Background: Predictions in pregnancy care are complex because of interactions among multiple factors. Hence, pregnancy outcomes are not easily predicted by a single predictor using only one algorithm or modeling method.Objective: This study aims to review and compare the predictive performances between logistic regression (LR) and other machine learning algorithms for developing or validating a multivariable prognostic prediction model for pregnancy care to inform clinicians’ decision making.Methods: Research articles from MEDLINE, Scopus, Web of Science, and Google Scholar were reviewed following several guidelines for a prognostic prediction study, including a risk of bias (ROB) assessment. We report the results based on the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Studies were primarily framed as PICOTS (population, index, comparator, outcomes, timing, and setting): Population: men or women in procreative management, pregnant women, and fetuses or newborns; Index: multivariable prognostic prediction models using non-LR algorithms for risk classification to inform clinicians’ decision making; Comparator: the models applying an LR; Outcomes: pregnancy-related outcomes of procreation or pregnancy outcomes for pregnant women and fetuses or newborns; Timing: pre-, inter-, and peripregnancy periods (predictors), at the pregnancy, delivery, and either puerperal or neonatal period (outcome), and either short- or long-term prognoses (time interval); and Setting: primary care or hospital. The results were synthesized by reporting study characteristics and ROBs and by random effects modeling of the difference of the logit area under the receiver operating characteristic curve of each non-LR model compared with the LR model for the same pregnancy outcomes. We also reported between-study heterogeneity by using τ2 and I2.Results: Of the 2093 records, we included 142 studies for the systematic review and 62 studies for a meta-analysis. Most prediction models used LR (92/142, 64.8%) and artificial neural networks (20/142, 14.1%) among non-LR algorithms. Only 16.9% (24/142) of studies had a low ROB. A total of 2 non-LR algorithms from low ROB studies significantly outperformed LR. The first algorithm was a random forest for preterm delivery (logit AUROC 2.51, 95% CI 1.49-3.53; I2=86%; τ2=0.77) and pre-eclampsia (logit AUROC 1.2, 95% CI 0.72-1.67; I2=75%; τ2=0.09). The second algorithm was gradient boosting for cesarean section (logit AUROC 2.26, 95% CI 1.39-3.13; I2=75%; τ2=0.43) and gestational diabetes (logit AUROC 1.03, 95% CI 0.69-1.37; I2=83%; τ2=0.07).Conclusions: Prediction models with the best performances across studies were not necessarily those that used LR but also used random forest and gradient boosting that also performed well. We recommend a reanalysis of existing LR models for several pregnancy outcomes by comparing them with those algorithms that apply standard guidelines.Trial Registration: PROSPERO (International Prospective Register of Systematic Reviews) CRD42019136106; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=136106

An all-inclusive and accurate prediction of outcomes for patients with acute ischemic stroke (AIS) is crucial for clinical decision-making. This study developed extreme gradient boosting (XGBoost)-based models using three simple factors—age, fasting glucose, and National Institutes of Health Stroke Scale (NIHSS) scores—to predict the three-month functional outcomes after AIS. We retrieved the medical records of 1848 patients diagnosed with AIS and managed at a single medical center between 2016 and 2020. We developed and validated the predictions and ranked the importance of each variable. The XGBoost model achieved notable performance, with an area under the curve of 0.8595. As predicted by the model, the patients with initial NIHSS score > 5, aged over 64 years, and fasting blood glucose > 86 mg/dL were associated with unfavorable prognoses. For patients receiving endovascular therapy, fasting glucose was the most important predictor. The NIHSS score at admission was the most significant predictor for those who received other treatments. Our proposed XGBoost model showed a reliable predictive power of AIS outcomes using readily available and simple predictors and also demonstrated the validity of the model for application in patients receiving different AIS treatments, providing clinical evidence for future optimization of AIS treatment strategies.

Introduction: Assisted reproductive technology has been proposed for women with infertility. Moreover, in vitro fertilization (IVF) cycles are increasing. Factors contributing to successful pregnancy have been widely explored. In this study, we used machine learning algorithms to construct prediction models for clinical pregnancies in IVF. Materials and methods: A total of 24,730 patients entered IVF and intracytoplasmic sperm injection cycles with clinical pregnancy outcomes at Taipei Medical University Hospital. Data used included patient characteristics and treatment. We used machine learning methods to develop prediction models for clinical pregnancy and explored how each variable affects the outcome of interest using partial dependence plots. Results: Experimental results showed that the random forest algorithm outperforms logistic regression in terms of areas under the receiver operating characteristics curve. The ovarian stimulation protocol is the most important factor affecting pregnancy outcomes. Long and ultra-long protocols have shown positive effects on clinical pregnancy among all protocols. Furthermore, total frozen and transferred embryos are positive for a clinical pregnancy, but female age and duration of infertility have negative effects on clinical pregnancy. Conclusion: Our findings show the importance of variables and propensity of each variable by random forest algorithm for clinical pregnancy in the assisted reproductive technology cycle. This study provides a ranking of variables affecting clinical pregnancy and explores the effects of each treatment on successful pregnancy. Our study has the potential to help clinicians evaluate the success of IVF in patients.

