Results Comparison of Cervical Cancer Early Detection Using Cerviray with VIA Test

Results Comparison of Cervical Cancer Early Detection Using Cerviray with VIA Test | 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 Results Comparison of Cervical Cancer Early Detection Using Cerviray with VIA Test Ali Budi Harsono, Hadi Susiarno, Dodi Suardi, Kemala Isnainiasih Mantilidewi, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3998751/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Objectives This study investigates the performance of Cerviray A.I. and evaluation of Cerviray A.I. by an expert, an artificial intelligence (AI) technology for diagnosing cervical cancer, aiming to compare its sensitivity, specificity, positive predictive value (PPV), and area under the receiver operating characteristic curve (AUC ROC) with the Visual Inspection with Acetic Acid (VIA) test. Results The study involved 44 patients from various health centers in West Java Province. Cerviray A.I., evaluation of Cerviray® A.I. by an expert, and VIA tests were administered to high-risk women of childbearing age. Preliminary results indicated that Cerviray A.I. had a sensitivity of 42.9%, specificity and PPV of 100%, and an AUC ROC of 71.4%. In comparison, the evaluation of Cerviray by an expert demonstrated a sensitivity of 71.4%, specificity of 97.3%, PPV of 83.3%, and AUC ROC of 84.4%. Evaluation of Cerviray A.I. by an expert outperformed Cerviray A.I. in AUC ROC. cervical cancer cerviray via test early detection Figures Figure 1 Introduction Cervical cancer is a cancer caused by Human Papilloma Virus (HPV) infection. It is considered one of the major health problems in women worldwide. Cervical cancer is the eighth most common cancer in the world, with an estimated 662,301 new cases and 348,874 deaths in 2022 worldwide, and the prevalence of HPV infection in women was 5.2%. About 90% of new cases and deaths from cervical cancer occur in low- and middle-income countries.[ 1 , 2 ] As the causative agent of almost all cases of cervical cancer, HPV can infect both male and female genital regions, including the skin of the vulva, penis, and anus; the lining of the vagina, cervix, and rectum; and the lining of the mouth and throat.[ 3 ] Unlike other sexually transmitted infections, most signs and symptoms of HPV are absent. Therefore, most people are unaware of HPV infection in their bodies. HPV types 16 and 18 are the most oncogenic virus types and are responsible for causing more than 75% of cervical cancer cases and most other genital cancers.[ 4 ] As time goes by, Artificial Intelligence technology is growing. Artificial intelligence (AI) in the medical field can improve the quality of care and cost-effectiveness.[ 5 ] Cerviray A.I. is an AI technology for diagnosing cervical cancer using a portable colposcope and artificial intelligence-based software (AIDOTNet algorithm with 93% sensitivity and 89% specificity). The Cerviray A.I. helps make VIA screening more objective. It classifies cervical cancer risk into four stages: normal, CIN1, CIN2-3, and CIN3+; it detects abnormal cervical lesions and divides them into two stages: abnormal and suspected cancer. Cerviray A.I. also has a telemedicine system that enables remote consultation with experts (Fig. 3). With this artificial intelligence and telemedicine system, Cerviray A.I. can maintain the advantages of VIA and help overcome its disadvantages.[ 6 , 7 ] This study aimed to determine the sensitivity, specificity, PPV, and AUC ROC of Cerviray A.I. and the evaluation of Cerviray A.I. by an expert compared to the VIA test. Subjects and method This study was a diagnostic test conducted to compare the performance of Cerviray A.I. and the evaluation of Cerviray A.I. by an expert compared to the VIA test. The study subjects were patients screened using Cerviray A.I., the evaluation of Cerviray A.I. by an expert, and VIA test in one clinic and four health centers, namely Mawar Clinic, Pasteur, Ibrahim Aji Health Center, Garuda Health Center, and Puter health center who met the inclusion criteria and did not meet the exclusion criteria. The target population included in this study were women of childbearing age who would be screened for cervical cancer in West Java Province. The target population was high-risk women of childbearing age who would be screened for cervical cancer (by Cerviray A.I., the evaluation of Cerviray A.I. by an expert, and VIA test) at Mawar Clinic and the other four health centers with samples taken by total sampling. The inclusion criteria for this study were all data on the results of the Cerviray A.I, the evaluation of Cerviray A.I. by an expert, and VIA test from high-risk fertile age patients in the period March–October 2023, while the exclusion criteria for this study were incomplete data, patients refusing to be examined. Patients refused to participate in the study. Data processing was carried out by presenting categorical data in the form of proportion data (%) using tables. Data analysis to determine the accuracy of diagnostic tests was carried out by analyzing sensitivity, specificity, and PPV (positive predictive value), and Kappa statistics were used to compare consistency between diagnostic tools. Results A total of 44 patients showed population and disease characteristics, as shown