Comparison of Multivariable Logistic Regression and Other Machine Learning Algorithms for Prognostic Prediction Studies in Pregnancy Care: Systematic Review and Meta-Analysis

Predictive model for assessing malnutrition in elderly hospitalized cancer patients: A machine learning approach

BACKGROUND

Malnutrition is prevalent among elderly cancer patients. This study aims to develop a predictive model for malnutrition in hospitalized elderly cancer patients.

METHODS

Data from January 2022 to January 2023 on cancer patients aged 60+ were collected, involving 22 variables. Key variables were identified using the LASSO (Least Absolute Shrinkage and Selection Operator) method, and nine machine learning models were tested. SHAP was used to interpret the XGBoost model. Malnutrition prevalence was assessed.

RESULTS

Among 450 participants, 46.4 % were malnourished. Key predictors identified were ADL (Activities of Daily Living), ALB (Albumin), BMI (Body Mass Index) and age. XGBoost had the highest AUC of 0.945, accuracy of 0.872, and sensitivity of 0.968. Higher ADL and age increased malnutrition risk, while lower ALB and BMI reduced it.

CONCLUSIONS

The XGBoost model is highly effective in detecting malnutrition in elderly cancer patients, enabling early and rapid nutritional assessments.

Computational Approaches for Connecting Maternal Stress to Preterm Birth

Multiple studies have hinted at a complex connection between maternal stress and preterm birth (PTB). This article describes the potential of computational methods to provide new insights into this relationship. For this, we outline existing approaches for stress assessments and various data modalities available for profiling stress responses, and review studies that sought either to establish a connection between stress and PTB or to predict PTB based on stress-related factors. Finally, we summarize the challenges of computational methods, highlighting potential future research directions within this field.

Machine Learning Methods Based on CT Features Differentiate G1/G2 From G3 Pancreatic Neuroendocrine Tumors

RATIONALE AND OBJECTIVES

To identify CT features for distinguishing grade 1 (G1)/grade 2 (G2) from grade 3 (G3) pancreatic neuroendocrine tumors (PNETs) using different machine learning (ML) methods.

MATERIALS AND METHODS

A total of 147 patients with 155 lesions confirmed by pathology were retrospectively included. Clinical-demographic and radiological CT features was collected. The entire cohort was separated into training and validation groups at a 7:3 ratio. Least absolute shrinkage and selection operator (LASSO) algorithm and principal component analysis (PCA) were used to select features. Three ML methods, namely logistic regression (LR), support vector machine (SVM), and K-nearest neighbor (KNN) were used to build a differential model. Receiver operating characteristic (ROC) curves and precision-recall curves for each ML method were generated. The area under the curve (AUC), accuracy rate, sensitivity, and specificity were calculated.

RESULTS

G3 PNETs were more likely to present with invasive behaviors and lower enhancement than G1/G2 PNETs. The LR classifier yielded the highest AUC of 0.964 (95% confidence interval [CI]: 0.930, 0.972), with 95.4% accuracy rate, 95.7% sensitivity, and 92.9% specificity, followed by SVM (AUC: 0.957) and KNN (AUC: 0.893) in the training group. In the validation group, the SVM classier reached the highest AUC of 0.952 (95% CI: 0.860, 0.981), with 91.5% accuracy rate, 97.3% sensitivity, and 70% specificity, followed by LR (AUC: 0.949) and KNN (AUC: 0.923).

CONCLUSIONS

The LR and SVM classifiers had the best performance in the training group and validation group, respectively. ML method could be helpful in differentiating between G1/G2 and G3 PNETs.

Identifying predictors of the tooth loss phenotype in a large periodontitis patient cohort using a machine learning approach

OBJECTIVES

This study aimed to identify predictors associated with the tooth loss phenotype in a large periodontitis patient cohort in the university setting.

METHODS

Information on periodontitis patients and nineteen factors identified at the initial visit was extracted from electronic health records. The primary outcome is tooth loss phenotype (presence or absence of tooth loss). Prediction models were built on significant factors (single or combinatory) selected by the RuleFit algorithm, and these factors were further adopted by regression models. Model performance was evaluated by Area Under the Receiver Operating Characteristic Curve (AUROC) and Area Under the Precision-Recall Curve (AUPRC). Associations between predictors and the tooth loss phenotype were also evaluated by classical statistical approaches to validate the performance of machine learning models.

RESULTS

In total, 7840 patients were included. The machine learning model predicting the tooth loss phenotype achieved AUROC of 0.71 and AUPRC of 0.66. Age, periodontal diagnosis, number of missing teeth at baseline, furcation involvement, and tooth mobility were associated with the tooth loss phenotype in both machine learning and classical statistical models.

CONCLUSIONS

The rule-based machine learning approach improves model explainability compared to classical statistical methods. However, the model's generalizability needs to be further validated by external datasets.

CLINICAL SIGNIFICANCE

Predictors identified by the current machine learning approach using the RuleFit algorithm had clinically relevant thresholds in predicting the tooth loss phenotype in a large and diverse periodontitis patient cohort. The results of this study will assist clinicians in performing risk assessment for periodontitis at the initial visit.

The relationship between heavy metals and metabolic syndrome using machine learning

Background

Exposure to high levels of heavy metals has been widely recognized as an important risk factor for metabolic syndrome (MetS). The main purpose of this study is to assess the associations between the level of heavy metal exposure and Mets using machine learning (ML) method.

Methods

The data used in this study are from the national health and nutrition examination survey 2003-2018. According to the demographic information and heavy metal exposure level of participants, a total of 22 variables were included. Lasso was used to screen out the key variables, and 9 commonly used ML models were selected to establish the associations with the 5-fold cross validation method. Finally, we choose the SHapley Additive exPlanations (SHAP) method to explain the prediction results of Adaboost model.

Results

11,667 eligible individuals were randomly divided into two groups to train and verify the prediction model. Through lasso, characteristic variables were selected from 24 variables as predictors. The AUC (area under curve) of the models selected in this study were all greater than 0.7, and AdaBoost was the best model. The AUC value of AdaBoost was 0.807, the accuracy was 0.720, and the sensitivity was 0.792. It is noteworthy that higher levels of cadmium, body mass index, cesium, being female, and increasing age were associated with an increased probability of MetS. Conversely, lower levels of cobalt and molybdenum were linked to a decrease in the estimated probability of MetS.

Conclusion

Our study highlights the AdaBoost model proved to be highly effective, precise, and resilient in detecting a correlation between exposure to heavy metals and MetS. Through the use of interpretable methods, we identified cadmium, molybdenum, cobalt, cesium, uranium, and barium as prominent contributors within the predictive model.

Application of machine learning for lung cancer survival prognostication-A systematic review and meta-analysis

Introduction

Machine learning (ML) techniques have gained increasing attention in the field of healthcare, including predicting outcomes in patients with lung cancer. ML has the potential to enhance prognostication in lung cancer patients and improve clinical decision-making. In this systematic review and meta-analysis, we aimed to evaluate the performance of ML models compared to logistic regression (LR) models in predicting overall survival in patients with lung cancer.

