OBJECTIVE: To employ machine learning (ML) and stacked ensemble learning (EL) methods in predicting short- and long-term mortality in Asian patients diagnosed with NSTEMI/UA and to identify the associated features, subsequently evaluating these findings against established risk scores.

METHODS: We analyzed data from the National Cardiovascular Disease Database for Malaysia (2006-2019), representing a diverse NSTEMI/UA Asian cohort. Algorithm development utilized in-hospital records of 9,518 patients, 30-day data from 7,133 patients, and 1-year data from 7,031 patients. This study utilized 39 features, including demographic, cardiovascular risk, medication, and clinical features. In the development of the stacked EL model, four base learner algorithms were employed: eXtreme Gradient Boosting (XGB), Support Vector Machine (SVM), Naive Bayes (NB), and Random Forest (RF), with the Generalized Linear Model (GLM) serving as the meta learner. Significant features were chosen and ranked using ML feature importance with backward elimination. The predictive performance of the algorithms was assessed using the area under the curve (AUC) as a metric. Validation of the algorithms was conducted against the TIMI for NSTEMI/UA using a separate validation dataset, and the net reclassification index (NRI) was subsequently determined.

RESULTS: Using both complete and reduced features, the algorithm performance achieved an AUC ranging from 0.73 to 0.89. The top-performing ML algorithm consistently surpassed the TIMI risk score for in-hospital, 30-day, and 1-year predictions (with AUC values of 0.88, 0.88, and 0.81, respectively, all p < 0.001), while the TIMI scores registered significantly lower at 0.55, 0.54, and 0.61. This suggests the TIMI score tends to underestimate patient mortality risk. The net reclassification index (NRI) of the best ML algorithm for NSTEMI/UA patients across these periods yielded an NRI between 40-60% (p < 0.001) relative to the TIMI NSTEMI/UA risk score. Key features identified for both short- and long-term mortality included age, Killip class, heart rate, and Low-Molecular-Weight Heparin (LMWH) administration.

METHODS: This retrospective cohort study included 962 patients admitted to two hospitals in Kuwait with a confirmed diagnosis of COVID-19. Cumulative all-cause mortality rate was the primary outcome.

RESULTS: A total of 302 patients (males, 196 [64.9%]; mean age, 57.2 ± 14.6 years; mean body mass index, 29.8 ± 6.5 kg/m2) received anticoagulation therapy. Patients receiving anticoagulation treatment tended to have pneumonia (n = 275 [91.1%]) or acute respiratory distress syndrome (n = 106 [35.1%]), and high D-dimer levels (median [interquartile range]: 608 [523;707] ng/mL). The mortality rate in this group was high (n = 63 [20.9%]). Multivariable logistic regression, the Cox proportional hazards, and Kaplan-Meier models revealed that the use of therapeutic anticoagulation agents affected the risk of all-cause cumulative mortality.

SETTING: Departments of Ophthalmology, University of Malaya, Kuala Lumpur, Malaysia, and Tan Tock Seng Hospital, Singapore.

METHODS: In a randomized, double-blind study performed at two centers, 51 patients received an HSM PMMA lens and 48, an unmodified PMMA IOL. Cell and pigment deposits were evaluated by slitlamp at 1 to 6 days, 2 to 3 weeks, and 3 to 6 months postoperatively.

RESULTS: Significantly more eyes with unmodified IOLs had inflammatory cell deposits than those with HSM IOLs at 3 to 6 months (P < .001) and 12 to 14 months (P = .018) postoperatively. The HSM group also had significantly fewer cell deposits per patient at these two follow-ups. Significantly more eyes in the non-HSM group had pigment deposits 3 to 6 months after surgery (P = .049). One year postoperatively, about 85% of patients in both groups had a best corrected visual acuity of 0.5 or better.

METHODS: A total of 15 PD bags (3 bags for each type of PD solution) containing meropenem and heparin and 24 PD bags (3 bags for each type of PD solution) containing PIP/TZB and heparin were prepared and stored at 4°C for 168 hours. The same bags were stored at 25°C for 3 hours followed by 10 hours at 37°C. An aliquot withdrawn before storage and at defined time points was analyzed for the concentration of meropenem, PIP, TZB, and heparin using high-performance liquid chromatography. Samples were also analysed for particle content, pH and color change, and the anticoagulant activity of heparin.

RESULTS: Meropenem and heparin retained more than 90% of their initial concentration in 4 out of 5 types of PD solutions when stored at 4°C for 168 hours, followed by storage at 25°C for 3 hours and then at 37°C for 10 hours. Piperacillin/tazobactam and heparin were found to be stable in all 8 types of PD solutions when stored under the same conditions. Heparin retained more than 98% of its initial anticoagulant activity throughout the study period. No evidence of particle formation, color change, or pH change was observed at any time under the storage conditions employed in the study.