in Table 1. Anatomical pathology examination of the seven patients showed the results of CIN I in as many as 4 cases (57.1%), followed by CIN II in as many as 1 case (14.3%). Malignancy cases in the form of endocervical squamous metaplasia were 1 case (14.3%), and non-malignancy cases were low-grade intraepithelial lesions accompanied by non-specific chronic inflammation in the cervical region. Colposcopic examination of the seven patients showed Normal/CIN 1 results (Table 1). Table 1. Characteristics of the study population. Characteristics Average Age 29,57 HPV DNA High-risk Low-risk or negative Unknown 3 5 16 Histopathology Benign CIN 1 CIN 2–3 Invasive cancer 1 4 1 1 The results of the interim analysis of the sensitivity, specificity, and PPV values of Cerviray A.I. and the evaluation of Cerviray A.I. by an expert are shown in Table 3. The sensitivity, specificity, PPV, and AUC ROC values of Cerviray A.I. were 42.9% (95% CI 12.9–77.3), 100%, 100%, and 71.4% (95% CI 46.2–96.6), respectively. The sensitivity, specificity, PPV, and AUC ROC values of the evaluation of Cerviray A.I. by an expert were 71.4% (95% CI 35.0-94.6), 97.3% (95% CI 88.6–99.8), 83.3% (95% CI 44.6–99.0), and 84.4% (63.7–100.0), respectively (Table 2 ). Table 2 Sensitivity, specificity, PPV, and AUC values of the two diagnostic tools. Cerviray AI (n = 44) Cerviray Expert (n = 44) % 95% CI % 95% CI Sensitivitas 42,9 12,9–77,3 71,4 35,0–94,6 Spesifisitas 100 - 97,3 88,6–99,8 PPV 100 - 83,3 44,6–99,0 AUC 71,4 46,2–96,6 84,4 63,7–100,0 PPV: Positive Predictive Value; AUC: Area Under Curve The ROC curves showed each tool's diagnostic ability, where an expert evaluated Cerviray A.I. by an expert showed higher AUC values than Cerviray A.I., with AUC values of 0.844 and 0.714, respectively (Fig. 1 ). The correlation between each diagnostic tool was analyzed using Kappa statistics with a value of 0.596 and p = 0.02 between Cerviray AI and an expert's evaluation of Cerviray AI. Discussion Cervical cancer is preventable and curable if detected early and managed effectively. However, cervical cancer is the eighth most prevalent cancer worldwide, having claimed the lives of more than 348,874 women in 2022.[ 1 ] Screening in the prevention of cervical cancer is a step taken to reduce the incidence of cervical cancer by 50–80%.29 Some screening tests should be sensitive, easy to obtain, and can be used independently by primary care physicians. Screening tools such as Cerviray® and VIA tests are easy to use and provide information quickly after the examination.[ 6 , 8 ] Cerviray A.I. showed sensitivity, specificity, PPV, and ROC curve AUC of 42.9%, 100%, 100%, and 0.714 in this study. The sensitivity of Cerviray A.I. is low enough to assess whether a person has precancerous lesions. Still, the 100% PPV value of Cerviray A.I. indicates that the tool is reliable when the test is positive. The AUC value of Cerviray A.I. was 71.4%, which indicates that Cerviray A.I. is still acceptable as a diagnostic tool for precancerous lesions. The result of this study is quite different from the study conducted by the previous study, where Cerviray A.I. had sensitivity, specificity, PPV, and ROC curve AUC values of 74.14%, 83.05%, 81.13%, and 0.777%. The difference between the two was significant in the sensitivity value, but they were categorized similarly in the ROC curve AUC value classification.[ 6 ] The evaluation of Cerviray A.I. by an expert result from re-evaluation by experts directly through the Cerviray® website portal. The results of the evaluation of Cerviray A.I. by an expert in this study showed sensitivity, specificity, PPV, and ROC curve AUC of 71.4%, 97.3%, 83.3%, 0.844. The sensitivity of the evaluation of Cerviray A.I. by an expert is good enough to assess whether someone has precancerous lesions, supported by the PPV and AUC values that are good enough so that the evaluation of Cerviray A.I. by expert results correct the results of Cerviray A.I. This result is quite close to the study conducted by the previous study, where the evaluation of Cerviray A.I. by an expert was conducted by two different doctors who had sensitivity, specificity, PPV, and ROC curve AUC values of 84.48% and 83.62%, 77.97% and 74.58%, 79.03% and 76.38%, and 0.7999 and 0.769. The correction of this study and the previous study conducted by the examining physician showed that the accuracy of the assessment would be better if the AI reading results were combined with the physician's examination results. The difference between these two studies may be due to the different reference standards. The previous study used cytology as a reference, and this study used VIA test results.[ 6 ] Kappa statistical test results showed a value of 0.596 and p = 0.02 between Cerviray A.I. and an expert's evaluation of Cerviray A.I. These results indicate acceptable measurement consistency between the two diagnostic tools. Few diseases can illustrate global inequalities as clearly as cervical cancer. Almost 90% of cervical cancer deaths in 2020 occurred in low- and middle-income countries. This is where the burden of cervical cancer is greatest, as community access to health services is still very limited, and screening and treatment of the disease are not widely implemented and are inadequate.