Methods

We followed the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) statement. A comprehensive search was conducted in Medline, Embase, and Cochrane databases using a predefined search query. Two independent reviewers screened abstracts and conflicts were resolved by a third reviewer. Inclusion and exclusion criteria were applied to select eligible studies. Risk of bias assessment was performed using predefined criteria. Data extraction was conducted using the Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies (CHARMS) checklist. Meta-analytic analysis was performed to compare the discriminative ability of ML and LR models.

Results

The literature search resulted in 3,635 studies, and 12 studies with a total of 211,068 patients were included in the analysis. Six studies reported confidence intervals and were included in the meta-analysis. The performance of ML models varied across studies, with C-statistics ranging from 0.60 to 0.85. The pooled analysis showed that ML models had higher discriminative ability compared to LR models, with a weighted average C-statistic of 0.78 for ML models compared to 0.70 for LR models.

Conclusion

Machine learning models show promise in predicting overall survival in patients with lung cancer, with superior discriminative ability compared to logistic regression models. However, further validation and standardization of ML models are needed before their widespread implementation in clinical practice. Future research should focus on addressing the limitations of the current literature, such as potential bias and heterogeneity among studies, to improve the accuracy and generalizability of ML models for predicting outcomes in patients with lung cancer. Further research and development of ML models in this field may lead to improved patient outcomes and personalized treatment strategies.

Investigation of statistical methods used in prognostic prediction models for obstetric care: A 10 year-span cross-sectional study

INTRODUCTION

Obstetric care is a highly active area in the development and application of prognostic prediction models. The development and validation of these models often require the utilization of advanced statistical techniques. However, failure to adhere to rigorous methodological standards could greatly undermine the reliability and trustworthiness of the resultant models. Consequently, the aim of our study was to examine the current statistical practices employed in obstetric care and offer recommendations to enhance the utilization of statistical methods in the development of prognostic prediction models.

MATERIAL AND METHODS

We conducted a cross-sectional survey using a sample of studies developing or validating prognostic prediction models for obstetric care published in a 10-year span (2011-2020). A structured questionnaire was developed to investigate the statistical issues in five domains, including model derivation (predictor selection and algorithm development), model validation (internal and external), model performance, model presentation, and risk threshold setting. On the ground of survey results and existing guidelines, a list of recommendations for statistical methods in prognostic models was developed.

RESULTS

A total of 112 eligible studies were included, with 107 reporting model development and five exclusively reporting external validation. During model development, 58.9% of the studies did not include any form of validation. Of these, 46.4% used stepwise regression in a crude manner for predictor selection, while two-thirds made decisions on retaining or dropping candidate predictors solely based on p-values. Additionally, 26.2% transformed continuous predictors into categorical variables, and 80.4% did not consider nonlinear relationships between predictors and outcomes. Surprisingly, 94.4% of the studies did not examine the correlation between predictors. Moreover, 47.1% of the studies did not compare population characteristics between the development and external validation datasets, and only one-fifth evaluated both discrimination and calibration. Furthermore, 53.6% of the studies did not clearly present the model, and less than half established a risk threshold to define risk categories. In light of these findings, 10 recommendations were formulated to promote the appropriate use of statistical methods.

CONCLUSIONS

The use of statistical methods is not yet optimal. Ten recommendations were offered to assist the statistical methods of prognostic prediction models in obstetric care.

A Machine Learning-Driven Virtual Biopsy System For Kidney Transplant Patients

In kidney transplantation, day-zero biopsies are used to assess organ quality and discriminate between donor-inherited lesions and those acquired post-transplantation. However, many centers do not perform such biopsies since they are invasive, costly and may delay the transplant procedure. We aim to generate a non-invasive virtual biopsy system using routinely collected donor parameters. Using 14,032 day-zero kidney biopsies from 17 international centers, we develop a virtual biopsy system. 11 basic donor parameters are used to predict four Banff kidney lesions: arteriosclerosis, arteriolar hyalinosis, interstitial fibrosis and tubular atrophy, and the percentage of renal sclerotic glomeruli. Six machine learning models are aggregated into an ensemble model. The virtual biopsy system shows good performance in the internal and external validation sets. We confirm the generalizability of the system in various scenarios. This system could assist physicians in assessing organ quality, optimizing allograft allocation together with discriminating between donor derived and acquired lesions post-transplantation.

Clinical nursing value of predictive nursing in reducing complications of pregnant women undergoing short-term massive blood transfusion during cesarean section

BACKGROUND

Cesarean hemorrhage is one of the serious complications, and short-term massive blood transfusion can easily cause postoperative infection and physical stress response. However, predictive nursing intervention has important clinical significance for it.

AIM

To explore the effect of predictive nursing intervention on the stress response and complications of women undergoing short-term mass blood transfusion during cesarean section (CS).

METHODS

A clinical medical record of 100 pregnant women undergoing rapid mass blood transfusion during sections from June 2019 to June 2021. According to the different nursing methods, patients divided into control group (n = 50) and observation group (n = 50). Among them, the control group implemented routine nursing, and the observation group implemented predictive nursing intervention based on the control group. Moreover, compared the differences in stress response, complications, and pain scores before and after the nursing of pregnant women undergoing rapid mass blood transfusion during CS.

RESULTS

The anxiety and depression scores of pregnant women in the two groups were significantly improved after nursing, and the psychological stress response of the observation group was significantly lower than that of the control group (P < 0.05). The heart rate and mean arterial pressure (MAP) of the observation group during delivery were lower than those of the control group, and the MAP at the end of delivery was lower than that of the control group (P < 0.05). Moreover, different pain scores improved significantly in both groups, with the observation group considerably less than the control group (P < 0.05). After nursing, complications such as skin rash, urinary retention, chills, diarrhea, and anaphylactic shock in the observation group were 18%, which significantly higher than in the control group (4%) (P < 0.05).

CONCLUSION

Predictive nursing intervention can effectively relieve the pain, reduce the incidence of complications, improve mood and stress response, and serve as a reference value for the nursing of women undergoing rapid mass transfusion during CS.

Application of machine learning in predicting survival outcomes involving real-world data: a scoping review

BACKGROUND

Despite the interest in machine learning (ML) algorithms for analyzing real-world data (RWD) in healthcare, the use of ML in predicting time-to-event data, a common scenario in clinical practice, is less explored. ML models are capable of algorithmically learning from large, complex datasets and can offer advantages in predicting time-to-event data. We reviewed the recent applications of ML for survival analysis using RWD in healthcare.

METHODS

PUBMED and EMBASE were searched from database inception through March 2023 to identify peer-reviewed English-language studies of ML models for predicting time-to-event outcomes using the RWD. Two reviewers extracted information on the data source, patient population, survival outcome, ML algorithms, and the Area Under the Curve (AUC).

RESULTS

Of 257 citations, 28 publications were included. Random survival forests (N = 16, 57%) and neural networks (N = 11, 39%) were the most popular ML algorithms. There was variability across AUC for these ML models (median 0.789, range 0.6-0.950). ML algorithms were predominately considered for predicting overall survival in oncology (N = 12, 43%). ML survival models were often used to predict disease prognosis or clinical events (N = 27, 96%) in the oncology, while less were used for treatment outcomes (N = 1, 4%).

