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.

METHODS: Four validation groups were extracted from a longitudinal community-based study dataset of 12,573 participants aged ≥18 years to validate the Framingham Risk Score (FRS), Systematic COronary Risk Evaluation 2 (SCORE2), Revised Pooled Cohort Equations (RPCE), and World Health Organization cardiovascular disease (WHO CVD) models. Two measures of validation are examined: discrimination and calibration. Outcome of interest was 10-year risk of CVD events (fatal and non-fatal). SCORE2 and RPCE performances were compared to SCORE and PCE, respectively.

FINDINGS: FRS (AUC = 0.750) and RPCE (AUC = 0.752) showed good discrimination in CVD risk prediction. Although FRS and RPCE have poor calibration, FRS demonstrates smaller discordance for FRS vs. RPCE (298% vs. 733% in men, 146% vs. 391% in women). Other models had reasonable discrimination (AUC = 0.706-0.732). Only SCORE2-Low, -Moderate and -High (aged <50) had good calibration (X2 goodness-of-fit, P-value = 0.514, 0.189, 0.129, respectively). SCORE2 and RPCE showed improvements compared to SCORE (AUC = 0.755 vs. 0.747, P-value <0.001) and PCE (AUC = 0.752 vs. 0.546, P-value <0.001), respectively. Almost all risk models overestimated 10-year CVD risk by 3%-1430%.

INTERPRETATION: In Malaysians, RPCE are evaluated be the most clinically useful to predict CVD risk. Additionally, SCORE2 and RPCE outperformed SCORE and PCE, respectively.

MATERIALS AND METHODS: A literature search was carried out to gather eligible studies from the following widely sourced electronic databases such as Scopus, PubMed and Google Scholar using the combination of the following keywords: AD, MRS, brain metabolites, deep learning (DL), machine learning (ML) and artificial intelligence (AI); having the aim of taking the readers through the advancements in the usage of MRS analysis and related AI applications for the detection of AD.

RESULTS: We elaborate on the MRS data acquisition, processing, analysis, and interpretation techniques. Recommendation is made for MRS parameters that can obtain the best quality spectrum for fingerprinting the brain metabolomics composition in AD. Furthermore, we summarise ML and DL techniques that have been utilised to estimate the uncertainty in the machine-predicted metabolite content, as well as streamline the process of displaying results of metabolites derangement that occurs as part of ageing.

METHODS: Geometric morphometric (GM) analysis of mandibles from 400 dental panoramic tomography (DPT) specimens was conducted. The MorphoJ program was used to perform generalized Procrustes analysis (GPA), Procrustes ANOVA, principal component analysis (PCA), discriminant function analysis (DFA), and canonical variate analysis (CVA). In the tpsDig2 program, the 27 landmarks were applied to the DPT radiographs. Variations in mandibular size and form were categorized into four age groups: group 1 (15-24 years), group 2 (25-34 years), group 3 (35-44 years), and group 4 (45-54 years).

METHODS: External root resorption was simulated on 88 extracted premolar teeth using tungsten bur in different depths (0.5 mm, 1 mm, and 2 mm). All teeth were scanned using a Cone beam CT (Carestream Dental, Atlanta, GA). Afterward, a training (70%), validation (10%), and test (20%) dataset were established. The performance of four DLMs including Random Forest (RF) + Visual Geometry Group 16 (VGG), RF + EfficienNetB4 (EFNET), Support Vector Machine (SVM) + VGG, and SVM + EFNET) and four hybrid models (DLM + FST: (i) FS + RF + VGG, (ii) FS + RF + EFNET, (iii) FS + SVM + VGG and (iv) FS + SVM + EFNET) was compared. Five performance parameters were assessed: classification accuracy, F1-score, precision, specificity, and error rate. FST algorithms (Boruta and Recursive Feature Selection) were combined with the DLMs to assess their performance.

RESULTS: RF + VGG exhibited the highest performance in identifying ERR, followed by the other tested models. Similarly, FST combined with RF + VGG outperformed other models with classification accuracy, F1-score, precision, and specificity of 81.9%, weighted accuracy of 83%, and area under the curve (AUC) of 96%. Kruskal Wallis test revealed a significant difference (p = 0.008) in the prediction accuracy among the eight DLMs.

MATERIALS AND METHODS: Two thousand seven hundred students were randomly selected by proportional stratified sampling. Analyses on 1,736 non-smoking students revealed that prevalence of adolescents susceptible to smoking was 16.3%.

RESULTS: Male gender (aOR=2.05, 95%CI= 1.23-3.39), poor academic achievement (aOR 1.60, 95%CI 1.05-2.44), ever-smoker (aOR 2.17, 95%CI 1.37-3.44) and having a smoking friend (aOR 1.76, 95%CI 1.10-2.83) were associated with susceptibility to smoking, while having the perception that smoking prohibition in school was strictly enforced (aOR 0.55, 95%CI 0.32-0.94), and had never seen friends smoking in a school compound (aOR 0.59, 95%CI 0.37-0.96) were considered protective factors