A Decision Tree-Driven IoT systems for improved pre-natal diagnostic accuracy DOI Creative Commons
Xuewen Yang, Ling Liu, Yan Wang

и другие.

BMC Medical Informatics and Decision Making, Год журнала: 2024, Номер 24(1)

Опубликована: Дек. 5, 2024

Prenatal diagnostics are vital for the woman as well her unborn baby. The help in early identification of possibility complication and initial measures that to ameliorate mother fetus health status taken. Over year's various techniques have been employed diagnosing genetic disorders before birth lack effectiveness terms cost, time, places access ultra-modern facilities. To overcome these problems, this paper puts forward a diagnostic model integrates Internet Things innovation with Machine Learning approach which is Decision Tree Algorithms. First, it implies application IOT devices collection information like heart rate, blood pressure, glucose levels, fetal movement. data structured form dataset transmitted Big Data storage warehousing processing. Secondly, DTA analyze look patterns possibilities future complications. operates divides into subsets considering specific features formulates tree-like decisions. At every node, algorithm chooses attribute has highest gain, partition different classes. This process goes on until reaches decision node through which, can decide probable problems from input data. increase reliability developed study fine-tunes by using large database pre-natal records. system capable collecting real-time flagging needs attention case any abnormality professional. above methodology was tested 1000-record records where proposal achieved 95% potential against 85% classical statistical analysis. Furthermore, scaled down number false positive cases 20 percent negatives 15 thus efficacy system.

Язык: Английский

NLP-Driven Integration of Electrophysiology and Traditional Chinese Medicine for Enhanced Diagnostics and Management of Postpartum Pain DOI Creative Commons
Yaning Wang

SLAS TECHNOLOGY, Год журнала: 2025, Номер unknown, С. 100267 - 100267

Опубликована: Март 1, 2025

Postpartum pain encompasses a range of physical and emotional discomforts, often influenced by hormonal changes, recovery, individual psychological states. The complex interactions between the variables can make it difficult for traditional diagnostic techniques to fully capture, creating inadequacies inefficient management techniques. aims develop comprehensive framework postpartum integrating Natural Language Processing (NLP), electrophysiological data, Traditional Chinese Medicine (TCM) principles. seeks enhance accuracy diagnosis, uncover meaningful correlations TCM diagnoses physiological markers, optimize personalized treatment strategies. focuses on analyzing textual data from patient-reported symptoms, medical records, diagnosis notes. Data pre-processing involves text cleaning tokenization, followed feature extraction using Term Frequency-Inverse Document Frequency (TF-IDF) capture patterns. For diagnostics management, Refined Coyote Optimized Deep Recurrent Neural Network (RCO-DRNN) is employed analyze predict profiles, combining insights with markers. results highlight effectiveness RCO-DRNN in accurately diagnosing types offering holistic This approach represents significant advancement data-driven methodologies practices, providing more management. continuously beats other models after thorough evaluation metrics like MSE, MAE, R2, obtaining lowest MSE (0.005), smallest MAE (0.04), highest R2 (0.98).

Язык: Английский

Процитировано

0
Development and validation of a predictive model for depression in patients with advanced stage of cardiovascular-kidney-metabolic syndrome DOI
Bowen Zha,

Angshu Cai,

Hao Yu

и другие.

Journal of Affective Disorders, Год журнала: 2025, Номер unknown

Опубликована: Апрель 1, 2025

Язык: Английский

Процитировано

0
Predictive Analysis of Postpartum Depression Using Machine Learning DOI Open Access
Hyun Kyoung Kim

Healthcare, Год журнала: 2025, Номер 13(8), С. 897 - 897

Опубликована: Апрель 14, 2025

Background: Maternal postpartum depression (PPD) is a major psychological problem affecting mothers, newborns, and their families after childbirth. This study investigated the factors influencing maternal PPD developed predictive model using machine learning. Methods/Design: In this study, we applied learning techniques to identify significant predictors of develop for classifying individuals at risk. Data from 2570 subjects were analyzed Korean Early Childhood Education Care Panel (K-ECEC-P) dataset as January 2025, utilizing Python version 3.12.8. Results: We compared performance decision tree classifier, random forest AdaBoost logistic regression metrics such precision, accuracy, recall, F1-score, area under curve. The was selected best model. Among 13 features analyzed, conflict with partner, stress, value children emerged PPD. Discussion: Conflict partner stress levels strongest predictors. Higher associated an increased likelihood PPD, whereas higher reduced status environmental should be managed carefully during period.

Язык: Английский

Процитировано

0
Sociodemographic bias in clinical machine learning models: A scoping review of algorithmic bias instances and mechanisms DOI Creative Commons
Michael Colacci, Yu Qing Huang, Gemma Postill

и другие.

Journal of Clinical Epidemiology, Год журнала: 2024, Номер 178, С. 111606 - 111606

Опубликована: Ноя. 10, 2024

Язык: Английский

Процитировано

0
A Decision Tree-Driven IoT systems for improved pre-natal diagnostic accuracy DOI Creative Commons
Xuewen Yang, Ling Liu, Yan Wang

и другие.

BMC Medical Informatics and Decision Making, Год журнала: 2024, Номер 24(1)

Опубликована: Дек. 5, 2024

Prenatal diagnostics are vital for the woman as well her unborn baby. The help in early identification of possibility complication and initial measures that to ameliorate mother fetus health status taken. Over year's various techniques have been employed diagnosing genetic disorders before birth lack effectiveness terms cost, time, places access ultra-modern facilities. To overcome these problems, this paper puts forward a diagnostic model integrates Internet Things innovation with Machine Learning approach which is Decision Tree Algorithms. First, it implies application IOT devices collection information like heart rate, blood pressure, glucose levels, fetal movement. data structured form dataset transmitted Big Data storage warehousing processing. Secondly, DTA analyze look patterns possibilities future complications. operates divides into subsets considering specific features formulates tree-like decisions. At every node, algorithm chooses attribute has highest gain, partition different classes. This process goes on until reaches decision node through which, can decide probable problems from input data. increase reliability developed study fine-tunes by using large database pre-natal records. system capable collecting real-time flagging needs attention case any abnormality professional. above methodology was tested 1000-record records where proposal achieved 95% potential against 85% classical statistical analysis. Furthermore, scaled down number false positive cases 20 percent negatives 15 thus efficacy system.

Язык: Английский

Процитировано

0