Medicina

Background and Objectives: Throughout the return-to-play process after anterior cruciate ligament reconstruction (ACLR), clearance criteria and limb symmetry indices (LSI) play an important role in clinical decision-making by helping evaluate patient readiness and informing safe activity progressions, with the goal of reducing re-injury risk. How clearance criteria are implemented in research studies to evaluate patient readiness, specifically in force plate jumping studies, is currently unknown. This scoping review was a focused examination of clearance criteria and limb symmetry indices in studies performing force plate-based jumping assessments with ACLR patients. The research questions guiding this scoping review were as follows: (1) What clearance criteria are reported in studies involving primary ACLR patients who participate in jumping assessments on force plates? (2) What LSI are reported in force plate studies, and what level of symmetry is deemed acceptable to allow for safe participation of ACLR patients who participate in jumping assessments of force plates? Materials and Methods: Nine databases were searched on 7 or 8 September 2024 for three concepts: ACLR, force plates, and movement properties. Inclusion criteria were as follows: (a) primary ACLR patients at least 6 months post-surgery; (b) performing a countermovement or drop jump; (c) collecting at least one kinetic parameter using a force plate. Clearance criteria was operationally defined as a time from surgery boundary, functional or performance-based testing criteria, medical evaluation, or completion/participation in a rehabilitation program. Results: Thirty-five studies were included. Time from surgery was the most frequently reported clearance criteria (26/35; 74.3%), followed by medical evaluation (18/35; 51.4%), and completion of rehabilitation (10/35; 28.6%). Use of LSI as clearance criteria was limited (5/35; 14.3%). Minimum required LSI ranged from 85 to 90% in quadriceps strength and hop testing. Conclusions: Clearance criteria varied by jump type and post-surgical time frame when the participant was tested. Standardized rehabilitation was common prior to 2 years post-surgery, whereas medical clearance was common after 2 years post-surgery. Single leg jumps typically required 2–3 clearance criteria, whereas double leg jumps required 1–2 clearance criteria. Limb symmetry indices were used in combination with two other clearance criteria in studies with single-leg countermovement or drop jumps. Improvements in clearance criteria and adverse event reporting may help improve patient safety and interpretation of findings across studies.

Background and Objectives: Diabetes mellitus represents one of the most prevalent chronic metabolic disorders worldwide, necessitating precise insulin dose management to prevent both acute and long-term complications. The optimization of insulin dosing remains a significant clinical challenge, as inappropriate dosing can lead to hypoglycemia or hyperglycemia, each carrying substantial morbidity risks. Machine learning approaches have emerged as promising tools for developing clinical decision support systems; however, their practical implementation requires both high predictive accuracy and model interpretability. This study aimed to develop and evaluate an explainable machine learning framework for predicting insulin dose adjustments in diabetic patients. We sought to compare multiple ensemble learning approaches and identify the optimal model configuration that balances predictive performance with clinical interpretability through comprehensive SHAP and LIME analyses. Materials and Methods: A comprehensive dataset comprising 10,000 patient records with 12 clinical and demographic features was utilized. We implemented and compared nine machine learning models, including gradient boosting variants (XGBoost, LightGBM, CatBoost, GradientBoosting), AdaBoost, and four ensemble strategies (Voting, Stacking, Blending, and Meta-Learning). Model interpretability was achieved through SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) analyses. Performance was evaluated using accuracy, weighted F1-score, area under the receiver operating characteristic curve (AUC-ROC), precision-recall AUC (PR-AUC), sensitivity, specificity, and cross-entropy loss. Results: The Meta-Learning Ensemble achieved superior performance across all evaluation metrics, attaining an accuracy of 81.35%, weighted F1-score of 0.8121, macro-averaged AUC-ROC of 0.9637, and PR-AUC of 0.9317. The model demonstrated exceptional sensitivity (86.61%) and specificity (91.79%), with particularly high performance in detecting dose reduction requirements (100% sensitivity for the ‘down’ class). SHAP analysis revealed insulin sensitivity, previous medications, sleep hours, weight, and body mass index as the most influential predictors across different insulin adjustment categories. The meta-model feature importance analysis indicated that LightGBM probability estimates contributed most significantly to the ensemble predictions. Conclusions: The proposed explainable Meta-Learning Ensemble framework demonstrates robust predictive capability for insulin dose adjustment recommendations while maintaining clinical interpretability. The integration of SHAP-based explanations facilitates clinician understanding of model predictions, supporting transparent and informed decision-making in diabetes management. This approach represents a significant advancement toward the clinical implementation of artificial intelligence in personalized insulin therapy.

Background and Objectives: This study aimed to evaluate the pre- and post-treatment changes in ICEB and ICEBc score markers of cardiac electrical balance in patients presenting to the emergency department with hypertensive urgency and to investigate their relationship with short-term clinical outcomes. Materials and Methods: In this retrospective study, 50 patients who presented to a tertiary university hospital emergency department between 1 January 2021 and 31 December 2024 with a diagnosis of hypertensive urgency and had pre- and post-treatment 12-lead ECGs were analysed. ICEB (QT/QRS) and ICEBc (QTc/QRS) scores were calculated manually. Patients were categorized as discharged or hospitalized. Within-group and between-group comparisons of the scores were performed. Results: Of the patients, 66% were female, and the mean age was 60.4 ± 14.5 years. A statistically significant increase in ICEB scores was observed after treatment in discharged patients (p = 0.006), whereas ICEBc scores showed no significant change. In the hospitalized group, no significant difference was found in either ICEB or ICEBc scores. Additionally, between-group comparisons revealed no significant differences in ICEBc values. Conclusions: The ICEB score may serve as a dynamic marker reflecting the electrophysiological response to antihypertensive treatment. The observed increase in ICEB after treatment may indicate the restoration of electrical stability. In contrast, ICEBc appeared to have limited predictive value in this clinical context. Further prospective studies with larger populations are needed to determine the clinical utility of ICEB in the management of hypertensive crises.