.\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec5\" class=\"Section2\"\u003e\n \u003ch2\u003ePreparing time series variables for modeling\u003c/h2\u003e\n \u003cp\u003eBefore developing the ARIMA model, smoothing was applied to variables (admission number, hospitalization days, and mortality proportion) by calculating a moving average (uniformly weighted moving average with a window size of 4 (average each point data with the previous 3-point data) to reduce noise and highlight underlying trends. We took natural Logarithm(LN) to stabilize variance too.\u003c/p\u003e\n \u003cp\u003eThe MacKinnon approximate test was used to analyze stationary time series. The results showed that the admission census and mortality proportion time series have a high probability of stationarity (P-values\u0026thinsp;\u0026lt;\u0026thinsp;0.05). However, the hospitalization days\u0026rsquo; variable showed a low probability of stationarity (P-value\u0026thinsp;=\u0026thinsp;0.193). All three variables showed a linear trend, which is a characteristic of a non-stationary series (P-value\u0026thinsp;\u0026lt;\u0026thinsp;0.001). Therefore, before model fitting, a data transformation was necessary. Differencing was used to make series stationary and remove trends.\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec6\" class=\"Section2\"\u003e\n \u003ch2\u003eTime series modelling\u003c/h2\u003e\n \u003cp\u003eWe have developed ARIMA and SARIMA models to forecast the future NICU census, hospitalization duration, and mortality proportion (%). The ARIMA (p,d,q) model comprises autoregressive and moving average components p and q, as well as an ordinary difference component d. Furthermore, the SARIMA (PDQ)s model includes seasonal autoregressive and moving average components P, Q, a seasonal difference component D, and the order of seasonal lag s. Autoregression refers to predicting the present value of a time series based on its past values. Seasonality refers to any pattern in the data that repeats with a known periodicity.\u003c/p\u003e\n \u003cp\u003eThe variable of NICU census exhibits a slowly decaying autocorrelation function (ACF) structure with a trend and statistically significant autocorrelation still present at lags up to 40 (Fig. \u003cspan class=\"InternalRef\"\u003e4\u003c/span\u003e). Additionally, the partial Autocorrelation function (PACF) suggests possible non-stationary behavior (Fig. \u003cspan class=\"InternalRef\"\u003e5\u003c/span\u003e). Hospitalization days\u0026rsquo; variable exhibit persistent and decaying autocorrelation structure, with statistically significant lags in the ACF and PACF. Additionally, a seasonality pattern is evident (see Figs. \u003cspan class=\"InternalRef\"\u003e6\u003c/span\u003e and \u003cspan class=\"InternalRef\"\u003e7\u003c/span\u003e). Mortality proportion (%) exhibited a decaying autocorrelation structure, with statistically significant in AC and PACF (Fig. \u003cspan class=\"InternalRef\"\u003e8\u003c/span\u003e,\u003cspan class=\"InternalRef\"\u003e9\u003c/span\u003e)\u003c/p\u003e\n \u003cp\u003eBased on the ACF and PACF graphs shown in Figs. \u003cspan class=\"InternalRef\"\u003e4\u003c/span\u003e and \u003cspan class=\"InternalRef\"\u003e5\u003c/span\u003e, it appears that the most suitable model for the admission number variable would be an ARIMA model with a range of 1\u0026ndash;4 for the ACF and 1\u0026ndash;2 for the PACF, with two differences. Additionally, a SARIMA model with lags of 1 and 3 for both ACF and PACF should also be considered. The best-fitting model was identified as ARIMA (1,2,1) SARIMA(1,0,1,4) through the use of various evaluation metrics such as Akaike Information Criterion (AIC), Bayesian Information Criterion (BIC), sigma coefficient, Log-likelihood, coefficients of Autoregressive (AR), and Moving Average (MA). Table \u003cspan class=\"InternalRef\"\u003e2\u003c/span\u003e lists models with similar goodness-of-fit measurements (Table \u003cspan class=\"InternalRef\"\u003e2\u003c/span\u003e). Once the model was fitted, diagnosis tools were used to evaluate the goodness of fit. These tools included a normal Q-Q plot of standardized residuals (Fig. \u003cspan class=\"InternalRef\"\u003e1\u003c/span\u003es), eigenvalue stability(Fig. \u003cspan class=\"InternalRef\"\u003e2\u003c/span\u003es), and Portmanteau test for the test of white noise(P-Value\u0026thinsp;=\u0026thinsp;0.58).\u003c/p\u003e\n \u003cdiv class=\"gridtable\"\u003e\u0026nbsp;\u003ctable id=\"Tab2\" border=\"1\"\u003e\n \u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eComparison of log-likelihood, AIC, BIC, Autocorrelation, moving average, and sigma coefficients of different models for selecting the best-fitted model in forecasting admission numbers.\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\n \u003ccolgroup cols=\"9\"\u003e\u003c/colgroup\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003cth align=\"left\" rowspan=\"2\"\u003e\u0026nbsp;\u003c/th\u003e\n \u003cth align=\"left\" rowspan=\"2\"\u003e\n \u003cp\u003eLog likelihood\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" rowspan=\"2\"\u003e\n \u003cp\u003eAR\u003c/p\u003e\n \u003cp\u003e(SE)\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" rowspan=\"2\"\u003e\n \u003cp\u003eMA\u003c/p\u003e\n \u003cp\u003e(SE)\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003eSeasonal\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" rowspan=\"2\"\u003e\n \u003cp\u003eSigma\u003c/p\u003e\n \u003cp\u003e(SE)\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" rowspan=\"2\"\u003e\n \u003cp\u003eAIC\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" rowspan=\"2\"\u003e\n \u003cp\u003eBIC\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eAR\u003c/p\u003e\n \u003cp\u003e(SE)\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eMA\u003c/p\u003e\n \u003cp\u003e(SE)\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003eD2.ln. smooth admission