CONCLUSIONS

The ML algorithms, random survival forests and neural networks, are mainly used for RWD to predict survival outcomes such as disease prognosis or clinical events in the oncology. This review shows that more opportunities remain to apply these ML algorithms to inform treatment decision-making in clinical practice. More methodological work is also needed to ensure the utility and applicability of ML models in survival outcomes.

Comparison of machine learning and conventional logistic regression-based prediction models for gestational diabetes in an ethnically diverse population; the Monash GDM Machine learning model

BACKGROUND

Early identification of pregnant women at high risk of developing gestational diabetes (GDM) is desirable as effective lifestyle interventions are available to prevent GDM and to reduce associated adverse outcomes. Personalised probability of developing GDM during pregnancy can be determined using a risk prediction model. These models extend from traditional statistics to machine learning methods; however, accuracy remains sub-optimal.

OBJECTIVE

We aimed to compare multiple machine learning algorithms to develop GDM risk prediction models, then to determine the optimal model for predicting GDM.

METHODS

A supervised machine learning predictive analysis was performed on data from routine antenatal care at a large health service network from January 2016 to June 2021. Predictor set 1 were sourced from the existing, internationally validated Monash GDM model: GDM history, body mass index, ethnicity, age, family history of diabetes, and past poor obstetric history. New models with different predictors were developed, considering statistical principles with inclusion of more robust continuous and derivative variables. A randomly selected 80% dataset was used for model development, with 20% for validation. Performance measures, including calibration and discrimination metrics, were assessed. Decision curve analysis was performed.

RESULTS

Upon internal validation, the machine learning and logistic regression model's area under the curve (AUC) ranged from 71% to 93% across the different algorithms, with the best being the CatBoost Classifier (CBC). Based on the default cut-off point of 0.32, the performance of CBC on predictor set 4 was: Accuracy (85%), Precision (90%), Recall (78%), F1-score (84%), Sensitivity (81%), Specificity (90%), positive predictive value (92%), negative predictive value (78%), and Brier Score (0.39).

CONCLUSIONS

In this study, machine learning approaches achieved the best predictive performance over traditional statistical methods, increasing from 75 to 93%. The CatBoost classifier method achieved the best with the model including continuous variables.

Differentiation Between Phyllodes Tumors and Fibroadenomas of Breast Using Mammography-based Machine Learning Methods: A Preliminary Study

OBJECTIVE

To investigate the diagnostic performance of a mammography-based radiomics model for distinguishing phyllodes tumors (PTs) from fibroadenomas (FAs) of the breast.

MATERIALS AND METHODS

A total of 156 patients were retrospectively included (75 with PTs, 81 with FAs) and divided into training and validation groups at a ratio of 7:3. Radiomics features were extracted from craniocaudal and mediolateral oblique images. The least absolute shrinkage and selection operator (LASSO) algorithm and principal component analysis (PCA) were performed to select features. Three machine learning classifiers, including logistic regression (LR), K-nearest neighbor classifier (KNN) and support vector machine (SVM), were implemented in the radiomics model, imaging model and combined model. Receiver operating characteristic curves, area under the curve (AUC), sensitivity and specificity were computed.

RESULTS

Among 1084 features, the LASSO algorithm selected 17 features, and PCA further selected 6 features. Three machine learning classifiers yielded the same AUC of 0.935 in the validation group for the radiomics model. In the imaging model, KNN yielded the highest accuracy rate of 89.4% and AUC of 0.947 in the validation set. For the combined model, the SVM classifier reached the highest AUC of 0.918 with an accuracy rate of 86.2%, sensitivity of 83.9%, and specificity of 89.4% in the training group. In the validation group, LR yielded the highest AUC of 0.973. The combined model had a relatively higher AUC than the radiomics model or imaging model, especially in the validation group.

CONCLUSIONS

Mammography-based radiomics features demonstrate good diagnostic performance for discriminating PTs from FAs.

A systematic review of clinical health conditions predicted by machine learning diagnostic and prognostic models trained or validated using real-world primary health care data

With the advances in technology and data science, machine learning (ML) is being rapidly adopted by the health care sector. However, there is a lack of literature addressing the health conditions targeted by the ML prediction models within primary health care (PHC) to date. To fill this gap in knowledge, we conducted a systematic review following the PRISMA guidelines to identify health conditions targeted by ML in PHC. We searched the Cochrane Library, Web of Science, PubMed, Elsevier, BioRxiv, Association of Computing Machinery (ACM), and IEEE Xplore databases for studies published from January 1990 to January 2022. We included primary studies addressing ML diagnostic or prognostic predictive models that were supplied completely or partially by real-world PHC data. Studies selection, data extraction, and risk of bias assessment using the prediction model study risk of bias assessment tool were performed by two investigators. Health conditions were categorized according to international classification of diseases (ICD-10). Extracted data were analyzed quantitatively. We identified 106 studies investigating 42 health conditions. These studies included 207 ML prediction models supplied by the PHC data of 24.2 million participants from 19 countries. We found that 92.4% of the studies were retrospective and 77.3% of the studies reported diagnostic predictive ML models. A majority (76.4%) of all the studies were for models' development without conducting external validation. Risk of bias assessment revealed that 90.8% of the studies were of high or unclear risk of bias. The most frequently reported health conditions were diabetes mellitus (19.8%) and Alzheimer's disease (11.3%). Our study provides a summary on the presently available ML prediction models within PHC. We draw the attention of digital health policy makers, ML models developer, and health care professionals for more future interdisciplinary research collaboration in this regard.

Applications, functions, and accuracy of artificial intelligence in restorative dentistry: A literature review

OBJECTIVE

The applications of artificial intelligence (AI) are increasing in restorative dentistry; however, the AI performance is unclear for dental professionals. The purpose of this narrative review was to evaluate the applications, functions, and accuracy of AI in diverse aspects of restorative dentistry including caries detection, tooth preparation margin detection, tooth restoration design, metal structure casting, dental restoration/implant detection, removable partial denture design, and tooth shade determination.

OVERVIEW

An electronic search was performed on Medline/PubMed, Embase, Web of Science, Cochrane, Scopus, and Google Scholar databases. English-language articles, published from January 1, 2000, to March 1, 2022, relevant to the aforementioned aspects were selected using the key terms of artificial intelligence, machine learning, deep learning, artificial neural networks, convolutional neural networks, clustering, soft computing, automated planning, computational learning, computer vision, and automated reasoning as inclusion criteria. A manual search was also performed. Therefore, 157 articles were included, reviewed, and discussed.

CONCLUSIONS

Based on the current literature, the AI models have shown promising performance in the mentioned aspects when being compared with traditional approaches in terms of accuracy; however, as these models are still in development, more studies are required to validate their accuracy and apply them to routine clinical practice.

CLINICAL SIGNIFICANCE

AI with its specific functions has shown successful applications with acceptable accuracy in diverse aspects of restorative dentistry. The understanding of these functions may lead to novel applications with optimal accuracy for AI in restorative dentistry.

Challenges and Opportunities for Data Science in Women's Health

The intersection of women's health and data science is a field of research that has historically trailed other fields, but more recently it has gained momentum. This growth is being driven not only by new investigators who are moving into this area but also by the significant opportunities that have emerged in new methodologies, resources, and technologies in data science. Here, we describe some of the resources and methods being used by women's health researchers today to meet challenges in biomedical data science. We also describe the opportunities and limitations of applying these approaches to advance women's health outcomes and the future of the field, with emphasis on repurposing existing methodologies for women's health.

