METHODS: This is a longitudinal cohort study. Psoriatic arthritis (PsA) patients with liver enzymes abnormalities were identified. Our control group consisted of PsA patient from the same cohort who had no history of liver abnormalities. Factors associated with liver abnormalities were identified using univariate and multivariate analysis.

RESULTS: A total of 247 of PsA patients were included and out of those, 99 developed liver enzymes abnormalities. The mean age of the patients was 56 years old (±13.5) with 56.1% female and 39.4% Indian descendants. The univariate logistic regression demonstrated that disease duration of PsA (OR=1.06, 95% CI=1.01 - 1.10, p=0.012), diabetes mellitus (OR=2.16, 95% CI=1.26 - 3.70, 0.005) and non-alcoholic fatty liver disease (NAFLD) (OR=3.90, 95% CI = 1.44 - 10.53, p=0.007) were associated with abnormal liver function in PsA patients. No association was found with both conventional synthetic disease-modifying antirheumatic drugs or biologics.

METHODS: This study analyzed death records from January 2017 to June 2022, sourced from Malaysia's Health Informatics Centre, coded into ICD-10. Data anonymization adhered to ethical standards, with 387,650 death registrations included after quality checks. The dataset, limited to three-digit ICD-10 codes, underwent cleaning and an 80:20 training-testing split. Preprocessing involved HTML tag removal and tokenization. ML approaches, including BERT (Bidirectional Encoder Representations from Transformers), Gzip+KNN (K-Nearest Neighbors), XGBoost (Extreme Gradient Boosting), TensorFlow, SVM (Support Vector Machine), and Naive Bayes, were evaluated for automated ICD-10 coding. Models were fine-tuned and assessed across accuracy, F1-score, precision, recall, specificity, and precision-recall curves using Amazon SageMaker (Amazon Web Services, Seattle, WA). Sensitivity analysis addressed unbalanced data scenarios, enhancing model robustness.

RESULTS: In assessing ICD-10 coding with ML, Gzip+KNN had the longest training time at 10 hours, with BERT leading in memory use. BERT performed best for the F1-score (0.71) and accuracy (0.82), closely followed by Gzip+KNN. TensorFlow excelled in recall, whereas SVM had the highest specificity but lower overall performance. XGBoost was notably less effective across metrics. Precision-recall analysis showed Gzip+KNN's superiority. On an unbalanced dataset, BERT and Gzip+KNN demonstrated consistent accuracy.