number\u0026thinsp;=\u0026thinsp;ARIMA (1,2,1) SARIMA (1,0,1,4)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e\u003cstrong\u003e69.65\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e0.939\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003e(0.172)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e-0.829\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003e(0.229)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e0.116\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003e(0.149)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e-0.799\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003e(0.195)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e0.101\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003e(0.006)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e\u003cstrong\u003e-105.54\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e\u003cstrong\u003e-93.54\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eD2.ln.smooth admission number\u0026thinsp;=\u0026thinsp;ARIMA(4,2,1)SARIMA(1,0,1,4)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e65.25\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-0.885\u003c/p\u003e\n \u003cp\u003e( 0.142)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.999\u003c/p\u003e\n \u003cp\u003e(0.109)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-0.921\u003c/p\u003e\n \u003cp\u003e(0.129)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.771\u003c/p\u003e\n \u003cp\u003e(0 .233\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.096\u003c/p\u003e\n \u003cp\u003e(0.931)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e-140.49\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e-95.33824\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eD2.ln.smooth admission number\u0026thinsp;=\u0026thinsp;ARIMA(1,2,1)SARIMA(4,0,1,4)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e60.19\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.908\u003c/p\u003e\n \u003cp\u003e(0.205)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-0.032 (0.0693)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.099 (0.007)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.498\u003c/p\u003e\n \u003cp\u003e(0 .663)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.108\u003c/p\u003e\n \u003cp\u003e(0.693)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e-107.38\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e-95.83\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eD2.ln.smooth admission number ARIMA(1,2,4) SARIMA(1,0,1,4)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e67.25\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u0026minus;\u0026thinsp;.489\u003c/p\u003e\n \u003cp\u003e(0.565)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-0.756\u003c/p\u003e\n \u003cp\u003e(0.289)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-0.917\u003c/p\u003e\n \u003cp\u003e(0 .149)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.779\u003c/p\u003e\n \u003cp\u003e(0 .301)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.099\u003c/p\u003e\n \u003cp\u003e(0.025)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e-118.35\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e-99.50\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003ctfoot\u003e\n \u003ctr\u003e\n \u003ctd colspan=\"9\"\u003e*Akaike Information Criterion (AIC), Bayesian Information Criterion (BIC)\u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tfoot\u003e\n \u003c/table\u003e\n \u003c/div\u003e\n \u003cp\u003eThe ACF and PACF graphs (as shown in Fig. \u003cspan class=\"InternalRef\"\u003e6\u003c/span\u003e and Fig. \u003cspan class=\"InternalRef\"\u003e7\u003c/span\u003e) indicated that the hospitalization days\u0026apos; variable would be best modeled with an ARIMA of lags of 1\u0026ndash;3 for ACF and 1\u0026ndash;2 for PACF and one difference. Additionally, the graphs suggested using a SARIMA with lags 1 and 4 (for both ACF and PACF).\u003c/p\u003e\n \u003cp\u003eAfter comparing the goodness of fit measurement (some close values of goodness of fit measurements are listed in Table \u003cspan class=\"InternalRef\"\u003e3\u003c/span\u003e), the SARIMA (4,0,1,4) model was identified as the best for hospitalization days. The model was then fitted and diagnostic tools were used to evaluate the goodness of fit (portmanteau test P-Value\u0026thinsp;=\u0026thinsp;0.46) (Figs. \u003cspan class=\"InternalRef\"\u003e3\u003c/span\u003es, \u003cspan class=\"InternalRef\"\u003e4\u003c/span\u003es).\u003c/p\u003e\n \u003cdiv class=\"gridtable\"\u003e\u0026nbsp;\u003ctable id=\"Tab3\" border=\"1\"\u003e\n \u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eComparison of log-likelihood, AIC, BIC, Autocorrelation, moving average, and sigma coefficients of different models for selecting the best-fitted model in forecasting Hospitalization days\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\n \u003ccolgroup cols=\"7\"\u003e\u003c/colgroup\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003cth align=\"left\"\u003e\u0026nbsp;\u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eLog likelihood\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eAr(SE)\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eMa(SE)\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eSigma(SE)\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eAIC\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eBIC\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eLN. smooth long stay SARIMA (1,0,4,4)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e51.17\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.563\u003c/p\u003e\n \u003cp\u003e(0.173)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.487(0.58)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e.119\u003c/p\u003e\n \u003cp\u003e(0.530)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e-88.342\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e-71.33\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003eLN. smooth