Systematic metareview of prediction studies demonstrates stable trends in bias and low PROBAST inter-rater agreement

OBJECTIVES

To (1) explore trends of risk of bias (ROB) in prediction research over time following key methodological publications, using the Prediction model Risk Of Bias ASsessment Tool (PROBAST) and (2) assess the inter-rater agreement of the PROBAST.

STUDY DESIGN AND SETTING

PubMed and Web of Science were searched for reviews with extractable PROBAST scores on domain and signaling question (SQ) level. ROB trends were visually correlated with yearly citations of key publications. Inter-rater agreement was assessed using Cohen's Kappa.

RESULTS

One hundred and thirty nine systematic reviews were included, of which 85 reviews (containing 2,477 single studies) on domain level and 54 reviews (containing 2,458 single studies) on SQ level. High ROB was prevalent, especially in the Analysis domain, and overall trends of ROB remained relatively stable over time. The inter-rater agreement was low, both on domain (Kappa 0.04-0.26) and SQ level (Kappa -0.14 to 0.49).

CONCLUSION

Prediction model studies are at high ROB and time trends in ROB as assessed with the PROBAST remain relatively stable. These results might be explained by key publications having no influence on ROB or recency of key publications. Moreover, the trend may suffer from the low inter-rater agreement and ceiling effect of the PROBAST. The inter-rater agreement could potentially be improved by altering the PROBAST or providing training on how to apply the PROBAST.

Machine learning applied in maternal and fetal health: a narrative review focused on pregnancy diseases and complications

Introduction

Machine learning (ML) corresponds to a wide variety of methods that use mathematics, statistics and computational science to learn from multiple variables simultaneously. By means of pattern recognition, ML methods are able to find hidden correlations and accomplish accurate predictions regarding different conditions. ML has been successfully used to solve varied problems in different areas of science, such as psychology, economics, biology and chemistry. Therefore, we wondered how far it has penetrated into the field of obstetrics and gynecology.

Aim

To describe the state of art regarding the use of ML in the context of pregnancy diseases and complications.

Methodology

Publications were searched in PubMed, Web of Science and Google Scholar. Seven subjects of interest were considered: gestational diabetes mellitus, preeclampsia, perinatal death, spontaneous abortion, preterm birth, cesarean section, and fetal malformations.

Current state

ML has been widely applied in all the included subjects. Its uses are varied, the most common being the prediction of perinatal disorders. Other ML applications include (but are not restricted to) biomarker discovery, risk estimation, correlation assessment, pharmacological treatment prediction, drug screening, data acquisition and data extraction. Most of the reviewed articles were published in the last five years. The most employed ML methods in the field are non-linear. Except for logistic regression, linear methods are rarely used.

Future challenges

To improve data recording, storage and update in medical and research settings from different realities. To develop more accurate and understandable ML models using data from cutting-edge instruments. To carry out validation and impact analysis studies of currently existing high-accuracy ML models.

Conclusion

The use of ML in pregnancy diseases and complications is quite recent, and has increased over the last few years. The applications are varied and point not only to the diagnosis, but also to the management, treatment, and pathophysiological understanding of perinatal alterations. Facing the challenges that come with working with different types of data, the handling of increasingly large amounts of information, the development of emerging technologies, and the need of translational studies, it is expected that the use of ML continue growing in the field of obstetrics and gynecology.

Human-guided deep learning with ante-hoc explainability by convolutional network from non-image data for pregnancy prognostication

BACKGROUND AND OBJECTIVE

Deep learning is applied in medicine mostly due to its state-of-the-art performance for diagnostic imaging. Supervisory authorities also require the model to be explainable, but most explain the model after development (post hoc) instead of incorporating explanation into the design (ante hoc). This study aimed to demonstrate a human-guided deep learning with ante-hoc explainability by convolutional network from non-image data to develop, validate, and deploy a prognostic prediction model for PROM and an estimator of time of delivery using a nationwide health insurance database.

METHODS

To guide modeling, we constructed and verified association diagrams respectively from literatures and electronic health records. Non-image data were transformed into meaningful images utilizing predictor-to-predictor similarities, harnessing the power of convolutional neural network mostly used for diagnostic imaging. The network architecture was also inferred from the similarities.

RESULTS

This resulted the best model for prelabor rupture of membranes (n=883, 376) with the area under curves 0.73 (95% CI 0.72 to 0.75) and 0.70 (95% CI 0.69 to 0.71) respectively by internal and external validations, and outperformed previous models found by systematic review. It was explainable by knowledge-based diagrams and model representation.

CONCLUSIONS

This allows prognostication with actionable insights for preventive medicine.

Identifying the suicidal ideation risk group among older adults in rural areas: Developing a predictive model using machine learning methods

AIMS

The aim of this study was to develop a predictive model that can identify the suicidal ideation risk group among older adults in rural areas using machine learning methods.

DESIGN

This study applied an exploratory, descriptive and cross-sectional design.

METHODS

The participants were older adults (N = 650) aged over 65 living in rural areas of South Korea. Self-report questionnaires were used to collect the demographics, suicidal ideation, depression, socioeconomic information and basic health information from September to October 2020. The collected data were analysed using machine learning methods with R statistical software 4.1.0.

RESULTS

The predictive models indicated that depression, pain, age and loneliness were significant factors of suicidal ideation. Good performance was observed based on the area under the receiver operating characteristic curve in the decision tree, random forest and logistic regression. Finally, the evaluation of model performance indicated moderate to high sensitivity and specificity.

CONCLUSION

The predictive models using machine learning methods may be useful to predict the risk of suicidal ideation. Furthermore, depression with pain, age and feelings of loneliness should be included in the initial screening to assess suicide risk among older adults in rural areas.

IMPACT

Identifying suicidal risk among older adults is challenging. Thus, employing predictive models that can assess depression, pain, age and loneliness can enable public healthcare providers to detect suicidal risk groups. Particularly, the presented models from this study can facilitate healthcare providers with initiating early interventions to prevent suicide among older adults in clinical and community nursing care settings.

REPORTING METHOD

The reporting of this study (Observational, cross-sectional study) conforms to the STROBE statement.

PATIENT OR PUBLIC CONTRIBUTION

No patient or public contribution. This study did not involve patients, service users, caregivers or members of the public.

IMPLICATION FOR THE PROFESSION AND/OR PATIENTS CARE

Applying this model may help to prevent geriatric suicide because the nursing staff will have a greater awareness regarding the suicide ideation risk of older adults, thereby reducing the possibility of their suicide.