[ 9 ] An ambitious, integrated, and inclusive strategy has been developed by WHO to guide the elimination of cervical cancer as a public health problem.[ 10 ] Cerviray A.I. is a promising applicative innovation in developing cervical cancer screening in resource-limited developing countries, including Indonesia. Cerviray A.I. is equipped with artificial intelligence software and telemedicine features that make VIA screening more objective and less dependent on the experience/competence of the examiner. Cerviray A.I. can maintain the advantages of VIA and help overcome its disadvantages. Conclusion This study underscores the potential of Cerviray A.I. and the evaluation of Cerviray A.I. by an expert in cervical cancer diagnosis, highlighting their distinct performance metrics. The findings suggest that the evaluation of Cerviray A.I. by an expert, enhanced sensitivity and diagnostic accuracy, could serve as a valuable tool in complementing traditional methods. Limitations This study was a single-center study with a limited number of participants. In addition, this is a preliminary attempt to determine the accuracy of Cerviray's A.I. compared to expert assessment of cervical precancerous lesions. Therefore, a larger study with more participants is needed to confirm the findings of this study. List Of Abbreviations AI artificial intelligence PPV positive predictive value AUC ROC area under the receiver operating characteristic curve VIA Visual inspection with acetic acid HPV Human papilloma virus VIA Visual inspection with acetic acid Declarations Ethics Approval and Informed Consent to Participate This research was conducted after obtaining approval and recommendations from the Ethics Committee Review Board of Dr. Hasan Sadikin General Hospital – Faculty of Medicine, Universitas Padjadjaran No. 622/UN6.KEP/EC/2023 Consent for publication All authors declare that approval of the version of the manuscript to be published has been obtained Availability of data and materials section The authors declare that the personal data from any patients involved in this study will not be shared based on patients’ confidentialities. Competing Interest The authors have declared that no competing interest exists. Funding No funding. Authors’ contributions Study conception and design: ABH Data collection: ABH, KIM Analysis and interpretation of result: ABH, KIM, VDW Draft manuscript preparation: ABH, KIM, VDW Acknowledgements We want to thank all the clinic and health center staff who have helped us greatly in data collection and patient recruitment. References Global Cancer Observatory. Global: incidence, mortality and prevalence by cancer site [Internet]. 2022 [cited 2024 Feb 24]. Available from: https://gco.iarc.who.int/media/globocan/factsheets/cancers/23-cervix-uteri-fact-sheet.pdf . Winarto H, Habiburrahman M, Dorothea M, Wijaya A, Nuryanto KH, Kusuma F, et al. Knowledge, attitudes, and practices among Indonesian urban communities regarding HPV infection, cervical cancer, and HPV vaccination. PLoS ONE. 2022;17:e0266139. Mitchell K, Saraiya M, Bhatt A. Increasing HPV Vaccination Rates Through National Provider Partnerships. J Womens Health. 2019;28:747–51. Markowitz LE, Dunne EF, Saraiya M, Chesson HW, Curtis CR, Gee J, et al. Human Papillomavirus Vaccination Recommendations of the Advisory Committee on Immunization Practices (ACIP). MMWR Recommendations Rep. 2014;63:1–30. Waring J, Lindvall C, Umeton R. Automated machine learning: Review of the state-of-the-art and opportunities for healthcare. Artif Intell Med. 2020;104:101822. Kim S, Lee H, Lee S, Song JY, Lee JK, Lee NW. Role of Artificial Intelligence Interpretation of Colposcopic Images in Cervical Cancer Screening. Healthc (Switzerland). 2022;10:468. Harsono AB, Susiarno H, Suardi D, Owen L, Fauzi H, Kireina J, et al. Cervical pre-cancerous lesion detection: development of smartphone-based VIA application using artificial intelligence. BMC Res Notes. 2022;15:356. David J, Joshi V, Jebin Aaron D, Baghel P. A Comparative Analysis of Visual Inspection With Acetic Acid, Cervical Cytology, and Histopathology in the Screening and Early Detection of Premalignant and Malignant Lesions of the Cervix. Cureus. 2022;14:e29762. World Health Organization. Framework for Monitoring the Implementation of the WHO Global Strategy to Accelerate the Elimination of Cervical Cancer as a Public Health Problem: including indicator metadata [Internet]. 2023 Feb. Available from: https://cdn.who.int/media/docs/default-source/ncds/ncd-surveillance/cxca/220121-bls21466-who-cp-accompany-doc_v01-web_.pdf?sfvrsn=2d2c 811c_5&download=true. eClinicalMedicine. Global strategy to eliminate cervical cancer as a public health problem: are we on track? [Internet]. EClinicalMedicine. 2023 Jan. Available from: https://www.thelancet.com/action/showPdf?pii=S2589-5370%2823%2900019-6 . Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted 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-3998751","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":276775614,"identity":"4c58e9ff-018d-4edb-b59d-c0e71bac7518","order_by":0,"name":"Ali Budi Harsono","email":"","orcid":"","institution":"Universitas Padjadjaran–Dr. Hasan Sadikin General Hospital","correspondingAuthor":false,"prefix":"","firstName":"Ali","middleName":"Budi","lastName":"Harsono","suffix":""},{"id":276775615,"identity":"f6effc56-5819-4e0c-9a48-58e823029025","order_by":1,"name":"Hadi Susiarno","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABAklEQVRIiWNgGAWjYBACAyA6AGKwgbkVMEEGBh6GA0RpOUOkFgSPsQ2hhQGXFnP2wxsPMPw5bM/HfvbZg4/zDucBRTYw/KhhkOHDocWyJ63gAGPb4cQ2nnRzw5nbDheDRBh7jjHwSOJy2IEcgwOMDYcT2BjS2KR5tx1O3AAUYeBtYOAxwKXl/BsDsMPY+J8BtcwBagGKMP7Fp+UG0BYGtsOMbRIgWxqAWoAizHhtufGs4EBiW3pim8QzNskZx9ITd854VnBY5pgEbr+cT9784cMfa3v5/jQ2iQ811onb+ZM3PnxTY2OPK8TAIAHFEAZwjEjgUY9hLwlqR8EoGAWjYGQAAMmSXxKE2yPfAAAAAElFTkSuQmCC","orcid":"","institution":"Universitas Padjadjaran–Dr. Hasan Sadikin General Hospital","correspondingAuthor":true,"prefix":"","firstName":"Hadi","middleName":"","lastName":"Susiarno","suffix":""},{"id":276775616,"identity":"73e0a001-bf61-4062-977a-b217ec142d06","order_by":2,"name":"Dodi Suardi","email":"","orcid":"","institution":"Universitas Padjadjaran–Dr. Hasan Sadikin General Hospital","correspondingAuthor":false,"prefix":"","firstName":"Dodi","middleName":"","lastName":"Suardi","suffix":""},{"id":276775617,"identity":"88284174-6399-4233-8264-9a4850be50ad","order_by":3,"name":"Kemala Isnainiasih Mantilidewi","email":"","orcid":"","institution":"Universitas Padjadjaran–Dr. Hasan Sadikin General Hospital","correspondingAuthor":false,"prefix":"","firstName":"Kemala","middleName":"Isnainiasih","lastName":"Mantilidewi","suffix":""},{"id":276775618,"identity":"fd9d4900-9b5a-4020-a547-ebeefabd8940","order_by":4,"name":"Viko Duvadilan Wibowo","email":"","orcid":"","institution":"Universitas Padjadjaran–Dr. Hasan Sadikin General Hospital","correspondingAuthor":false,"prefix":"","firstName":"Viko","middleName":"Duvadilan","lastName":"Wibowo","suffix":""},{"id":276775619,"identity":"820951c8-7782-41db-bf43-3fb539909270","order_by":5,"name":"Yudi Mulyana Hidayat","email":"","orcid":"","institution":"Universitas Padjadjaran–Dr. Hasan Sadikin General Hospital","correspondingAuthor":false,"prefix":"","firstName":"Yudi","middleName":"Mulyana","lastName":"Hidayat","suffix":""}],"badges":[],"createdAt":"2024-02-29 06:32:15","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3998751/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3998751/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":52450177,"identity":"f5f29902-0073-4c6d-b0fc-5db687e91f91","added_by":"auto","created_at":"2024-03-11 19:03:52","extension":"jpg","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":47217,"visible":true,"origin":"","legend":"\u003cp\u003eROC curve of Cerviray A.I. and the evaluation of Cerviray A.I. by expert against VIA test.\u003c/p\u003e","description":"","filename":"Figure1.jpg","url":"https://assets-eu.researchsquare.com/files/rs-3998751/v1/4491e6413f4f12d1e29de3cc.jpg"},{"id":52453205,"identity":"73792bb4-9865-4334-8a88-43d1a6fd944b","added_by":"auto","created_at":"2024-03-11 19:19:57","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":269831,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3998751/v1/89c5b45a-bc7f-4dd4-843a-a52e5ef615f3.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Results Comparison of Cervical Cancer Early Detection Using Cerviray with VIA Test","fulltext":[{"header":"Introduction","content":"\u003cp\u003eCervical cancer is a cancer caused by Human Papilloma Virus (HPV) infection. It is considered one of the major health problems in women worldwide. Cervical cancer is the eighth most common cancer in the world, with an estimated 662,301 new cases and 348,874 deaths in 2022 worldwide, and the prevalence of HPV infection in women was 5.2%. About 90% of new cases and deaths from cervical cancer occur in low- and middle-income countries.[\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e, \u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]\u003c/p\u003e \u003cp\u003eAs the causative agent of almost all cases of cervical cancer, HPV can infect both male and female genital regions, including the skin of the vulva, penis, and anus; the lining of the vagina, cervix, and rectum; and the lining of the mouth and throat.[\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e] Unlike other sexually transmitted infections, most signs and symptoms of HPV are absent. Therefore, most people are unaware of HPV infection in their bodies. HPV types 16 and 18 are the most oncogenic virus types and are responsible for causing more than 75% of cervical cancer cases and most other genital cancers.[\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]\u003c/p\u003e \u003cp\u003eAs time goes by, Artificial Intelligence technology is growing. Artificial intelligence (AI) in the medical field can improve the quality of care and cost-effectiveness.[\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e] Cerviray A.I. is an AI technology for diagnosing cervical cancer using a portable colposcope and artificial intelligence-based software (AIDOTNet algorithm with 93% sensitivity and 89% specificity). The Cerviray A.I. helps make VIA screening more objective. It classifies cervical cancer risk into four stages: normal, CIN1, CIN2-3, and CIN3+; it detects abnormal cervical lesions and divides them into two stages: abnormal and suspected cancer. Cerviray A.I. also has a telemedicine system that enables remote consultation with experts (Fig.\u0026nbsp;3). With this artificial intelligence and telemedicine system, Cerviray A.I. can maintain the advantages of VIA and help overcome its disadvantages.