Matches in SemOpenAlex for { <https://semopenalex.org/work/W4221092010> ?p ?o ?g. }
- W4221092010 endingPage "e29967" @default.
- W4221092010 startingPage "e29967" @default.
- W4221092010 abstract "Background Artificial intelligence and digital health care have substantially advanced to improve and enhance medical diagnosis and treatment during the prolonged period of the COVID-19 global pandemic. In this study, we discuss the development of prediction models for the self-diagnosis of polycystic ovary syndrome (PCOS) using machine learning techniques. Objective We aim to develop self-diagnostic prediction models for PCOS in potential patients and clinical providers. For potential patients, the prediction is based only on noninvasive measures such as anthropomorphic measures, symptoms, age, and other lifestyle factors so that the proposed prediction tool can be conveniently used without any laboratory or ultrasound test results. For clinical providers who can access patients’ medical test results, prediction models using all predictor variables can be adopted to help health providers diagnose patients with PCOS. We compare both prediction models using various error metrics. We call the former model the patient model and the latter, the provider model throughout this paper. Methods In this retrospective study, a publicly available data set of 541 women’s health information collected from 10 different hospitals in Kerala, India, including PCOS status, was acquired and used for analysis. We adopted the CatBoost method for classification, K-fold cross-validation for estimating the performance of models, and SHAP (Shapley Additive Explanations) values to explain the importance of each variable. In our subgroup study, we used k-means clustering and Principal Component Analysis to split the data set into 2 distinct BMI subgroups and compared the prediction results as well as the feature importance between the 2 subgroups. Results We achieved 81% to 82.5% prediction accuracy of PCOS status without any invasive measures in the patient models and achieved 87.5% to 90.1% prediction accuracy using both noninvasive and invasive predictor variables in the provider models. Among noninvasive measures, variables including acanthosis nigricans, acne, hirsutism, irregular menstrual cycle, length of menstrual cycle, weight gain, fast food consumption, and age were more important in the models. In medical test results, the numbers of follicles in the right and left ovaries and anti-Müllerian hormone were ranked highly in feature importance. We also reported more detailed results in a subgroup study. Conclusions The proposed prediction models are ultimately expected to serve as a convenient digital platform with which users can acquire pre- or self-diagnosis and counsel for the risk of PCOS, with or without obtaining medical test results. It will enable women to conveniently access the platform at home without delay before they seek further medical care. Clinical providers can also use the proposed prediction tool to help diagnose PCOS in women." @default.
- W4221092010 created "2022-04-03" @default.
- W4221092010 creator A5045367124 @default.
- W4221092010 creator A5083564817 @default.
- W4221092010 creator A5091853931 @default.
- W4221092010 date "2022-03-15" @default.
- W4221092010 modified "2023-10-01" @default.
- W4221092010 title "Machine-Aided Self-diagnostic Prediction Models for Polycystic Ovary Syndrome: Observational Study" @default.
- W4221092010 cites W166615144 @default.
- W4221092010 cites W1953204053 @default.
- W4221092010 cites W1969211441 @default.
- W4221092010 cites W1979143098 @default.
- W4221092010 cites W1981665764 @default.
- W4221092010 cites W1982674203 @default.
- W4221092010 cites W2008089585 @default.
- W4221092010 cites W2034205108 @default.
- W4221092010 cites W2041423220 @default.
- W4221092010 cites W2050593976 @default.
- W4221092010 cites W2097142926 @default.
- W4221092010 cites W2108380448 @default.
- W4221092010 cites W2154859309 @default.
- W4221092010 cites W2165316974 @default.
- W4221092010 cites W2171138278 @default.
- W4221092010 cites W2295124130 @default.
- W4221092010 cites W2487770199 @default.
- W4221092010 cites W2558741448 @default.
- W4221092010 cites W2576830570 @default.
- W4221092010 cites W2593816261 @default.
- W4221092010 cites W2766966628 @default.
- W4221092010 cites W2793887346 @default.