Prediction of HELLP Syndrome Severity Using Machine Learning Algorithms-Results from a Retrospective Study

(1) Background: HELLP (hemolysis, elevated liver enzymes, and low platelets) syndrome is a rare and life-threatening complication of preeclampsia. The aim of this study was to evaluate and compare the predictive performances of four machine learning-based models for the prediction of HELLP syndrome, and its subtypes according to the Mississippi classification; (2) Methods: This retrospective case-control study evaluated pregnancies that occurred in women who attended a tertiary maternity hospital in Romania between January 2007 and December 2021. The patients' clinical and paraclinical characteristics were included in four machine learning-based models: decision tree (DT), naïve Bayes (NB), k-nearest neighbors (KNN), and random forest (RF), and their predictive performance were assessed; (3) Results: Our results showed that HELLP syndrome was best predicted by RF (accuracy: 89.4%) and NB (accuracy: 86.9%) models, while DT (accuracy: 91%) and KNN (accuracy: 87.1%) models had the highest performance when used to predict class 1 HELLP syndrome. The predictive performance of these models was modest for class 2 and 3 of HELLP syndrome, with accuracies ranging from 65.2% and 83.8%; (4) Conclusions: The machine learning-based models could be useful tools for predicting HELLP syndrome, and its most severe form-class 1.

Predictive Performance of Machine Learning-Based Methods for the Prediction of Preeclampsia-A Prospective Study

(1) Background: Preeclampsia (PE) prediction in the first trimester of pregnancy is a challenge for clinicians. The aim of this study was to evaluate and compare the predictive performances of machine learning-based models for the prediction of preeclampsia and its subtypes. (2) Methods: This prospective case-control study evaluated pregnancies that occurred in women who attended a tertiary maternity hospital in Romania between November 2019 and September 2022. The patients' clinical and paraclinical characteristics were evaluated in the first trimester and were included in four machine learning-based models: decision tree (DT), naïve Bayes (NB), support vector machine (SVM), and random forest (RF), and their predictive performance was assessed. (3) Results: Early-onset PE was best predicted by DT (accuracy: 94.1%) and SVM (accuracy: 91.2%) models, while NB (accuracy: 98.6%) and RF (accuracy: 92.8%) models had the highest performance when used to predict all types of PE. The predictive performance of these models was modest for moderate and severe types of PE, with accuracies ranging from 70.6% and 82.4%. (4) Conclusions: The machine learning-based models could be useful tools for EO-PE prediction and could differentiate patients who will develop PE as early as the first trimester of pregnancy.

The application of machine learning to predict high-cost patients: A performance-comparison of different models using healthcare claims data

Our aim was to predict future high-cost patients with machine learning using healthcare claims data. We applied a random forest (RF), a gradient boosting machine (GBM), an artificial neural network (ANN) and a logistic regression (LR) to predict high-cost patients in the following year. Therefore, we exploited routinely collected sickness funds claims and cost data of the years 2016, 2017 and 2018. Various specifications of each algorithm were trained and cross-validated on training data (n = 20,984) with claims and cost data from 2016 and outcomes from 2017. The best performing specifications of each algorithm were selected based on validation dataset performance. For performance comparison, selected models were applied to unforeseen data with features of the year 2017 and outcomes of the year 2018 (n = 21,146). The RF was the best performing algorithm measured by the area under the receiver operating curve (AUC) with a value of 0.883 (95% confidence interval (CI): 0.872-0.893) on test data, followed by the GBM (AUC = 0.878; 95% CI: 0.867-0.889). The ANN (AUC = 0.846; 95% CI: 0.834-0.857) and LR (AUC = 0.839; 95% CI: 0.826-0.852) were significantly outperformed by the GBM and the RF. All ML algorithms and the LR performed ´good´ (i.e. 0.9 > AUC ≥ 0.8). We were able to develop machine learning models that predict high-cost patients with 'good' performance facilitating routinely collected sickness fund claims and cost data. We found that tree-based models performed best and outperformed the ANN and LR.

Questionnaire-free machine-learning method to predict depressive symptoms among community-dwelling older adults

The 15-item Geriatric Depression Scale (GDS-15) is widely used to screen for depressive symptoms among older populations. This study aimed to develop and validate a questionnaire-free, machine-learning model as an alternative triage test for the GDS-15 among community-dwelling older adults. The best models were the random forest (RF) and deep-insight visible neural network by internal validation, but both performances were undifferentiated by external validation. The AUROC of the RF model was 0.619 (95% CI 0.610 to 0.627) for the external validation set with a non-local ethnic group. Our triage test can allow healthcare professionals to preliminarily screen for depressive symptoms in older adults without using a questionnaire. If the model shows positive results, then the GDS-15 can be used for follow-up measures. This preliminary screening will save a lot of time and energy for healthcare providers and older adults, especially those persons who are illiterate.

[Machine Learning vs. Statistical Model for Prediction Modelling: Application in Medical Imaging Research]

Clinical prediction models has been increasingly published in radiology research. In particular, as a radiomics research is being actively conducted, the prediction model is developed based on the traditional statistical model, as well as machine learning, to account for the high-dimensional data. In this review, we investigated the statistical and machine learning methods used in clinical prediction model research, and briefly summarized each analytical method for statistical model, machine learning, and statistical learning. Finally, we discussed several considerations for choosing the prediction modeling method.

Machine learning in predicting antimicrobial resistance: a systematic review and meta-analysis

INTRODUCTION

Antimicrobial resistance (AMR) is a global health threat; rapid and timely identification of AMR improves patient prognosis and reduces inappropriate antibiotic use.

METHODS

Relevant literature in PubMed, Web of Science, Embase and Institute of Electrical and Electronics Engineers prior to 28 September 2021 was searched. Any study that deployed machine learning (ML) or a risk score as a tool to predict AMR was included in the final review; there were 25 studies that employed the ML algorithm to predict AMR.

RESULTS

Extended spectrum β-lactamases, methicillin-resistant Staphylococcus aureus (MRSA) and carbapenem resistance were the most common outcomes in studies with a specific resistance pattern. The most common algorithms in ML prediction were logistic regression (n = 14 studies), decision tree (n = 14) and random forest (n = 7). The area under the curve (AUC) range for ML prediction was 0.48-0.93. The pooled AUC for ML prediction was 0.82 (0.78-0.85). Compared with risk score, higher specificity [87% (82-91) vs. 37% (25-51)] was indicated for ML prediction, but not sensitivity [67% (62-72) vs. 73% (67-79)].

CONCLUSIONS

Machine learning might be a potential technology for AMR prediction; however, retrospective methodology for model development, nonstandard data processing and scarcity of validation in a randomised controlled trial or real-world study limit the application of these models in clinical practice.

Identifying patients at risk of unplanned re-hospitalisation using statewide electronic health records

Preventing unplanned hospitalisations, including readmissions and re-presentations to the emergency department, is an important strategy for addressing the growing demand for hospital care. Significant successes have been reported from interventions put in place by hospitals to reduce their incidence. However, there is limited use of data-driven algorithms in hospital services to identify patients for enrolment into these intervention programs. Here we present the results of a study aiming to develop algorithms deployable at scale as part of a state government’s initiative to address rehospitalizations and which fills several gaps identified in the state-of-the-art literature. To the best of our knowledge, our study involves the largest-ever sample size for developing risk models. Logistic regression, random forests and gradient boosted techniques were explored as model candidates and validated retrospectively on five years of data from 27 hospitals in Queensland, Australia. The models used a range of predictor variables sourced from state-wide Emergency Department(ED), inpatient, hospital-dispensed medications and hospital-requested pathology databases. The investigation leads to several findings: (i) the advantage of looking at a longer patient data history, (ii) ED and inpatient datasets alone can provide useful information for predicting hospitalisation risk and the addition of medications and pathology test results leads to trivial performance improvements, (iii) predicting readmissions to the hospital was slightly easier than predicting re-presentations to ED after an inpatient stay, which was slightly easier again than predicting re-presentations to ED after an EDstay, (iv) a gradient boosted approach (XGBoost) was systematically the most powerful modelling approach across various tests.