long staySARIMA (4,0,1,4)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e\u003cstrong\u003e48.91\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e0.563 (0.173)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026minus;\u0026thinsp;.426 (0.99)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e.0.113\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003e(0.530)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e\u003cstrong\u003e-83.82\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e\u003cstrong\u003e-66.80\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eLN. smooth long stay SARIMA (1,0,1,4)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e45.88\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-0.153\u003c/p\u003e\n \u003cp\u003e(0.454)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.462 (0.376)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.139\u003c/p\u003e\n \u003cp\u003e(.013)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e-83.77\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e-74.04\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eLN. smooth long stay SARIMA (4,1,4,4)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e54.09\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u0026minus;\u0026thinsp;.519 (0.225)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.179 (0.523)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.0958\u003c/p\u003e\n \u003cp\u003e(0.029)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e-92.19\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e-73.14\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eLN. smooth long stay SARIMA (4,1,1,4)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e49.26\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-0.294 (0.163)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-1.000009 3121.368\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.118\u003c/p\u003e\n \u003cp\u003e(0.592)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e-84.501\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e-67.839\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eLN. smooth long stay SARIMA (1,1,1,4)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e45.44\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.125 (0.127)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e.128\u003c/p\u003e\n \u003cp\u003e(0.011)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e-84.88\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e-77.74\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eLN. smooth long stay SARIMA (1,1,4,4)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e51.17\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-0.789 (0.258)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-0.426 (0.1)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e.119\u003c/p\u003e\n \u003cp\u003e(0.530)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e-86.29\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e-71.99\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003ctfoot\u003e\n \u003ctr\u003e\n \u003ctd colspan=\"7\"\u003e*Akaike Information Criterion (AIC), Bayesian Information Criterion (BIC)\u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tfoot\u003e\n \u003c/table\u003e\n \u003c/div\u003e\n \u003cp\u003eThe AC and PACF graphs displayed in Figs. \u003cspan class=\"InternalRef\"\u003e8\u003c/span\u003e and \u003cspan class=\"InternalRef\"\u003e9\u003c/span\u003e indicate that an ARIMA (1, 1, 4) model is suitable for the mortality proportion (some models that were similar by goodness of fit measurements are listed in Table \u003cspan class=\"InternalRef\"\u003e4\u003c/span\u003e), based on the considered indices (portmanteau test P-Value\u0026thinsp;=\u0026thinsp;0.69) (Figs. \u003cspan class=\"InternalRef\"\u003e5\u003c/span\u003es, \u003cspan class=\"InternalRef\"\u003e6\u003c/span\u003es).\u003c/p\u003e\n \u003cdiv class=\"gridtable\"\u003e\u0026nbsp;\u003ctable id=\"Tab4\" border=\"1\"\u003e\n \u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 4\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eComparison of log-likelihood, AIC, BIC, Autocorrelation, moving average, and sigma coefficients of different models for selecting the best-fitted model in forecasting mortality proportion\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\n \u003ccolgroup cols=\"7\"\u003e\u003c/colgroup\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003emodels\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eLog likelihood\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eAR\u003c/p\u003e\n \u003cp\u003e(SE)\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eMA\u003c/p\u003e\n \u003cp\u003e(SE)\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eSigma\u003c/p\u003e\n \u003cp\u003e(SE)\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eAIC\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eBIC\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eD1.ln. smooth mortality ARIMA (1,1,1)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e64.54\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.889\u003c/p\u003e\n \u003cp\u003e(0.039)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u0026minus;\u0026thinsp;.0078\u003c/p\u003e\n \u003cp\u003e(0.094)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.111\u003c/p\u003e\n \u003cp\u003e(0.005)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e-129.09\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e-114.37\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003eD1.ln. smooth mortality ARIMA (1,1,4)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e\u003cstrong\u003e72.03\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e0.886\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003e(0.1)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e-0.416\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003e(0.269)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e.0995\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003e(0.912)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e\u003cstrong\u003e-130.07\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e\u003cstrong\u003e-113.05\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eD1.ln. smooth mortality ARIMA (4,1,1)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e72.07\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.743\u003c/p\u003e\n \u003cp\u003e(0.139)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.99\u003c/p\u003e\n \u003cp\u003e(NC)*\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.099\u003c/p\u003e\n \u003cp\u003e(0.006)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e-132.14\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e-117.56\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eD1.ln. smooth mortality ARIMA (4,1,4)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e73.03\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.795\u003c/p\u003e\n \u003cp\u003e(0.255)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-0.411\u003c/p\u003e\n \u003cp\u003e(NC)*\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.097\u003c/p\u003e\n \u003cp\u003e(0.69)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e-128.07\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e-106.19\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003ctfoot\u003e\n \u003ctr\u003e\n \u003ctd colspan=\"7\"\u003e*Akaike Information Criterion (AIC), Bayesian Information Criterion (BIC), NC\u0026thinsp;=\u0026thinsp;no calculated\u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tfoot\u003e\n \u003c/table\u003e\n \u003c/div\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec7\" class=\"Section2\"\u003e\n \u003ch2\u003eForecasting of time series variables\u003c/h2\u003e\n \u003cp\u003eThe estimated monthly forecasted NICU admission census for the period of January 2023 to September 2025 ranges from 93 to 105 cases, as shown in Table \u003cspan class=\"InternalRef\"\u003e5\u003c/span\u003e. Furthermore, the monthly admissions to NICU have decreased during this period, as depicted in Fig. \u003cspan class=\"InternalRef\"\u003e7\u003c/span\u003e, with a trend coefficient of -0.222 and a P-Value of 0.002. However, when we consider the trend from 2016 to 2023, there is a slight rise, but it is not statistically significant, with a trend coefficient of 0.36 and a P-Value of 0.163, as shown in Fig. \u003cspan class=\"InternalRef\"\u003e10\u003c/span\u003e(2016\u0026ndash;2025).\u003c/p\u003e\n \u003cdiv class=\"gridtable\"\u003e\u0026nbsp;\u003ctable id=\"Tab5\" border=\"1\"\u003e\n \u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 5\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eThe forecasted number of admissions, hospitalization days, and mortality proportion using ARIMA (1,2,1) SARIMA (1,0,1,4), SARIMA (4,0,1,4), and ARIMA (1,1,4), respectively,\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\n \u003ccolgroup cols=\"4\"\u003e\u003c/colgroup\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eTime\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colspan=\"3\"\u003e\n \u003cp\u003ePredicted value\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eadmissions number ; ARIMA(1,2,1)SARIMA(1,0,1,4)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ehospitalization days; SARIMA (4,0,1,4)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003emortality proportion; ARIMA(1,1,4)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e2023m1\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e94.86262\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e12.47947\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e3.193621\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e2023m2\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e104.7546\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e12.24222\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e3.15402\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e2023m3\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e101.673\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e11.61682\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e3.789941\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e2023m4\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e105.1995\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e11.91629\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e4.09831\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e2023m5\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e101.2042\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e11.91629\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e4.15157\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e2023m6\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e102.636\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e12.19027\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e4.05896\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e2023m7\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e102.8402\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e12.853\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e3.702393\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e2023m8\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e102.6626\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e13.13674\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e3.371494\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e2023m9\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e102.6687\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e12.67798\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e3.162202\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e2023m10\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