OBJECTIVE: To derive a single algorithm using deep learning and machine learning for the prediction and identification of factors associated with in-hospital mortality in Asian patients with ACS and to compare performance to a conventional risk score.
METHODS: The Malaysian National Cardiovascular Disease Database (NCVD) registry, is a multi-ethnic, heterogeneous database spanning from 2006-2017. It was used for in-hospital mortality model development with 54 variables considered for patients with STEMI and Non-STEMI (NSTEMI). Mortality prediction was analyzed using feature selection methods with machine learning algorithms. Deep learning algorithm using features selected from machine learning was compared to Thrombolysis in Myocardial Infarction (TIMI) score.
RESULTS: A total of 68528 patients were included in the analysis. Deep learning models constructed using all features and selected features from machine learning resulted in higher performance than machine learning and TIMI risk score (p < 0.0001 for all). The best model in this study is the combination of features selected from the SVM algorithm with a deep learning classifier. The DL (SVM selected var) algorithm demonstrated the highest predictive performance with the least number of predictors (14 predictors) for in-hospital prediction of STEMI patients (AUC = 0.96, 95% CI: 0.95-0.96). In NSTEMI in-hospital prediction, DL (RF selected var) (AUC = 0.96, 95% CI: 0.95-0.96, reported slightly higher AUC compared to DL (SVM selected var) (AUC = 0.95, 95% CI: 0.94-0.95). There was no significant difference between DL (SVM selected var) algorithm and DL (RF selected var) algorithm (p = 0.5). When compared to the DL (SVM selected var) model, the TIMI score underestimates patients' risk of mortality. TIMI risk score correctly identified 13.08% of the high-risk patient's non-survival vs 24.7% for the DL model and 4.65% vs 19.7% of the high-risk patient's non-survival for NSTEMI. Age, heart rate, Killip class, cardiac catheterization, oral hypoglycemia use and antiarrhythmic agent were found to be common predictors of in-hospital mortality across all ML feature selection models in this study. The final algorithm was converted into an online tool with a database for continuous data archiving for prospective validation.
CONCLUSIONS: ACS patients were better classified using a combination of machine learning and deep learning in a multi-ethnic Asian population when compared to TIMI scoring. Machine learning enables the identification of distinct factors in individual Asian populations to improve mortality prediction. Continuous testing and validation will allow for better risk stratification in the future, potentially altering management and outcomes.
METHODS: The retrospective study was conducted from 2006 to 2008. Data on sociodemographic along with histopathological results were collected. The signs and symptoms were also recorded from TB registers, treatment cards, and TB medical personal files using the standard data collection tool. Among multiple variables, the significant factors identified by univariate analysis were included in the multivariate logistic regression to estimate the odds ratios with the 95% confidence intervals. The statistically significant P value was considered <0.05.
RESULTS: There were 348 (57%) males, and on the other hand, 262 (43%) females which shows almost equal incidence rate of lymphadenitis in both genders. The age group was observed from 2 to 83 years old. Therefore, the age group between 26 and 35 years showed 194 (31.8%) patients diagnosed with lymphadenitis and followed by 16-25 years (21%). The mean age was found as 34.3 ± 14.6 years were majorly reported with positive diagnosis. One hundred and ninety-six (32.1%) Malay population were found with tuberculous lymphadenitis followed by the Chinese population of 148 (24.3%). The other prominent races were Pilipino, Indonesians, and other expatriates. Geographically, patients were from 386 (63.3%) urban population were found positive for lymphadenitis and over 224 (36.7%) population of the rural region. The treatment outcome was observed 444 (72.8%) with successful treatment. The World Health Organization states the types of treatment failures, and accordingly, 85 (13.9%) patients were continued with the therapy that can be due to noncompliance or relapse of TB. Among the unsuccessful outcomes, 194 patients of age group 26-35 years, 65 (33.5%) were reported and 38 (29.7%) patients out of 128 between ages of 16-25 years. Blood test results showed erythrocyte sedimentation rate >10 in 280 (45.9%) patients. Therefore, among 280, there were 115 (41.1%) patients were found to have unsuccessful treatment showing very strong association with P < 0.001.
CONCLUSION: The finding signifies that effect of weight loss on poor treatment outcomes' and active screening measures for patients with comorbidities are therefore recommended in patients with tuberculous lymphadenitis along with improvements in the diagnosis and early management of comorbidities complications. As young age group was found to have poor or unsuccessful treatment outcomes and required aggressive strategy together with educating patients can further increase the treatment success rate.
METHODS: A phenomenological qualitative study was conducted from November 2020 to June 2021. Thirteen respondents were recruited from two public rehabilitation centers in Kota Bharu, Kelantan, Malaysia. In-depth interviews were conducted. A comprehensive representation of perspectives from the respondents was achieved through purposive sampling. The interviews were conducted in the Kelantanese dialect, recorded, transcribed, and analyzed by using thematic analysis.
RESULTS: Thirteen participants were involved in the interviews. All of them agreed with the need for a mobile application in stroke management. They believed the future stroke application will help them to seek information, continuous stroke home care, and help in the welfare of caregivers and stroke patients.
CONCLUSIONS: The current study revealed two themes with respective subthemes that were identified, namely, self-seeking for information and reasons for using a stroke mobile application in the future. This application helps in reducing healthcare costs, enhancing the rehabilitation process, facilitating patient engagement in decision making, and the continuous monitoring of patient health.