Artificial intelligence and its impact on the domains of universal health coverage, health emergencies and health promotion: An overview of systematic reviews

•

An overview of systematic reviews on the application of AI including 129 studies.

•

AI use is prominent in Universal Health Coverage, featuring image analysis in neoplasms.

•

Half of the reviews did not evaluate validation procedures nor reporting guidelines.

•

Risk of bias was only included un a third of the reviews.

•

There is not sufficient evidence to transfer AI to actual healthcare delivery.

Background

Artificial intelligence is fueling a new revolution in medicine and in the healthcare sector. Despite the growing evidence on the benefits of artificial intelligence there are several aspects that limit the measure of its impact in people’s health. It is necessary to assess the current status on the application of AI towards the improvement of people’s health in the domains defined by WHO’s Thirteenth General Programme of Work (GPW13) and the European Programme of Work (EPW), to inform about trends, gaps, opportunities, and challenges.

Objective

To perform a systematic overview of systematic reviews on the application of artificial intelligence in the people’s health domains as defined in the GPW13 and provide a comprehensive and updated map on the application specialties of artificial intelligence in terms of methodologies, algorithms, data sources, outcomes, predictors, performance, and methodological quality.

Methods

A systematic search in MEDLINE, EMBASE, Cochrane and IEEEXplore was conducted between January 2015 and June 2021 to collect systematic reviews using a combination of keywords related to the domains of universal health coverage, health emergencies protection, and better health and wellbeing as defined by the WHO’s PGW13 and EPW. Eligibility criteria was based on methodological quality and the inclusion of practical implementation of artificial intelligence. Records were classified and labeled using ICD-11 categories into the domains of the GPW13. Descriptors related to the area of implementation, type of modeling, data entities, outcomes and implementation on care delivery were extracted using a structured form and methodological aspects of the included reviews studies was assessed using the AMSTAR checklist.

Results

The search strategy resulted in the screening of 815 systematic reviews from which 203 were assessed for eligibility and 129 were included in the review. The most predominant domain for artificial intelligence applications was Universal Health Coverage (N = 98) followed by Health Emergencies (N = 16) and Better Health and Wellbeing (N = 15). Neoplasms area on Universal Health Coverage was the disease area featuring most of the applications (21.7 %, N = 28). The reviews featured analytics primarily over both public and private data sources (67.44 %, N = 87). The most used type of data was medical imaging (31.8 %, N = 41) and predictors based on regions of interest and clinical data. The most prominent subdomain of Artificial Intelligence was Machine Learning (43.4 %, N = 56), in which Support Vector Machine method was predominant (20.9 %, N = 27). Regarding the purpose, the application of Artificial Intelligence I is focused on the prediction of the diseases (36.4 %, N = 47). With respect to the validation, more than a half of the reviews (54.3 %, N = 70) did not report a validation procedure and, whenever available, the main performance indicator was the accuracy (28.7 %, N = 37). According to the methodological quality assessment, a third of the reviews (34.9 %, N = 45) implemented methods for analysis the risk of bias and the overall AMSTAR score below was 5 (4.01 ± 1.93) on all the included systematic reviews.

Conclusion

Artificial intelligence is being used for disease modelling, diagnose, classification and prediction in the three domains of GPW13. However, the evidence is often limited to laboratory and the level of adoption is largely unbalanced between ICD-11 categoriesand diseases. Data availability is a determinant factor on the developmental stage of artificial intelligence applications. Most of the reviewed studies show a poor methodological quality and are at high risk of bias, which limits the reproducibility of the results and the reliability of translating these applications to real clinical scenarios. The analyzed papers show results only in laboratory and testing scenarios and not in clinical trials nor case studies, limiting the supporting evidence to transfer artificial intelligence to actual care delivery.

Risk of bias of prognostic models developed using machine learning: a systematic review in oncology

BACKGROUND

Prognostic models are used widely in the oncology domain to guide medical decision-making. Little is known about the risk of bias of prognostic models developed using machine learning and the barriers to their clinical uptake in the oncology domain.

METHODS

We conducted a systematic review and searched MEDLINE and EMBASE databases for oncology-related studies developing a prognostic model using machine learning methods published between 01/01/2019 and 05/09/2019. The primary outcome was risk of bias, judged using the Prediction model Risk Of Bias ASsessment Tool (PROBAST). We described risk of bias overall and for each domain, by development and validation analyses separately.

RESULTS

We included 62 publications (48 development-only; 14 development with validation). 152 models were developed across all publications and 37 models were validated. 84% (95% CI: 77 to 89) of developed models and 51% (95% CI: 35 to 67) of validated models were at overall high risk of bias. Bias introduced in the analysis was the largest contributor to the overall risk of bias judgement for model development and validation. 123 (81%, 95% CI: 73.8 to 86.4) developed models and 19 (51%, 95% CI: 35.1 to 67.3) validated models were at high risk of bias due to their analysis, mostly due to shortcomings in the analysis including insufficient sample size and split-sample internal validation.

CONCLUSIONS

The quality of machine learning based prognostic models in the oncology domain is poor and most models have a high risk of bias, contraindicating their use in clinical practice. Adherence to better standards is urgently needed, with a focus on sample size estimation and analysis methods, to improve the quality of these models.

Development and validation of a meta-learner for combining statistical and machine learning prediction models in individuals with depression

BACKGROUND

The debate of whether machine learning models offer advantages over standard statistical methods when making predictions is ongoing. We discuss the use of a meta-learner model combining both approaches as an alternative.

METHODS

To illustrate the development of a meta-learner, we used a dataset of 187,757 people with depression. Using 31 variables, we aimed to predict two outcomes measured 60 days after initiation of antidepressant treatment: severity of depressive symptoms (continuous) and all-cause dropouts (binary). We fitted a ridge regression and a multi-layer perceptron (MLP) deep neural network as two separate prediction models ("base-learners"). We then developed two "meta-learners", combining predictions from the two base-learners. To compare the performance across the different methods, we calculated mean absolute error (MAE, for continuous outcome) and the area under the receiver operating characteristic curve (AUC, for binary outcome) using bootstrapping.

RESULTS

Compared to the best performing base-learner (MLP base-learner, MAE at 4.63, AUC at 0.59), the best performing meta-learner showed a 2.49% decrease in MAE at 4.52 for the continuous outcome and a 6.47% increase in AUC at 0.60 for the binary outcome.

CONCLUSIONS

A meta-learner approach may effectively combine multiple prediction models. Choosing between statistical and machine learning models may not be necessary in practice.

Using Machine Learning to Predict Complications in Pregnancy: A Systematic Review

Introduction: Artificial intelligence is widely used in medical field, and machine learning has been increasingly used in health care, prediction, and diagnosis and as a method of determining priority. Machine learning methods have been features of several tools in the fields of obstetrics and childcare. This present review aims to summarize the machine learning techniques to predict perinatal complications.

Objective: To identify the applicability and performance of machine learning methods used to identify pregnancy complications.