[\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e, \u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e] This study aimed to determine the sensitivity, specificity, PPV, and AUC ROC of Cerviray A.I. and the evaluation of Cerviray A.I. by an expert compared to the VIA test.\u003c/p\u003e "},{"header":"Subjects and method","content":"\u003cp\u003eThis study was a diagnostic test conducted to compare the performance of Cerviray A.I. and the evaluation of Cerviray A.I. by an expert compared to the VIA test. The study subjects were patients screened using Cerviray A.I., the evaluation of Cerviray A.I. by an expert, and VIA test in one clinic and four health centers, namely Mawar Clinic, Pasteur, Ibrahim Aji Health Center, Garuda Health Center, and Puter health center who met the inclusion criteria and did not meet the exclusion criteria.\u003c/p\u003e \u003cp\u003eThe target population included in this study were women of childbearing age who would be screened for cervical cancer in West Java Province. The target population was high-risk women of childbearing age who would be screened for cervical cancer (by Cerviray A.I., the evaluation of Cerviray A.I. by an expert, and VIA test) at Mawar Clinic and the other four health centers with samples taken by total sampling.\u003c/p\u003e \u003cp\u003eThe inclusion criteria for this study were all data on the results of the Cerviray A.I, the evaluation of Cerviray A.I. by an expert, and VIA test from high-risk fertile age patients in the period March\u0026ndash;October 2023, while the exclusion criteria for this study were incomplete data, patients refusing to be examined. Patients refused to participate in the study.\u003c/p\u003e \u003cp\u003eData processing was carried out by presenting categorical data in the form of proportion data (%) using tables. Data analysis to determine the accuracy of diagnostic tests was carried out by analyzing sensitivity, specificity, and PPV (positive predictive value), and Kappa statistics were used to compare consistency between diagnostic tools.\u003c/p\u003e"},{"header":"Results","content":"\u003cp\u003eA total of 44 patients showed population and disease characteristics, as shown in Table\u0026nbsp;1. Anatomical pathology examination of the seven patients showed the results of CIN I in as many as 4 cases (57.1%), followed by CIN II in as many as 1 case (14.3%). Malignancy cases in the form of endocervical squamous metaplasia were 1 case (14.3%), and non-malignancy cases were low-grade intraepithelial lesions accompanied by non-specific chronic inflammation in the cervical region. Colposcopic examination of the seven patients showed Normal/CIN 1 results (Table\u0026nbsp;1).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 1.\u0026nbsp;\u003c/strong\u003eCharacteristics of the study population.\u003c/p\u003e\n\u003cdiv class=\"gridtable\"\u003e\u003ctable id=\"Taba\" border=\"1\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCharacteristics\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAverage\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAge\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e29,57\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eHPV DNA\u003c/p\u003e\n \u003cp\u003eHigh-risk\u003c/p\u003e\n \u003cp\u003eLow-risk or negative\u003c/p\u003e\n \u003cp\u003eUnknown\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cbr\u003e\u003c/p\u003e\n \u003cp\u003e3\u003c/p\u003e\n \u003cp\u003e5\u003c/p\u003e\n \u003cp\u003e16\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eHistopathology\u003c/p\u003e\n \u003cp\u003eBenign\u003c/p\u003e\n \u003cp\u003eCIN 1\u003c/p\u003e\n \u003cp\u003eCIN 2\u0026ndash;3\u003c/p\u003e\n \u003cp\u003eInvasive cancer\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cbr\u003e\u003c/p\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003cp\u003e4\u003c/p\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003cp\u003e1\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\u003e\u003cbr\u003e\u003c/p\u003e\n\u003cp\u003eThe results of the interim analysis of the sensitivity, specificity, and PPV values of Cerviray A.I. and the evaluation of Cerviray A.I. by an expert are shown in Table 3. The sensitivity, specificity, PPV, and AUC ROC values of Cerviray A.I. were 42.9% (95% CI 12.9\u0026ndash;77.3), 100%, 100%, and 71.4% (95% CI 46.2\u0026ndash;96.6), respectively. The sensitivity, specificity, PPV, and AUC ROC values of the evaluation of Cerviray A.I. by an expert were 71.4% (95% CI 35.0-94.6), 97.3% (95% CI 88.6\u0026ndash;99.8), 83.3% (95% CI 44.6\u0026ndash;99.0), and 84.4% (63.7\u0026ndash;100.0), respectively (Table \u003cspan class=\"InternalRef\"\u003e2\u003c/span\u003e).\u0026nbsp;\u003c/p\u003e\n\u003ctable id=\"Tab1\" border=\"1\"\u003e\n \u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eSensitivity, specificity, PPV, and AUC values of the two diagnostic tools.