SHAP based predictive modeling for 1 year all-cause readmission risk in elderly heart failure patients: feature selection and model interpretation.

Heart failure (HF) is a significant global public health concern with a high readmission rate, posing a serious threat to the health of the elderly population. While several studies have used machine learning (ML) to develop all-cause readmission risk prediction models for elderly patients with HF, few have integrated ML-selected features with those chosen by human experts to assess HF patients readmission. A retrospective analysis of 8396 elderly HF patients hospitalized at the Affiliated Hospital of North Sichuan Medical College from January 1, 2018 to December 31, 2021 was conducted. Variables selected by XGBoost, LASSO regression, and random forest constituted the machine group, while the human expert group comprised variables chosen by two experienced cardiovascular professors. The variables selected by both groups were combined to form a human-machine collaboration group. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC). The SHapley Additive exPlanations (SHAP) method was used to elucidate the importance of each predictive feature, explain the impact of individual features on the model, and provide visual representation. A total of 73 features were included for model development. The human-machine collaboration model, utilizing CatBoost, achieved an AUC of 0.83617, an F1-score of 0.73521, and a Brier score of 0.16536 on the validation set. This model demonstrated superior predictive performance compared to those created solely by human experts or machine. The SHAP plot was then used to visually display the feature analysis of the human-machine collaboration model, revealing HGB, NT-proBNP, smoking history, NYHA classification, and LVEF as the 5 most important features. This study indicate that the human-machine collaboration model outperforms those relying solely on human expert selection or machine algorithm at predicting all-cause readmission in elderly HF patients. The application of the SHAP method enhanced the interpretability of the model outcomes, aiding clinicians in accurately pinpointing risk factors associated with HF readmission. This advancement enables the formulation of tailored treatment strategies, offering a more personalized approach to patient care.

A Review of Artificial Intelligence in the Rupture Risk Assessment of Intracranial Aneurysms: Applications and Challenges.

Intracranial aneurysms (IAs) are highly prevalent in the population, and their rupture poses a significant risk of death or disability. However, the treatment of aneurysms, whether through interventional embolization or craniotomy clipping surgery, is not always safe and carries a certain proportion of morbidity and mortality. Therefore, early detection and prompt intervention of IAs with a high risk of rupture is of notable clinical significance. Moreover, accurately predicting aneurysms that are likely to remain stable can help avoid the risks and costs of over-intervention, which also has considerable social significance. Recent advances in artificial intelligence (AI) technology offer promising strategies to assist clinical trials. This review will discuss the state-of-the-art AI applications for assessing the rupture risk of IAs, with a focus on achievements, challenges, and potential opportunities.

Modified Valsalva maneuver after burr-hole drainage of chronic subdural hematomas: A single-center cohort study.

Background: Previous studies on the management of chronic subdural hematoma (cSDH) mainly focused on the risk of postoperative recurrence and measures to prevent it. In this study, we propose the use of a non-invasive postoperative treatment method, the modified Valsalva maneuver (MVM), as a means of reducing the recurrence of cSDH. This study aims to clarify the effects of MVM on functional outcomes and recurrence rates. Methods: A prospective study was conducted at the Department of Neurosurgery, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology from November 2016 to December 2020. The study included 285 adult patients who underwent burr-hole drainage for the treatment of cSDH and received subdural drains. These patients were divided into two groups: the MVM group (n = 117) and the control group (n = 98). In the MVM group, patients received treatment with a customized MVM device for at least 10 times per hour, 12 h per day. The study's primary endpoint was the recurrence rate of SDH, while functional outcomes and morbidity 3 months after surgery were the secondary outcomes. Results: In the current study, 9 out of 117 patients (7.7%) in the MVM group experienced a recurrence of SDH, while 19 out of 98 patients (19.4%, p < 0.05) in the HC group experienced a recurrence of SDH. Additionally, the infection rate of diseases such as pneumonia (1.7%) was significantly lower in the MVM group compared to the HC group (9.2%, p < 0.001, odds ratio (OR = 0.1). After 3 months of the surgery, 109 out of 117 patients (93.2%) in the MVM group achieved a favorable prognosis, compared to 80 out of 98 patients (81.6%) in the HC group (p = 0.008, with an OR of 2.9). Additionally, infection rate (with an OR of 0.2) and age (with an OR of 0.9) are independent predictors of a favorable prognosis at the follow-up stage. Conclusions: The use of MVM in the postoperative management of cSDHs has been shown to be safe and effective, resulting in reduced rates of cSDH recurrence and infection following burr-hole drainage. These findings suggest that MVM treatment may lead to a more favorable prognosis at the follow-up stage.

MarkovHC: Markov hierarchical clustering for the topological structure of high-dimensional single-cell omics data with transition pathway and critical point detection.