Methods: A total of 98 articles were obtained with the keywords “machine learning,” “deep learning,” “artificial intelligence,” and accordingly as they related to perinatal complications (“complications in pregnancy,” “pregnancy complications”) from three scientific databases: PubMed, Scopus, and Web of Science. These were managed on the Mendeley platform and classified using the PRISMA method.

Results: A total of 31 articles were selected after elimination according to inclusion and exclusion criteria. The features used to predict perinatal complications were primarily electronic medical records (48%), medical images (29%), and biological markers (19%), while 4% were based on other types of features, such as sensors and fetal heart rate. The main perinatal complications considered in the application of machine learning thus far are pre-eclampsia and prematurity. In the 31 studies, a total of sixteen complications were predicted. The main precision metric used is the AUC. The machine learning methods with the best results were the prediction of prematurity from medical images using the support vector machine technique, with an accuracy of 95.7%, and the prediction of neonatal mortality with the XGBoost technique, with 99.7% accuracy.

Conclusion: It is important to continue promoting this area of research and promote solutions with multicenter clinical applicability through machine learning to reduce perinatal complications. This systematic review contributes significantly to the specialized literature on artificial intelligence and women’s health.

Interpretable machine learning to identify important predictors of birth weight: A prospective cohort study

BACKGROUND

Predicting birth weight and identifying its risk factors are clinically important. This study aims to use interpretable machine learning to predict birth weight and identity important predictors.

METHODS

This prospective cohort study was conducted in Tongzhou Maternal and Child Health Care Hospital of Beijing, China, recruiting pregnant women between June 2018 and February 2019. We used 24 features to predict infant birth weight, including gestational age, mother's age, parity, history of macrosomia delivery, pre-pregnancy body mass index (BMI), height, father's BMI, lifestyle (diet, physical activity, smoking), and biomarker (fasting glucose and lipids) features. Study outcome was birth weight of infant. We used 8 supervised learning models including 4 individual [linear regression, ridge regression, lasso regression, support vector machines regression (SVR)], and 4 ensemble estimators (random forest, AdaBoost, gradient boosted trees, and voting ensemble for regression) to predict birth weight. Model accuracy was measured by root mean squared error (RMSE) of 10-fold cross validation on the training set and RMSE of prediction on the test set. We used permutation importance algorithm to understand the prediction from the models and what affected them.

RESULT

This study included 4,754 mother-child dyads. RMSEs were lower in voting ensemble for regression, linear regression, and SVR than random forest, AdaBoost, and gradient boosted tree. The 5 most important predictors for infant birth weight were gestational age, fetal sex, preterm birth, mother's height, and pre-pregnancy BMI. After adding ultrasound-measured indicators of fetal growth into predictors, mother's height and pre-pregnancy BMI remained the most important predictors in predicting the outcome.

CONCLUSION

Mother's height and pre-pregnancy BMI were identified as important predictors for infant birth weight. Interpretable machine learning is a promising tool in the prediction of birth weight.

Artificial intelligence's role in vascular surgery decision-making

Artificial intelligence (AI) is the next great advance informing medical science. Several disciplines, including vascular surgery, use AI-based decision-making tools to improve clinical performance. Although applied widely, AI functions best when confronted with voluminous, accurate data. Consistent, predictable analytic technique selection also challenges researchers. This article contextualizes AI analyses within evidence-based medicine, focusing on "big data" and health services research, as well as discussing opportunities to improve data collection and realize AI's promise.

Health Data-Driven Machine Learning Algorithms Applied to Risk Indicators Assessment for Chronic Kidney Disease

PURPOSE

As global aging progresses, the health management of chronic diseases has become an important issue of concern to governments. Influenced by the aging of its population and improvements in the medical system and healthcare in general, Taiwan's population of patients with chronic kidney disease (CKD) has tended to grow year by year, including the incidence of high-risk cases that pose major health hazards to the elderly and middle-aged populations.

METHODS

This study analyzed the annual health screening data for 65,394 people from 2010 to 2015 sourced from the MJ Group - a major health screening center in Taiwan - including data for 18 risk indicators. We used five prediction model analysis methods, namely, logistic regression (LR) analysis, C5.0 decision tree (C5.0) analysis, stochastic gradient boosting (SGB) analysis, multivariate adaptive regression splines (MARS), and eXtreme gradient boosting (XGboost), with estimated glomerular filtration rate (e-GFR) data to determine G3a, G3b & G4 stage CKD risk factors.

RESULTS

The LR analysis (AUC=0.848), SGB analysis (AUC=0.855), and XGboost (AUC=0.858) generated similar classification performance levels and all outperformed the C5.0 and MARS methods. The study results showed that in terms of CKD risk factors, blood urea nitrogen (BUN) and uric acid (UA) were identified as the first and second most important indicators in the models of all five analysis methods, and they were also clinically recognized as the major risk factors. The results for systolic blood pressure (SBP), SGPT, SGOT, and LDL were similar to those of a related study. Interestingly, however, socioeconomic status-related education was found to be the third important indicator in all three of the better performing analysis methods, indicating that it is more important than the other risk indicators of this study, which had different levels of importance according to the different methods.

CONCLUSION

The five prediction model methods can provide high and similar classification performance in this study. Based on the results of this study, it is recommended that education as the socioeconomic status should be an important factor for CKD, as high educational level showed a negative and highly significant correlation with CKD. The findings of this study should also be of value for further discussions and follow-up research.

Metabolomic Profile of Young Adults Born Preterm

Prematurity is a risk factor for the development of chronic adult diseases. Metabolomics can correlate the biochemical changes to a determined phenotype, obtaining real information about the state of health of a subject at that precise moment. Significative differences in the metabolomic profile of preterm newborns compared to those born at term have been already identified at birth. An observational case–control study was performed at the University Hospital of Siena. The aim was to evaluate and compare the metabolomic profiles of young adults born preterm to those born at term. Urinary samples were collected from 67 young adults (18–23 years old) born preterm (mean gestational age of 30 weeks, n = 49), and at term of pregnancy (mean gestational age of 38 weeks, n = 18). The urinary spectra of young adults born preterm was different from those born at term and resembled what was previously described at birth. The Random Forest algorithm gave the best classification (accuracy 82%) and indicated the following metabolites as responsible for the classification: citrate, CH2 creatinine, fumarate and hippurate. Urine spectra are promising tools for the early identification of neonates at risk of disease in adulthood and may provide insight into the pathogenesis and effects of fetal programming and infants’ outcomes.

Machine learning modeling for preterm birth prediction using health record: A systematic review (Preprint)

Background

Preterm birth (PTB), a common pregnancy complication, is responsible for 35% of the 3.1 million pregnancy-related deaths each year and significantly affects around 15 million children annually worldwide. Conventional approaches to predict PTB lack reliable predictive power, leaving >50% of cases undetected. Recently, machine learning (ML) models have shown potential as an appropriate complementary approach for PTB prediction using health records (HRs).

Objective

This study aimed to systematically review the literature concerned with PTB prediction using HR data and the ML approach.

Methods

This systematic review was conducted in accordance with the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) statement. A comprehensive search was performed in 7 bibliographic databases until May 15, 2021. The quality of the studies was assessed, and descriptive information, including descriptive characteristics of the data, ML modeling processes, and model performance, was extracted and reported.