- W4221092010 cites W2802772536 @default.
- W4221092010 cites W2808636532 @default.
- W4221092010 cites W2884536266 @default.
- W4221092010 cites W2894883890 @default.
- W4221092010 cites W2900701301 @default.
- W4221092010 cites W2923389169 @default.
- W4221092010 cites W2951209146 @default.
- W4221092010 cites W2979324155 @default.
- W4221092010 cites W3012290708 @default.
- W4221092010 cites W3013547516 @default.
- W4221092010 cites W3036813420 @default.
- W4221092010 cites W3113209434 @default.
- W4221092010 cites W3146996380 @default.
- W4221092010 cites W3163936961 @default.
- W4221092010 cites W3164291146 @default.
- W4221092010 cites W4248393160 @default.
- W4221092010 cites W4256605237 @default.
- W4221092010 doi "https://doi.org/10.2196/29967" @default.
- W4221092010 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35289757" @default.
- W4221092010 hasPublicationYear "2022" @default.
- W4221092010 type Work @default.
- W4221092010 citedByCount "8" @default.
- W4221092010 countsByYear W42210920102022 @default.
- W4221092010 countsByYear W42210920102023 @default.
- W4221092010 crossrefType "journal-article" @default.
- W4221092010 hasAuthorship W4221092010A5045367124 @default.
- W4221092010 hasAuthorship W4221092010A5083564817 @default.
- W4221092010 hasAuthorship W4221092010A5091853931 @default.
- W4221092010 hasBestOaLocation W42210920101 @default.
- W4221092010 hasConcept C119857082 @default.
- W4221092010 hasConcept C124101348 @default.
- W4221092010 hasConcept C126322002 @default.
- W4221092010 hasConcept C138885662 @default.
- W4221092010 hasConcept C154945302 @default.
- W4221092010 hasConcept C23131810 @default.
- W4221092010 hasConcept C2776401178 @default.
- W4221092010 hasConcept C2777391703 @default.
- W4221092010 hasConcept C3018442814 @default.
- W4221092010 hasConcept C41008148 @default.
- W4221092010 hasConcept C41895202 @default.
- W4221092010 hasConcept C45804977 @default.
- W4221092010 hasConcept C511355011 @default.
- W4221092010 hasConcept C58489278 @default.
- W4221092010 hasConcept C71924100 @default.
- W4221092010 hasConceptScore W4221092010C119857082 @default.
- W4221092010 hasConceptScore W4221092010C124101348 @default.
- W4221092010 hasConceptScore W4221092010C126322002 @default.
- W4221092010 hasConceptScore W4221092010C138885662 @default.
- W4221092010 hasConceptScore W4221092010C154945302 @default.
- W4221092010 hasConceptScore W4221092010C23131810 @default.
- W4221092010 hasConceptScore W4221092010C2776401178 @default.
- W4221092010 hasConceptScore W4221092010C2777391703 @default.
- W4221092010 hasConceptScore W4221092010C3018442814 @default.
- W4221092010 hasConceptScore W4221092010C41008148 @default.
- W4221092010 hasConceptScore W4221092010C41895202 @default.
- W4221092010 hasConceptScore W4221092010C45804977 @default.
- W4221092010 hasConceptScore W4221092010C511355011 @default.
- W4221092010 hasConceptScore W4221092010C58489278 @default.
- W4221092010 hasConceptScore W4221092010C71924100 @default.
- W4221092010 hasIssue "3" @default.
- W4221092010 hasLocation W42210920101 @default.
- W4221092010 hasLocation W42210920102 @default.
- W4221092010 hasLocation W42210920103 @default.
- W4221092010 hasOpenAccess W4221092010 @default.
- W4221092010 hasPrimaryLocation W42210920101 @default.
- W4221092010 hasRelatedWork W2748952813 @default.
- W4221092010 hasRelatedWork W2765980456 @default.
- W4221092010 hasRelatedWork W2899084033 @default.