BackgroundStroke is an acute disorder and dysfunction of the focal neurological system that has long been recognized as one of the leading causes of death and severe disability in most regions globally. This study aimed to supplement and exploit multiple comorbidities, laboratory tests and demographic factors to more accurately predict death related to stroke, and furthermore, to make inferences about the heterogeneity of treatment in stroke patients to guide better treatment planning.MethodsWe extracted data from the Medical Information Mart from the Intensive Care (MIMIC)-IV database. We compared the distribution of the demographic factors between the control and death groups. Subsequently, we also developed machine learning (ML) models to predict mortality among stroke patients. Furthermore, we used meta-learner to recognize the heterogeneity effects of warfarin and human albumin. We comprehensively evaluated and interpreted these models using Shapley Additive Explanation (SHAP) analysis.ResultsWe included 7,483 patients with MIMIC-IV in this study. Of these, 1,414 (18.9%) patients died during hospitalization or 30 days after discharge. We found that the distributions of age, marital status, insurance type, and BMI differed between the two groups. Our machine learning model achieved the highest level of accuracy to date in predicting mortality in stroke patients. We also observed that patients who were consistent with the model determination had significantly better survival outcomes than the inconsistent population and were better than the overall treatment group.ConclusionWe used several highly interpretive machine learning models to predict stroke prognosis with the highest accuracy to date and to identify heterogeneous treatment effects of warfarin and human albumin in stroke patients. Our interpretation of the model yielded a number of findings that are consistent with clinical knowledge and warrant further study and verification.

No abstract

At present, the existing vegetable grafting machines are cutting and grafting operations for a single plant or row. They need to manually or automatically grab the seedlings, and their grafting efficiency is not significantly higher than that of manual grafting techniques. In this paper, grafted melon seedlings were the subject of the research. Based on the splice-grafting method, we designed a clamping and positioning device for full-tray seedlings and a mechanical device to realize full-tray grafting by locating the vegetable seedlings and completing the full-tray grafting process without damaging the seedlings. The results show that the cutting success rate for pumpkin rootstock and for melon scion reached 100% and 92%, respectively. The lengths of the long axis of the section of the rootstock and the scion were 6.2–7.7 mm, and the cutting angle was maintained at 30 degrees, thereby able to meet the requirements of the grafting method. The average grafting efficiency for the rootstock and scion were 2134 plants/h, and the average grafting success rate was 67%.

BackgroundAcute kidney injury (AKI) is a common complication associated with significant morbidity and mortality in high-energy trauma patients. Given the poor efficacy of interventions after AKI development, it is important to predict AKI before its diagnosis. Therefore, this study aimed to develop models using machine learning algorithms to predict the risk of AKI in patients with femoral neck fractures.MethodsWe developed machine-learning models using the Medical Information Mart from Intensive Care (MIMIC)-IV database. AKI was predicted using 10 predictive models in three-time windows, 24, 48, and 72 h. Three optimal models were selected according to the accuracy and area under the receiver operating characteristic curve (AUROC), and the hyperparameters were adjusted using a random search algorithm. The Shapley additive explanation (SHAP) analysis was used to determine the impact and importance of each feature on the prediction. Compact models were developed using important features chosen based on their SHAP values and clinical availability. Finally, we evaluated the models using metrics such as accuracy, precision, AUROC, recall, F1 scores, and kappa values on the test set after hyperparameter tuning.ResultsA total of 1,596 patients in MIMIC-IV were included in the final cohort, and 402 (25%) patients developed AKI after surgery. The light gradient boosting machine (LightGBM) model showed the best overall performance for predicting AKI before 24, 48, and 72 h. AUROCs were 0.929, 0.862, and 0.904. The SHAP value was used to interpret the prediction models. Renal function markers and perioperative blood transfusions are the most critical features for predicting AKI. In compact models, LightGBM still performs the best. AUROCs were 0.930, 0.859, and 0.901.ConclusionsIn our analysis, we discovered that LightGBM had the best metrics among all algorithms used. Our study identified the LightGBM as a solid first-choice algorithm for early AKI prediction in patients after femoral neck fracture surgery.

BackgroundConsidering the huge population in China, the available mental health resources are inadequate. Thus, our study aimed to evaluate whether mental questionnaires, serving as auxiliary diagnostic tools, have efficient diagnostic ability in outpatient psychiatric services.MethodsWe conducted a retrospective study of Chinese psychiatric outpatients. Altogether 1,182, 5,069, and 4,958 records of Symptom Checklist-90 (SCL-90), Hamilton Anxiety Rating Scale (HAM-A), and Hamilton Depression Rating Scale (HAM-D), respectively, were collected from March 2021 to July 2022. The Mann–Whitney U test was applied to subscale scores and total scores of SCL-90, HAM-A, and HAM-D between the two sexes (male and female groups), different age groups, and four diagnostic groups (anxiety disorder, depressive disorder, bipolar disorder, and schizophrenia). Kendall's tau coefficient analysis and machine learning were also conducted in the diagnostic groups.ResultsWe found significant differences in most subscale scores for both age and gender groups. Using the Mann–Whitney U test and Kendall's tau coefficient analysis, we found that there were no statistically significant differences in diseases in total scale scores and nearly all subscale scores. The results of machine learning (ML) showed that for HAM-A, anxiety had a small degree of differentiation with an AUC of 0.56, while other diseases had an AUC close to 0.50. As for HAM-D, bipolar disorder was slightly distinguishable with an AUC of 0.60, while the AUC of other diseases was lower than 0.50. In SCL-90, all diseases had a similar AUC; among them, bipolar disorder had the lowest score, schizophrenia had the highest score, while anxiety and depression both had an AUC of approximately 0.56.ConclusionThis study is the first to conduct wide and comprehensive analyses on the use of these three scales in Chinese outpatient clinics with both traditional statistical approaches and novel machine learning methods. Our results indicated that the univariate subscale scores did not have statistical significance among our four diagnostic groups, which highlights the limit of their practical use by doctors in identifying different mental diseases in Chinese outpatient psychiatric services.