e102.3177\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e12.53526\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e3.009127\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e2023m11\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e102.4759\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e12.46693\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2.980458\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e2023m12\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e102.0668\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e12.17485\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e3.001916\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e2024m1\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e101.8813\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e11.98417\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2.99346\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e2024m2\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e101.4768\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e12.10709\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2.9725\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e2024m3\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e101.282\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e12.23928\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2.893365\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e2024m4\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e100.8444\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e12.04398\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2.769386\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e2024m5\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e100.8444\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e12.14263\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2.650515\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e2024m6\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e100.4837\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e12.23709\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2.533159\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e2024m7\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e100.0233\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e12.43997\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2.437697\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e2024m8\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e99.63045\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e12.52246\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2.370777\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e2024m9\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e99.13049\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e12.40494\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2.310666\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e2024m10\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e98.64646\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e12.36318\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2.256401\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e2024m11\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e98.1105\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e12.34774\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2.199562\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e2024m12\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e98.1105\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e12.27391\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2.130691\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e2025m1\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e96.42227\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e12.20712\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2.057809\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e2025m2\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e95.80264\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e12.23792\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1.982477\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e2025m3\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e95.17403\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e12.26797\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1.907469\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e2025m4\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e94.51074\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e12.20298\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1.839173\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e2025m5\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e93.83088\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e12.23394\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1.775703\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e2025m6\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e93.12\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e12.26516\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1.716126\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003c/table\u003e\n \u003c/div\u003e\n \u003cp\u003eLong hospitalizations in the NICU ranged from 11 to 13 days(Table \u003cspan class=\"InternalRef\"\u003e5\u003c/span\u003e).\u003c/p\u003e\n \u003cp\u003eMortality proportion forecasted ranged 1.72 to 4.15 cases in month. with mean(SD) equals at 2.79(0.72) (Fig. \u003cspan class=\"InternalRef\"\u003e11\u003c/span\u003e).\u003c/p\u003e\n \u003cp\u003eIn the case of the forecasted mortality proportion from 2016 to September 2025, it is expected that the probability of mortality proportion will decrease by -0.027 per unit increase in time (month) with a P-value of less than 0.001 (Fig. \u003cspan class=\"InternalRef\"\u003e12\u003c/span\u003e).