Myasthenia gravis (MG), a low-prevalence autoimmune disorder characterized by clinical heterogeneity and unpredictable disease fluctuations, presents significant risks of acute exacerbations requiring intensive care. These crises contribute substantially to patient morbidity and mortality. This study aimed to develop and validate machine-learning models for predicting intensive care unit (ICU) admission risk among patients with MG-related disease instability. In this retrospective analysis of 314 MG patients hospitalized between 2015 and 2018, we implemented four machine learning algorithms, including logistic regression, support vector machine, extreme gradient boosting (XGBoost), and random forest, to predict ICU admission risk. The models incorporated fourteen clinical parameters as predictive features. The SHapley Additive exPlanations method was utilized to assess the importance of factors associated with ICU admission. Through 10-fold cross-validation, the XGBoost model demonstrated superior predictive performance (area under the receiver operating characteristic curve: 0.8943, accuracy: 0.8603, sensitivity: 0.7222, and specificity: 0.9125). Among the analyzed features, MG severity, as classified by the Myasthenia Gravis Foundation of America clinical classification, was identified as the most significant factor influencing ICU admission. Additionally, disease duration, a key continuous variable, was inversely correlated with the risk of ICU admission. MG severity is the primary determinant of ICU admission, with shorter disease duration increasing the risk, possibly due to greater susceptibility to exacerbations. The XGBoost model exhibited excellent performance and accuracy, effectively identifying critical clinical factors for predicting ICU admission risk in MG patients. This novel, personalized approach to risk stratification elucidates crucial risk factors and has the potential to enhance clinical decision-making, optimize resource allocation, and ultimately improve patient outcomes.

Background: Due to the spread of the coronavirus disease 2019 (COVID-19) pandemic in 2020, the interest of nutritional supplements has emerged. Limited data are available on how the COVID-19 pandemic affects the search interest in nutritional supplements in Taiwan and worldwide. The study aims to investigate changes in public search interest of nutritional supplements pre- and during the COVID-19 pandemic. Methods: Our World in Data dataset was used to collect both global and local (Taiwan) number of COVID-19 newly confirmed cases and deaths. Google Trends search query was being used to obtain relative search volumes (RSVs) covering a timeframe between 2019 to 2022. Spearman’s rank-order correlation coefficients were used to measure relationships between confirmed new cases and deaths and RSVs of nutritional supplements. Multivariate analysis was conducted to examine the effect of domestic and global new cases and deaths on the RSVs of nutritional supplements. Results: The mean RSVs for nutritional supplements were higher during the COVID-19 pandemic period (between 2020 to 2022) compared to the pre-pandemic period (year of 2019) for both Taiwan and worldwide. In terms of seasonal variations, except for vitamin D, the mean RSVs of probiotics, vitamin B complex, and vitamin C in winter were significantly lower compared to other seasons in Taiwan. The RSVs of nutritional supplements were not only affected by domestic cases and deaths but also by global new cases and deaths. Conclusions: The interests in nutritional supplements had substantially increased in response to the COVID-19 pandemic. The RSVs of nutritional supplements in Taiwan were not only influenced by global and domestic pandemic severity but also by seasons.

Purpose: Boron Neutron Capture Therapy (BNCT) has gained popularity in recent years, with over 500 treatment courses performed in Taiwan since 2017. Traditionally, the tumor-to-normal tissue ratio (T/N ratio) is assessed using SUV measurements from 4-borono-2-(18) F-fluoro-phenylalanine (F-BPA) PET, allowing for precise tumor boron concentration estimation when serum boron levels are measured on the day of treatment. However, limited accessibility to F-BPA PET complicates dose calculations, and in its absence, a fixed T/N ratio of 3 is used in treatment planning. Fluciclovine PET has recently been explored as an alternative, as both fluciclovine and BPA share the L-type amino acid transporter 1 (LAT-1) transporter, although fluciclovine can also be transported via alanine-serine-cysteine transporter 2 (ASCT2). However, its accuracy in reflecting BPA distribution and its correlation with treatment response remain uncertain. Patients and Methods: Since June 2022, fluciclovine PET has been used for brain tumor evaluation in Taiwan. By June 2024, 80 brain tumor patients underwent pre-BNCT assessment with fluciclovine PET. After excluding those who received a second treatment course, 44 patients were analyzed. The average T/N ratio in this cohort was 4.6, higher than reported averages for F-BPA PET (2.5 for head and neck tumors, 3 for brain tumors). The tumor response rate was defined as patients achieving either a complete or partial response, as evaluated by experienced neuroradiologists. Patients were categorized based on response achievement, and potential prognostic factors were compared. Results: The mean T/N ratio of fluciclovine PET was 4.61±1.43 (range: 2.58–8.86). Among 15 patients who underwent follow-up fluciclovine PET 3 months post-BNCT, the mean T/N ratio decreased significantly to 2.85±1.16 (range: 1.00–5.47). Treatment response assessment at 3 months post-BNCT revealed that 4 patients achieved complete response (CR), 26 had partial response (PR), 5 exhibited stable disease (SD), and 9 experienced progressive disease (PD). Responders had significantly smaller tumors compared with nonresponders (35.74 vs. 83.83 cm³, p=0.009) and received higher minimum tumor doses (18.50 vs. 12.13 GyE, p=0.033). In addition, a significant decline in T/N ratio was observed following BNCT, decreasing from 4.602±0.368 pretreatment to 2.847±0.300 at 3 months post-treatment. Conclusions: Our findings suggest that while fluciclovine PET may provide an estimate of BPA uptake, it is not a reliable predictor of treatment response. However, it remains an effective tool for assessing treatment effect following BNCT. Further studies are necessary to identify key prognostic factors for selecting BNCT candidates and to determine whether fluciclovine PET can effectively predict BNCT outcomes.