\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003cth align=\"left\"\u003e\u0026nbsp;\u003c/th\u003e\n \u003cth align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003eCerviray AI\u003c/p\u003e\n \u003cp\u003e(n\u0026thinsp;=\u0026thinsp;44)\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003eCerviray Expert\u003c/p\u003e\n \u003cp\u003e(n\u0026thinsp;=\u0026thinsp;44)\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003cth align=\"left\"\u003e\u0026nbsp;\u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003e%\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003e95% CI\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003e%\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003e95% CI\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\u003eSensitivitas\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e42,9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e12,9\u0026ndash;77,3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e71,4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e35,0\u0026ndash;94,6\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003eSpesifisitas\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e100\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=\"char\"\u003e\n \u003cp\u003e97,3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e88,6\u0026ndash;99,8\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003ePPV\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e100\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=\"char\"\u003e\n \u003cp\u003e83,3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e44,6\u0026ndash;99,0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003eAUC\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e71,4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e46,2\u0026ndash;96,6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e84,4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e63,7\u0026ndash;100,0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003ctfoot\u003e\n \u003ctr\u003e\n \u003ctd colspan=\"5\"\u003ePPV: Positive Predictive Value; AUC: Area Under Curve\u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tfoot\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003cbr\u003e\u003c/p\u003e\n\u003cp\u003eThe ROC curves showed each tool\u0026apos;s diagnostic ability, where an expert evaluated Cerviray A.I. by an expert showed higher AUC values than Cerviray A.I., with AUC values of 0.844 and 0.714, respectively (Fig. \u003cspan class=\"InternalRef\"\u003e1\u003c/span\u003e). The correlation between each diagnostic tool was analyzed using Kappa statistics with a value of 0.596 and p\u0026thinsp;=\u0026thinsp;0.02 between Cerviray AI and an expert\u0026apos;s evaluation of Cerviray AI.\u003c/p\u003e"},{"header":"Discussion","content":"\u003cp\u003eCervical cancer is preventable and curable if detected early and managed effectively. However, cervical cancer is the eighth most prevalent cancer worldwide, having claimed the lives of more than 348,874 women in 2022.[\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]\u003c/p\u003e \u003cp\u003eScreening in the prevention of cervical cancer is a step taken to reduce the incidence of cervical cancer by 50\u0026ndash;80%.29 Some screening tests should be sensitive, easy to obtain, and can be used independently by primary care physicians. Screening tools such as Cerviray\u0026reg; and VIA tests are easy to use and provide information quickly after the examination.[\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e, \u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]\u003c/p\u003e \u003cp\u003eCerviray A.I. showed sensitivity, specificity, PPV, and ROC curve AUC of 42.9%, 100%, 100%, and 0.714 in this study. The sensitivity of Cerviray A.I. is low enough to assess whether a person has precancerous lesions. Still, the 100% PPV value of Cerviray A.I. indicates that the tool is reliable when the test is positive. The AUC value of Cerviray A.I. was 71.4%, which indicates that Cerviray A.I. is still acceptable as a diagnostic tool for precancerous lesions. The result of this study is quite different from the study conducted by the previous study, where Cerviray A.I. had sensitivity, specificity, PPV, and ROC curve AUC values of 74.14%, 83.05%, 81.13%, and 0.777%. The difference between the two was significant in the sensitivity value, but they were categorized similarly in the ROC curve AUC value classification.[\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]\u003c/p\u003e \u003cp\u003eThe evaluation of Cerviray A.I. by an expert result from re-evaluation by experts directly through the Cerviray\u0026reg; website portal. The results of the evaluation of Cerviray A.I. by an expert in this study showed sensitivity, specificity, PPV, and ROC curve AUC of 71.4%, 97.3%, 83.3%, 0.844. The sensitivity of the evaluation of Cerviray A.I. by an expert is good enough to assess whether someone has precancerous lesions, supported by the PPV and AUC values that are good enough so that the evaluation of Cerviray A.I. by expert results correct the results of Cerviray A.I. This result is quite close to the study conducted by the previous study, where the evaluation of Cerviray A.I. by an expert was conducted by two different doctors who had sensitivity, specificity, PPV, and ROC curve AUC values of 84.48% and 83.62%, 77.97% and 74.58%, 79.03% and 76.38%, and 0.7999 and 0.769. The correction of this study and the previous study conducted by the examining physician showed that the accuracy of the assessment would be better if the AI reading results were combined with the physician's examination results. The difference between these two studies may be due to the different reference standards. The previous study used cytology as a reference, and this study used VIA test results.