Objective: This study aimed to systematically assess the characteristics and risk of bias of previous studies that have investigated nonlinear machine learning algorithms for warfarin dose prediction. Methods: We systematically searched PubMed, Embase, Cochrane Library, Chinese National Knowledge Infrastructure (CNKI), China Biology Medicine (CBM), China Science and Technology Journal Database (VIP), and Wanfang Database up to March 2022. We assessed the general characteristics of the included studies with respect to the participants, predictors, model development, and model evaluation. The methodological quality of the studies was determined, and the risk of bias was evaluated using the Prediction model Risk of Bias Assessment Tool (PROBAST). Results: From a total of 8996 studies, 23 were assessed in this study, of which 23 (100%) were retrospective, and 11 studies focused on the Asian population. The most common demographic and clinical predictors were age (21/23, 91%), weight (17/23, 74%), height (12/23, 52%), and amiodarone combination (11/23, 48%), while CYP2C9 (14/23, 61%), VKORC1 (14/23, 61%), and CYP4F2 (5/23, 22%) were the most common genetic predictors. Of the included studies, the MAE ranged from 1.47 to 10.86 mg/week in model development studies, from 2.42 to 5.18 mg/week in model development with external validation (same data) studies, from 12.07 to 17.59 mg/week in model development with external validation (another data) studies, and from 4.40 to 4.84 mg/week in model external validation studies. All studies were evaluated as having a high risk of bias. Factors contributing to the risk of bias include inappropriate exclusion of participants (10/23, 43%), small sample size (15/23, 65%), poor handling of missing data (20/23, 87%), and incorrect method of selecting predictors (8/23, 35%). Conclusions: Most studies on nonlinear-machine-learning-based warfarin prediction models show poor methodological quality and have a high risk of bias. The analysis domain is the major contributor to the overall high risk of bias. External validity and model reproducibility are lacking in most studies. Future studies should focus on external validity, diminish risk of bias, and enhance real-world clinical relevance.

Background. Acupoint sensitization is considered an important factor in the efficacy of acupoint therapy. This study aimed to evaluate the efficacy of acupressure in the prevention of stable angina pectoris using acupoints with different pressure-pain sensitivities. Methods. A total of 202 patients were enrolled and randomly assigned to a high-sensitivity group (HSG) (n = 109) in which patients received acupressure at the five acupoints with the highest sensitivity to pain and a low-sensitivity group (LSG) (n = 93) in which patients received acupressure at the five acupoints with the lowest sensitivity to pain. The duration of acupressure treatment was 4 weeks, and the patients were evaluated at baseline, week 4, and week 8. The primary outcome was a change in the frequency of angina attacks from baseline. The secondary outcomes included nitroglycerin consumption, the Canadian Cardiovascular Society classification, and the Seattle Angina Questionnaire score. Adverse events such as bleeding and subcutaneous haemorrhage were recorded in both groups. Results. The effect of acupressure compared with baseline on the prevention of angina pectoris in HSG was better than that in LSG at week 4 (incidence rate ratio (IRR): 0.691 and 95% confidence interval (CI): [0.569, 0.839]) and week 8 (IRR: 0.692 and 95% CI: [0.569, 0.839]). No significant difference between groups was found in the frequency of nitroglycerin consumption at week 4 (odds ratio (OR) = 0.863 and 95% CI: [0.147, 5.077]) or week 8 (OR = 1.426 and 95% CI: [0.211, 9.661]). Two themes in the questionnaire showed significantly different changes from baseline between the two groups. Scores on the angina frequency (AF) subscale had changed more from the baseline in the HSG at week 8 than in the LSG (mean difference (MD) = 3.807 and 95% CI: [0.673, 6.942]). Scores on the treatment satisfaction (TS) subscale had also changed more in the HSG than in the LSG at week 4 (MD = 3.651 and 95% CI: [0.327, 7.327]) and week 8 (MD = 4.220 and 95% CI: [0.347, 7.346]). One patient in the LSG reported bruising at the acupoint. No unexpected safety problems arose. Conclusions. This study showed that acupressure at acupoints with high sensitivity to pain may effectively reduce the frequency of stable angina pectoris episodes. This trial is registered with NCT03975140.

Patients requiring low-dose warfarin are more likely to suffer bleeding due to overdose. The goal of this work is to improve the feedforward neural network model's precision in predicting the low maintenance dose for Chinese in the aspect of training data construction. We built the model from a resampled dataset created by equal stratified sampling (maintaining the same sample number in three dose-groups with a total of 3639) and performed internal and external validations. Comparing to the model trained from the raw dataset of 19,060 eligible cases, we improved the low-dose group's ideal prediction percentage from 0.7 to 9.6% and maintained the overall performance (76.4% vs. 75.6%) in external validation. We further built neural network models on single-dose subsets to invest whether the subsets samples were sufficient and whether the selected factors were appropriate. The training set sizes were 1340 and 1478 for the low and high dose subsets; the corresponding ideal prediction percentages were 70.2% and 75.1%. The training set size for the intermediate dose varied and was 1553, 6214, and 12,429; the corresponding ideal prediction percentages were 95.6, 95.1%, and 95.3%. Our conclusion is that equal stratified sampling can be a considerable alternative approach in training data construction to build drug dosing models in the clinic.