\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec8\" class=\"Section2\"\u003e\n \u003ch2\u003eValidation of forecasting\u003c/h2\u003e\n \u003cp\u003eTo evaluate the accuracy of our forecasts, we used two metrics: the mean absolute percentage error (MAPE) and the root mean square error (RMSE). According to Muge Capan\u0026apos;s literature[\u003cspan class=\"CitationRef\"\u003e5\u003c/span\u003e], a MAPE value of less than 10% indicates highly accurate forecasting. The Table \u003cspan class=\"InternalRef\"\u003e6\u003c/span\u003e provides the MAPE and RMSE values for all of the variables that were forecasted.\u003c/p\u003e\n \u003cdiv class=\"gridtable\"\u003e\u0026nbsp;\u003ctable id=\"Tab6\" border=\"1\"\u003e\n \u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 6\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eAccuracy of forecasts by mean absolute percentage error (MAPE) and the root mean square error (RMSE)\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\n \u003ccolgroup cols=\"3\"\u003e\u003c/colgroup\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eModels\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eMAPE\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eRMSE\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003eadmissions number ; ARIMA(1,2,1)SARIMA(1,0,1,4)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e4.73\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.869\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003ehospitalization days; SARIMA (4,0,1,4)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e4.35\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.89\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003emortality proportion; ARIMA(1,1,4)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e2.03\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.021\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003c/table\u003e\n \u003c/div\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec9\" class=\"Section2\"\u003e\n \u003ch2\u003eRegression analysis on time series variables\u003c/h2\u003e\n \u003cp\u003eAccording to the regression time series analysis, there exists an inverse linear relationship between the number of hospitalizations per month and the duration of hospital stay. The coefficient of linear regression was estimated \u0026minus;\u0026thinsp;2.58, and the P-value was less than 0.001.\u003c/p\u003e\n \u003cp\u003eAlso, it has been observed that for every unit (day) increase in length of stay in NICU, the proportion of mortality increase by 0.339 (with a P-value\u0026thinsp;=\u0026thinsp;0.018) from 2016 to 2022 (B (SE)\u0026thinsp;=\u0026thinsp;0.339(0.139)), adjusted by admission number variable.\u003c/p\u003e\n\u003c/div\u003e"},{"header":"Discussion","content":"\u003cp\u003eThis is the first study in Iran to use time series analysis to mathematically model and predict admissions and mortality in the NICU. The study forecasted admission numbers, length of hospitalization, and mortality proportions in the NICU over the last 7 years for a period of 2.5 years (from January 2023 to September 2025).\u003c/p\u003e \u003cp\u003eIn the present study, the admission census was higher during the winter season, while the mean length of hospitalization days decreased during the same period. In the regression time series analysis, an inverse relationship was found between admission census and length of hospitalization (P-Value\u0026thinsp;\u0026lt;\u0026thinsp;0.01).\u003c/p\u003e \u003cp\u003eAfter conducting primary analysis and making necessary data adjustments, we used ARIMA models for forecasting, which are considered to be one of the most appropriate tools.\u003c/p\u003e \u003cp\u003eThere detected trend for admission number and mortality proportion. Also seasonal pattern was clear in admission number and hospitalization days in NICU.\u003c/p\u003e \u003cp\u003eWe selected an ARIMA (1,2,1) and SARIMA (1,0,1,4) for admissions number, SARIMA (4,0,1,4) for hospitalization days, and ARIMA (1,1,4) for mortality proportion in NICU as the best fitting models after model assessment. The goodness of fit and accuracy tests showed that the models can adequately explain the fluctuations in admission number, hospitalization days, and mortality proportion in NICU, and there was good matching between the observed values and the fitted values.\u003c/p\u003e \u003cp\u003eAccurate prediction of admission numbers, length of hospital stays, and mortality proportion is crucial for maintaining high-quality care, effective resource planning, and ensuring employee satisfaction in healthcare systems. Relying on a fixed value based on the previous year\u0026rsquo;s average daily census does not account for the dynamic nature of patient admissions over time.\u003c/p\u003e \u003cp\u003eBy forecasted findings from January 2023 to September 2025, the admission numbers appear to have decreased relatively (R= -0.222 and a P-Value of 0.002). However, no specific trend was observed in general from March 2016 to September 2025 (p\u0026thinsp;\u0026gt;\u0026thinsp;0.05).\u003c/p\u003e \u003cp\u003eThere has been a significant decrease in the incidence of mortality in neonates in the NICU.\u003c/p\u003e \u003cp\u003eThe highest mortality proportion in the NICU was recorded in February and April. A positive relationship was found between neonatal mortality and length of stay in the hospital (B\u0026thinsp;=\u0026thinsp;0.339) in the regression time series analysis. Fu (2023) identified critical risk factors affecting prolonged NICU stay, including birth weight, gestational age, sepsis, Necrotizing enterocolitis (NEC), bronchopulmonary dysplasia (BPD), and retinopathy of prematurity (ROM)[\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e]. On the other hand, with the increase in length of stay in the hospital, the possibility of nosocomial infection and mortality increases[\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e]. In Dalili's study, Mortality proportion was calculated 37% in neonates with acinetobacter \u003cem\u003eboumani\u003c/em\u003e infection (from 2016 to 2022)[\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eThe generalizability of these findings may be low. Additionally, this study only considered variations in admission numbers and mortality, without taking into account other impacting factors such as age, gender, socioeconomic status, environment, and politics. Nonetheless, the methodology and analyses could be used to improve decision-making, proper allocation, and use of health resources to further reduce the rate of deaths in the NICU.