[\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]\u003c/p\u003e \u003cp\u003eKappa statistical test results showed a value of 0.596 and p\u0026thinsp;=\u0026thinsp;0.02 between Cerviray A.I. and an expert's evaluation of Cerviray A.I. These results indicate acceptable measurement consistency between the two diagnostic tools.\u003c/p\u003e \u003cp\u003eFew diseases can illustrate global inequalities as clearly as cervical cancer. Almost 90% of cervical cancer deaths in 2020 occurred in low- and middle-income countries. This is where the burden of cervical cancer is greatest, as community access to health services is still very limited, and screening and treatment of the disease are not widely implemented and are inadequate.[\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e] An ambitious, integrated, and inclusive strategy has been developed by WHO to guide the elimination of cervical cancer as a public health problem.[\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e]\u003c/p\u003e \u003cp\u003eCerviray A.I. is a promising applicative innovation in developing cervical cancer screening in resource-limited developing countries, including Indonesia. Cerviray A.I. is equipped with artificial intelligence software and telemedicine features that make VIA screening more objective and less dependent on the experience/competence of the examiner. Cerviray A.I. can maintain the advantages of VIA and help overcome its disadvantages.\u003c/p\u003e"},{"header":"Conclusion","content":"\u003cp\u003eThis study underscores the potential of Cerviray A.I. and the evaluation of Cerviray A.I. by an expert in cervical cancer diagnosis, highlighting their distinct performance metrics. The findings suggest that the evaluation of Cerviray A.I. by an expert, enhanced sensitivity and diagnostic accuracy, could serve as a valuable tool in complementing traditional methods.\u003c/p\u003e "},{"header":"Limitations","content":"\u003cp\u003eThis study was a single-center study with a limited number of participants. In addition, this is a preliminary attempt to determine the accuracy of Cerviray's A.I. compared to expert assessment of cervical precancerous lesions. Therefore, a larger study with more participants is needed to confirm the findings of this study.\u003c/p\u003e"},{"header":"List Of Abbreviations","content":"\u003cdiv class=\"DefinitionList\"\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003eAI\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eartificial intelligence\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003ePPV\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003epositive predictive value\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003eAUC ROC\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003earea under the receiver operating characteristic curve\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003eVIA\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eVisual inspection with acetic acid\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003eHPV\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eHuman papilloma virus\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003eVIA\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eVisual inspection with acetic acid\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003c/div\u003e"},{"header":"Declarations","content":"\u003ch2\u003eEthics Approval and Informed Consent to Participate\u003c/h2\u003e\n\u003cp\u003eThis research was conducted after obtaining approval and recommendations from the Ethics Committee Review Board of Dr. Hasan Sadikin General Hospital \u0026ndash; Faculty of Medicine, Universitas Padjadjaran No. 622/UN6.KEP/EC/2023\u003c/p\u003e\n\u003ch2\u003eConsent for publication\u003c/h2\u003e\n\u003cp\u003eAll authors declare that approval of the version of the manuscript to be published has been obtained\u0026nbsp;\u003c/p\u003e\n\u003ch2\u003eAvailability of data and materials section\u003c/h2\u003e\n\u003cp\u003eThe authors declare that the personal data from any patients involved in this study will not be shared based on patients\u0026rsquo; confidentialities.\u003c/p\u003e\n\u003ch2\u003eCompeting Interest\u003c/h2\u003e\n\u003cp\u003eThe authors have declared that no competing interest exists.\u003c/p\u003e\n\u003ch2\u003eFunding\u003c/h2\u003e\n\u003cp\u003eNo funding.\u003c/p\u003e\n\u003ch2\u003eAuthors\u0026rsquo; contributions\u003c/h2\u003e\n\u003cp\u003eStudy conception and design: ABH\u003c/p\u003e\n\u003cp\u003eData collection: ABH, KIM\u003c/p\u003e\n\u003cp\u003eAnalysis and interpretation of result:\u0026nbsp;ABH, KIM, VDW\u003c/p\u003e\n\u003cp\u003eDraft manuscript preparation: ABH, KIM, VDW\u0026nbsp;\u003c/p\u003e\n\u003ch2\u003eAcknowledgements\u003c/h2\u003e\n\u003cp\u003eWe want to thank all the clinic and health center staff who have helped us greatly in data collection and patient recruitment.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eGlobal Cancer Observatory. Global: incidence, mortality and prevalence by cancer site [Internet]. 