Results

A total of 732 papers were screened through title and abstract. Of these 732 studies, 23 (3.1%) were screened by full text, resulting in 13 (1.8%) papers that met the inclusion criteria. The sample size varied from a minimum value of 274 to a maximum of 1,400,000. The time length for which data were extracted varied from 1 to 11 years, and the oldest and newest data were related to 1988 and 2018, respectively. Population, data set, and ML models’ characteristics were assessed, and the performance of the model was often reported based on metrics such as accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve.

Conclusions

Various ML models used for different HR data indicated potential for PTB prediction. However, evaluation metrics, software and package used, data size and type, selected features, and importantly data management method often remain unjustified, threatening the reliability, performance, and internal or external validity of the model. To understand the usefulness of ML in covering the existing gap, future studies are also suggested to compare it with a conventional method on the same data set.

Comparison of Different Machine Learning Classifiers for Glaucoma Diagnosis Based on Spectralis OCT

Early detection is important in glaucoma management. By using optical coherence tomography (OCT), the subtle structural changes caused by glaucoma can be detected. Though OCT provided abundant parameters for comprehensive information, clinicians may be confused once the results conflict. Machine learning classifiers (MLCs) are good tools for considering numerous parameters and generating reliable diagnoses in glaucoma practice. Here we aim to compare different MLCs based on Spectralis OCT parameters, including circumpapillary retinal nerve fiber layer (cRNFL) thickness, Bruch’s membrane opening-minimum rim width (BMO-MRW), Early Treatment Diabetes Retinopathy Study (ETDRS) macular thickness, and posterior pole asymmetry analysis (PPAA), in discriminating normal from glaucomatous eyes. Five MLCs were proposed, namely conditional inference trees (CIT), logistic model tree (LMT), C5.0 decision tree, random forest (RF), and extreme gradient boosting (XGBoost). Logistic regression (LGR) was used as a benchmark for comparison. RF was shown to be the best model. Ganglion cell layer measurements were the most important predictors in early glaucoma detection and cRNFL measurements were more important as the glaucoma severity increased. The global, temporal, inferior, superotemporal, and inferotemporal sites were relatively influential locations among all parameters. Clinicians should cautiously integrate the Spectralis OCT results into the entire clinical picture when diagnosing glaucoma.

Use of an artificial intelligence-based rule extraction approach to predict an emergency cesarean section

Objective

One of the major problems with artificial intelligence (AI) is that it is generally known as a “black box”. Therefore, the present study aimed to construct an emergency cesarean section (CS) prediction system using an AI‐based rule extraction approach as a “white box” to detect the cause for the emergency CS.

Methods

Data were collected from all perinatal records of all delivery outcomes at Osaka Medical College between December 2014 and July 2019. We identified the delivery method for all deliveries after 36 gestational weeks as either (1) vaginal delivery or scheduled CS, or (2) emergency CS. From among these, we selected 52 risk factors to feed into an AI‐based rule extraction algorithm to extract rules to predict an emergency CS.

Results

We identified 1513 singleton deliveries (1285 [84.9%] vaginal deliveries, 228 emergency CS [15.1%]) and extracted 15 rules. We achieved an average accuracy of 81.90% using five‐fold cross‐validation and an area under the receiving operating characteristic curve of 71.46%.

Conclusion

To our knowledge, this is the first study to use interpretable AI‐based rule extraction technology to predict an emergency CS. This system appears to be useful for identifying hidden factors for emergency CS.

This is the first study to construct a prediction system for an emergency cesarean section using an artificial intelligence‐based “white box” rule extraction approach.

Screening of gene markers related to the prognosis of metastatic skin cutaneous melanoma based on Logit regression and survival analysis

BACKGROUND

Bioinformatics was used to analyze the skin cutaneous melanoma (SKCM) gene expression profile to provide a theoretical basis for further studying the mechanism underlying metastatic SKCM and the clinical prognosis.

METHODS

We downloaded the gene expression profiles of 358 metastatic and 102 primary (nonmetastatic) CM samples from The Cancer Genome Atlas (TCGA) database as a training dataset and the GSE65904 dataset from the National Center for Biotechnology Information database as a validation dataset. Differentially expressed genes (DEGs) were screened using the limma package of R3.4.1, and prognosis-related feature DEGs were screened using Logit regression (LR) and survival analyses. We also used the STRING online database, Cytoscape software, and Database for Annotation, Visualization and Integrated Discovery software for protein-protein interaction network, Gene Ontology, and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analyses based on the screened DEGs.

RESULTS

Of the 876 DEGs selected, 11 (ZNF750, NLRP6, TGM3, KRTDAP, CAMSAP3, KRT6C, CALML5, SPRR2E, CD3G, RTP5, and FAM83C) were screened using LR analysis. The survival prognosis of nonmetastatic group was better compared to the metastatic group between the TCGA training and validation datasets. The 11 DEGs were involved in 9 KEGG signaling pathways, and of these 11 DEGs, CALML5 was a feature DEG involved in the melanogenesis pathway, 12 targets of which were collected.

CONCLUSION

The feature DEGs screened, such as CALML5, are related to the prognosis of metastatic CM according to LR. Our results provide new ideas for exploring the molecular mechanism underlying CM metastasis and finding new diagnostic prognostic markers.

Machine Learning Prediction Models for Gestational Diabetes Mellitus: A meta- analysis (Preprint)

Background

Gestational diabetes mellitus (GDM) is a common endocrine metabolic disease, involving a carbohydrate intolerance of variable severity during pregnancy. The incidence of GDM-related complications and adverse pregnancy outcomes has declined, in part, due to early screening. Machine learning (ML) models are increasingly used to identify risk factors and enable the early prediction of GDM.

Objective

The aim of this study was to perform a meta-analysis and comparison of published prognostic models for predicting the risk of GDM and identify predictors applicable to the models.

Methods

Four reliable electronic databases were searched for studies that developed ML prediction models for GDM in the general population instead of among high-risk groups only. The novel Prediction Model Risk of Bias Assessment Tool (PROBAST) was used to assess the risk of bias of the ML models. The Meta-DiSc software program (version 1.4) was used to perform the meta-analysis and determination of heterogeneity. To limit the influence of heterogeneity, we also performed sensitivity analyses, a meta-regression, and subgroup analysis.

Results

A total of 25 studies that included women older than 18 years without a history of vital disease were analyzed. The pooled area under the receiver operating characteristic curve (AUROC) for ML models predicting GDM was 0.8492; the pooled sensitivity was 0.69 (95% CI 0.68-0.69; P<.001; I²=99.6%) and the pooled specificity was 0.75 (95% CI 0.75-0.75; P<.001; I²=100%). As one of the most commonly employed ML methods, logistic regression achieved an overall pooled AUROC of 0.8151, while non–logistic regression models performed better, with an overall pooled AUROC of 0.8891. Additionally, maternal age, family history of diabetes, BMI, and fasting blood glucose were the four most commonly used features of models established by the various feature selection methods.

Conclusions

Compared to current screening strategies, ML methods are attractive for predicting GDM. To expand their use, the importance of quality assessments and unified diagnostic criteria should be further emphasized.