\u003c/p\u003e"},{"header":"Conclusion","content":"\u003cp\u003eIn this time series study, a downward trend was observed in mortality proportion, and seasonality patterns were more evident in admission numbers (increasing during the winter season) and hospitalization days (decreasing during the winter season) in the NICU. Regression time series appears while the length of stay in the hospital increases and, mortality proportion increases. Further extensive and well-designed studies are needed to investigate risk factors for long stays in the NICU and its management. Studies should also focus on interventions to effectively reduce long stays in the NICU and improve short- and long-term newborn outcomes\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eAcknowledgments\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eWe would like to acknowledge of Maternal-Fetal and neonatal research center, Tehran university of Medical sciences and all co-operator in the hospital registration system for collecting data and supervising.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthics approval and consent to participate\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe study was approved by the Research Ethics Committee of Tehran University of Medical Sciences (IR.TUMS.IKHC.REC. REC.1402.090), Tehran, Iran. All methods were performed in accordance with the relevant guidelines and regulations by including a statement in ethical approval contract and in accordance with the declarations of Helsinki. The information documented by the hospital registry system was used for the study and waived the need for informed consent by ethics committee of biomedical research, Imam Khomeini hospital complex, Tehran University of medical sciences. \u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent for publication\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003cstrong\u003eAvailability of data and materials\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe datasets and outputs used during the current study available from the corresponding author ( Leyla Sahebi/ [email protected]) on reasonable request.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u0026nbsp;Competing interests\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot aplicable\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003cstrong\u003eFunding\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot aplicable\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthors\u0026rsquo; contributions\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eH.D and L.S designed the study. L.S and M.Sh collected \u0026nbsp;data L.S modeled and analyzed data. L.S and H.D wrote the initial draft of the manuscript which was subsequently modified by M.Sh. All authors read and edited the manuscript for important intellectual content. All authors have seen and approved the final version of the manuscript.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u0026nbsp;Author information\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eHosein\u0026nbsp;Dalili, Professor. Maternal-Fetal and Neonatal Research Center, Family Health Research Institute, Imam Khomeini Hospital Complex . Tehran University of Medical Sciences, Tehran, Iran.\u003c/p\u003e\n\u003cp\u003eMamak Shariat, Professor. Vali-E-Asr Reproductive Health Research Center, Family Health Research Institute, Imam Khomeini Hospital Complex .Tehran University of Medical Sciences. Tehran, Iran\u003c/p\u003e\n\u003cp\u003eLeyla Sahebi*, Corresponding author.Ph.D. Maternal-Fetal and Neonatal Research Center, Family Health Research Institute, Imam Khomeini Hospital Complex. Tehran University of Medical Science, Tehran, Iran\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eSilva ABD, et al. Auto-Regressive Integrated Moving Average Model (ARIMA): conceptual and methodological aspects and applicability in infant mortality. Revista Brasileira de Sa\u0026uacute;de Materno Infantil. 2021;21:647\u0026ndash;56.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGudayu T, Zeleke E, Molla A. Time to Death and its Predictors among Neonates Admitted in the Intensive Care Unit of the University of Gondar Comprehensive Specialized Hospital, Northwest Ethiopia. Volume 10. Research and Reports in Neonatology; 2020. pp. 1\u0026ndash;10.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWesenu M, Kulkarni S, Tilahun T. Modeling Determinants of Time-To-Death in Premature Infants Admitted to Neonatal Intensive Care Unit in Jimma University Specialized Hospital. Annals Data Sci, 2017. 4.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMurray LL, et al. Forecasting ICU Census by Combining Time Series and Survival Models. Crit Care Explor. 2023;5(5):e0912.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCapan M, et al. Time Series Analysis for Forecasting Hospital Census: Application to the Neonatal Intensive Care Unit. Appl Clin Inf. 2016;7(2):275\u0026ndash;89.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSankar MJ, et al. When do newborns die? A systematic review of timing of overall and cause-specific neonatal deaths in developing countries. J Perinatol. 2016;36(Suppl 1):S1\u0026ndash;11.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJehan I, et al. Neonatal mortality, risk factors and causes: a prospective population-based cohort study in urban Pakistan. Bull World Health Organ. 