2022 [cited 2024 Feb 24]. Available from: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://gco.iarc.who.int/media/globocan/factsheets/cancers/23-cervix-uteri-fact-sheet.pdf\u003c/span\u003e\u003cspan address=\"https://gco.iarc.who.int/media/globocan/factsheets/cancers/23-cervix-uteri-fact-sheet.pdf\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWinarto H, Habiburrahman M, Dorothea M, Wijaya A, Nuryanto KH, Kusuma F, et al. Knowledge, attitudes, and practices among Indonesian urban communities regarding HPV infection, cervical cancer, and HPV vaccination. PLoS ONE. 2022;17:e0266139.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMitchell K, Saraiya M, Bhatt A. Increasing HPV Vaccination Rates Through National Provider Partnerships. J Womens Health. 2019;28:747\u0026ndash;51.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMarkowitz LE, Dunne EF, Saraiya M, Chesson HW, Curtis CR, Gee J, et al. Human Papillomavirus Vaccination Recommendations of the Advisory Committee on Immunization Practices (ACIP). MMWR Recommendations Rep. 2014;63:1\u0026ndash;30.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWaring J, Lindvall C, Umeton R. Automated machine learning: Review of the state-of-the-art and opportunities for healthcare. Artif Intell Med. 2020;104:101822.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKim S, Lee H, Lee S, Song JY, Lee JK, Lee NW. Role of Artificial Intelligence Interpretation of Colposcopic Images in Cervical Cancer Screening. Healthc (Switzerland). 2022;10:468.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHarsono AB, Susiarno H, Suardi D, Owen L, Fauzi H, Kireina J, et al. Cervical pre-cancerous lesion detection: development of smartphone-based VIA application using artificial intelligence. BMC Res Notes. 2022;15:356.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDavid J, Joshi V, Jebin Aaron D, Baghel P. A Comparative Analysis of Visual Inspection With Acetic Acid, Cervical Cytology, and Histopathology in the Screening and Early Detection of Premalignant and Malignant Lesions of the Cervix. Cureus. 2022;14:e29762.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWorld Health Organization. Framework for Monitoring the Implementation of the WHO Global Strategy to Accelerate the Elimination of Cervical Cancer as a Public Health Problem: including indicator metadata [Internet]. 2023 Feb. Available from: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://cdn.who.int/media/docs/default-source/ncds/ncd-surveillance/cxca/220121-bls21466-who-cp-accompany-doc_v01-web_.pdf?sfvrsn=2d2c\u003c/span\u003e\u003cspan address=\"https://cdn.who.int/media/docs/default-source/ncds/ncd-surveillance/cxca/220121-bls21466-who-cp-accompany-doc_v01-web_.pdf?sfvrsn=2d2c\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e811c_5\u0026amp;download=true.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eeClinicalMedicine. Global strategy to eliminate cervical cancer as a public health problem: are we on track? [Internet]. EClinicalMedicine. 2023 Jan. Available from: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.thelancet.com/action/showPdf?pii=S2589-5370%2823%2900019-6\u003c/span\u003e\u003cspan address=\"https://www.thelancet.com/action/showPdf?pii=S2589-5370%2823%2900019-6\" targettype=\"URL\" 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":true,"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":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"cervical cancer, cerviray, via test, early detection","lastPublishedDoi":"10.21203/rs.3.rs-3998751/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3998751/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eObjectives\u003c/h2\u003e \u003cp\u003eThis study investigates the performance of Cerviray A.I. and evaluation of Cerviray A.I. by an expert, an artificial intelligence (AI) technology for diagnosing cervical cancer, aiming to compare its sensitivity, specificity, positive predictive value (PPV), and area under the receiver operating characteristic curve (AUC ROC) with the Visual Inspection with Acetic Acid (VIA) test.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eThe study involved 44 patients from various health centers in West Java Province. Cerviray A.I., evaluation of Cerviray\u0026reg; A.I. by an expert, and VIA tests were administered to high-risk women of childbearing age. Preliminary results indicated that Cerviray A.I. had a sensitivity of 42.9%, specificity and PPV of 100%, and an AUC ROC of 71.4%. In comparison, the evaluation of Cerviray by an expert demonstrated a sensitivity of 71.4%, specificity of 97.3%, PPV of 83.3%, and AUC ROC of 84.4%. Evaluation of Cerviray A.I. by an expert outperformed Cerviray A.I. in AUC ROC.\u003c/p\u003e","manuscriptTitle":"Results Comparison of Cervical Cancer Early Detection Using Cerviray with VIA Test","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-03-11 19:03:47","doi":"10.21203/rs.3.rs-3998751/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"149ab392-1daf-4b15-987a-d8a6a8b0ab6b","owner":[],"postedDate":"March 11th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-04-22T05:46:29+00:00","versionOfRecord":[],"versionCreatedAt":"2024-03-11 19:03:47","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-3998751","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3998751","identity":"rs-3998751","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}