Clustering cells and depicting the lineage relationship among cell subpopulations are fundamental tasks in single-cell omics studies. However, existing analytical methods face challenges in stratifying cells, tracking cellular trajectories, and identifying critical points of cell transitions. To overcome these, we proposed a novel Markov hierarchical clustering algorithm (MarkovHC), a topological clustering method that leverages the metastability of exponentially perturbed Markov chains for systematically reconstructing the cellular landscape. Briefly, MarkovHC starts with local connectivity and density derived from the input and outputs a hierarchical structure for the data. We firstly benchmarked MarkovHC on five simulated datasets and ten public single-cell datasets with known labels. Then, we used MarkovHC to investigate the multi-level architectures and transition processes during human embryo preimplantation development and gastric cancer procession. MarkovHC found heterogeneous cell states and sub-cell types in lineage-specific progenitor cells and revealed the most possible transition paths and critical points in the cellular processes. These results demonstrated MarkovHC's effectiveness in facilitating the stratification of cells, identification of cell populations, and characterization of cellular trajectories and critical points.

A new low-profile anatomic locking plate for fixation of comminuted, displaced greater tuberosity fractures of the proximal humerus.

BACKGROUND: Although various implants exist for the fixation of isolated greater tuberosity fractures, few implants are specifically designed for such fractures. The purpose of this study was to investigate the clinical and radiologic outcomes of open reduction-internal fixation with a low-profile anatomic locking plate for comminuted greater tuberosity fractures of the proximal humerus. METHODS: From November 2012 to February 2018, 24 patients with displaced and comminuted isolated greater tuberosity fractures were treated with the new low-profile anatomic locking plate. To determine clinical outcomes, we evaluated active range of motion; the visual analog scale pain score; the Constant-Murley score; the Disabilities of the Arm, Shoulder and Hand score; radiographs; and complications. RESULTS: In all cases, a mean follow-up period of 29.3 months (range, 18-48 months) was completed. All patients achieved bone union with a mean healing time of 11.3 weeks (range, 8-16 weeks). The mean Constant-Murley score was 91.1 points (range, 69-100 points), with a rate of good to excellent results of 95.8%. The average Disabilities of the Arm, Shoulder and Hand score was 9.9 points (range, 2-25 points), and the mean visual analog scale pain score was 1.1 points (range, 0-4 points). Mean active forward flexion, abduction, external rotation, and internal rotation (level) were 157°, 152°, and 40°, and T11, respectively. Postoperatively, 1 patient had persistent shoulder stiffness, and 1 patient had recurrence of shoulder dislocation because of a falling injury during badminton. No serious complications such as subacromial impingement, malunion, nonunion, loss of reduction, or implant failure occurred. CONCLUSIONS: The new low-profile anatomic locking plate was useful for the treatment of comminuted isolated greater tuberosity fractures as it provided reliable stability and satisfactory radiographic and functional results. The described technique is a simple and effective method and provides a new reliable option for the treatment of isolated greater tuberosity fractures.

Long-term olfactory dysfunction after single-nostril endoscopic transnasal transsphenoidal pituitary adenoma surgery.

BACKGROUND: Over the past decade, the endoscopic transnasal transsphenoidal approach for pituitary adenomas has been widely adopted among neurosurgeons. However, olfactory disturbances have been observed after this procedure, and few studies on long-term (>6 mo) olfactory disturbance after endoscopic transnasal transsphenoidal pituitary adenoma surgery have been conducted. Although we perform minimally invasive endoscopic surgery, some patients continue to experience hyposmia, with some even experience long-term hyposmia. This impairment results in a considerable loss in quality of life. We present a series of patients who underwent minimally invasive single-nostril TSS for pituitary adenoma, including evaluation of their olfactory function. We further investigated the related risk factors for long-term olfactory dysfunction. METHODS: One hundred sixty-one consecutive patients who met the study criteria underwent the single-nostril endoscopic transsphenoidal approach by the senior author. The Smell Diskettes Olfaction Test was used to evaluate olfactory function. RESULTS: Postoperative olfactory disturbance in patients treated with endoscopic transnasal TSS is frequent. Of the study population, 67.1% of the patients were hyposmic or anosmic and 14.9% had long-term olfactory dysfunction. We also performed multivariate logistic regression analysis to compare the characteristics of patients with long-term olfactory dysfunction. Nasal symptoms (odds ratio [OR], 6.77) and smoking (OR, 14.77) were associated with long-term olfactory dysfunction after transnasal TSS. CONCLUSIONS: Significant disturbances in olfactory performance occur after single-nostril transnasal TSS for pituitary adenoma. Furthermore, preoperative nasal disease and smoking appear to be risk factors for long-term olfactory dysfunction. Physicians should address clinical findings related to olfactory function and provide appropriate care.