2009;87(2):130\u0026ndash;8.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRogowski JA, et al. Nurse staffing and NICU infection rates. JAMA Pediatr. 2013;167(5):444\u0026ndash;50.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJakuskiene R, et al. Neonatal outcomes of very preterm infants admitted to a tertiary center in Lithuania between the years 2003 and 2005. Eur J Pediatr. 2011;170(10):1293\u0026ndash;303.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePenoyer DA. Nurse staffing and patient outcomes in critical care: a concise review. Crit Care Med, 2010. 38(7): pp. 1521-8; quiz 1529.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSheward L, et al. The relationship between UK hospital nurse staffing and emotional exhaustion and job dissatisfaction. J Nurs Manag. 2005;13(1):51\u0026ndash;60.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAiken LH, et al. Hospital nurse staffing and patient mortality, nurse burnout, and job dissatisfaction. JAMA. 2002;288(16):1987\u0026ndash;93.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTarnow-Mordi WO, et al. Hospital mortality in relation to staff workload: a 4-year study in an adult intensive-care unit. Lancet. 2000;356(9225):185\u0026ndash;9.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFu M et al. Risk factors for length of NICU stay of newborns: A systematic review. Front Pead, 2023. 11.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSheikhtaheri A, et al. Prediction of neonatal deaths in NICUs: development and validation of machine learning models. BMC Med Inf Decis Mak. 2021;21(1):131.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBekele T et al. Predictors of mortality among neonates hospitalized with neonatal sepsis: a case control study from southern Ethiopia. BMC Pediatr, 2022. 22.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHosein Dalili M, Shariat L, Sahebi et al. Survival and causes of death in infants admitted in NICU in Tehran (a retrospective cohort study 2016\u0026ndash;2022), 08 January 2024, PREPRINT (Version 1).under review. available at Research Square [\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.21203/rs.3.rs-3831825/v1]\u003c/span\u003e\u003cspan address=\"10.21203/rs.3.rs-3831825/v1]\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003c/ol\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":"bmc-medical-research-methodology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"bmrm","sideBox":"Learn more about [BMC Medical Research Methodology](http://bmcmedresmethodol.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/bmrm/default.aspx","title":"BMC Medical Research Methodology","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Intensive Care Units, Neonatal, Time Series Analysis, Forecasting, Mortality, Hospitalization","lastPublishedDoi":"10.21203/rs.3.rs-4606104/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4606104/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003eBackground\u003c/strong\u003e: \u0026nbsp;Neonatal intensive care units(NICUs) play a crucial role in caring for premature or critically ill newborns, but challenges persist in managing patient volumes and addressing mortality. This study aims to analyze the time series of the NICU admission numbers, hospitalization days, and mortality proportion.\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eMethods: \u003c/strong\u003eWe used seven years of retrospective daily NICU census data for model development (March 2016 - December 2022, N=7,216 infants). Best-fitting models of ARIMA and SARIMA were applied for forecasting admission number, long stay and mortality proportion in STATA.14 and SPSS.20. The accuracy of forecasting approved by root mean squared error (RMSE), mean absolute percentage error (MAPE).\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eResults: \u003c/strong\u003eWe observed a decreasing trend in mortality proportion in the NICU, with more pronounced seasonal patterns in admission numbers (which increased during the winter season) and length of stay (which decreased during the winter season). Our regression time series analysis showed that as the length of stay in the hospital increases, the mortality proportion also increases.\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConclusion:\u003c/strong\u003e More extensive and well-designed studies are required to investigate the risk factors for prolonged stays in the NICU and how to manage them. Research should also concentrate on interventions that can effectively reduce long NICU stays and improve short- and long-term outcomes for newborns.\u003c/p\u003e","manuscriptTitle":"Time Series Analysis for forecasting neonatal intensive care unit census and neonatal mortality","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-07-18 20:31:00","doi":"10.21203/rs.3.rs-4606104/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorAssigned","content":"","date":"2024-06-21T18:08:45+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-06-21T18:08:18+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Medical Research Methodology","date":"2024-06-19T13:07:49+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-medical-research-methodology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"bmrm","sideBox":"Learn more about [BMC Medical Research Methodology](http://bmcmedresmethodol.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/bmrm/default.aspx","title":"BMC Medical Research Methodology","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"b0014b7f-1eae-430b-91ab-efef6b93e0c8","owner":[],"postedDate":"July 18th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2024-10-22T14:38:45+00:00","versionOfRecord":[],"versionCreatedAt":"2024-07-18 20:31:00","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4606104","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4606104","identity":"rs-4606104","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}