PURPOSE: We aimed to examine the role of age-dependent intervention thresholds (ITs) applied to the Fracture Risk Assessment (FRAX) tool in therapeutic decision making for osteoporosis in the Malaysian population.
METHODS: Data were collated from 1380 treatment-naïve postmenopausal women aged 40-85 years who underwent bone mineral density (BMD) measurements for clinical reasons. Age-dependent ITs, for both major osteoporotic fracture (MOF) and hip fracture (HF), were calculated considering a woman with a BMI of 25 kg/m2, aged between 40 and 85years, with a prior fragility fracture, sans other clinical risk factors. Those with fracture probabilities equal to or above upper assessment thresholds (UATs) were considered to have high fracture risk. Those below the lower assessment thresholds (LATs) were considered to have low fracture risk.
RESULTS: The ITs of MOF and HF ranged from 0.7 to 18% and 0.2 to 8%, between 40 and 85years. The LATs of MOF ranged from 0.3 to 11%, while those of HF ranged from 0.1 to 5.2%. The UATs of MOF and HF were 0.8 to 21.6% and 0.2 to 9.6%, respectively. In this study, 24.8% women were in the high-risk category while 30.4% were in the low-risk category. Of the 44.8% (n=618) in the intermediate risk group, after recalculation of fracture risk with BMD input, 38.3% (237/618) were above the ITs while the rest (n=381, 61.7%) were below the ITs. Judged by the Youden Index, 11.5% MOF probability which was associated with a sensitivity of 0.62 and specificity of 0.83 and 4.0% HF probability associated with a sensitivity of 0.63 and a specificity 0.82 were found to be the most appropriate fixed ITs in this analysis.
CONCLUSION: Less than half of the study population (44.8%) required BMD for osteoporosis management when age-specific assessment thresholds were applied. Therefore, in more than half, therapeutic decisions can be made without BMD based on these assessment thresholds.
AREAS COVERED: We searched multiple databases, including PubMed, Web of Knowledge, Scopus, ACM, Embase, IEEE and Ingenta. We explored various evaluation aspects of MD and EMR to gain a better understanding of their complex integration. We reviewed numerous risk management and assessment frameworks related to MD and EMR security aspects and mitigation controls and then identified their common evaluation aspects. Our review indicated that previous evaluation frameworks assessed MD and EMR independently. To address this gap, we proposed an evaluation framework based on the sociotechnical dimensions of health information systems and risk assessment approaches for MDs to evaluate MDI-EMR integratively.
EXPERT OPINION: The emergence of MDI-EMR cyber threats requires appropriate evaluation tools to ensure the safe development and application of MDI-EMR. Consequently, our proposed framework will continue to evolve through subsequent validations and refinements. This process aims to establish its applicability in informing stakeholders of the safety level and assessing its effectiveness in mitigating risks for future improvements.
METHODS: A 2-year cross-sectional study was conducted to determine the prevalence and associated risk factors for infections among urban refugees in the Klang Valley, Malaysia. A total of 418 faecal samples were collected and examined by microscopy.
RESULTS: Faecal screening revealed moderate levels (32.3%) of infections in the community. Three nematode (Ascaris lumbricoides, Trichuris trichiura and hookworm) and three protozoan species (Entamoeba, Giardia and Cryptosporidium) were recorded, with the highest prevalence being A. lumbricoides (20.6%) followed by T. trichiura (10.3%), while other infections were <5%. Statistical analysis found that young males with less education were more likely to be infected with helminths. Additionally, living near waste disposal sites, the presence of stray animals, eating with bare hands, bare footedness, poor handwashing practices and no anthelmintic treatment constituted significant risk factors for helminth infections. Protozoan infections were linked to drinking tap water or from water dispensers and poor handwashing practices.
CONCLUSIONS: These findings emphasize the importance of health education in addition to introduction of biannual anthelmintic treatment to promote community health and well-being.
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.
CONCLUSIONS: In a broad multi-ethnic population, ML approaches outperformed conventional TIMI scoring in classifying patients with NSTEMI and UA. ML allows for the precise identification of unique characteristics within individual Asian populations, improving the accuracy of mortality predictions. Continuous development, testing, and validation of these ML algorithms holds the promise of enhanced risk stratification, thereby revolutionizing future management strategies and patient outcomes.
PATIENTS AND METHODS: A total of 7476 patients with routine health check-up data who underwent prostate biopsies from January 2008 to December 2021 in eight referral centres in Asia were screened. After data pre-processing and cleaning, 5037 patients and 117 features were analyzed. Seven AI-based algorithms were tested for feature selection and seven AI-based algorithms were tested for classification, with the best combination applied for model construction. The APAC score was established in the CH cohort and validated in a multi-centre cohort and in each validation cohort to evaluate its generalizability in different Asian regions. The performance of the models was evaluated using area under the receiver operating characteristic curve (ROC), calibration plot, and decision curve analyses.
RESULTS: Eighteen features were involved in the APCA score predicting HGPCa, with some of these markers not previously used in prostate cancer diagnosis. The area under the curve (AUC) was 0.76 (95% CI:0.74-0.78) in the multi-centre validation cohort and the increment of AUC (APCA vs. PSA) was 0.16 (95% CI:0.13-0.20). The calibration plots yielded a high degree of coherence and the decision curve analysis yielded a higher net clinical benefit. Applying the APCA score could reduce unnecessary biopsies by 20.2% and 38.4%, at the risk of missing 5.0% and 10.0% of HGPCa cases in the multi-centre validation cohort, respectively.
CONCLUSIONS: The APCA score based on routine health check-ups could reduce unnecessary prostate biopsies without additional examinations in Asian populations. Further prospective population-based studies are warranted to confirm these results.
METHODS: A systematic literature search guided by the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statement was performed using the EBSCOHost® platform, ScienceDirect, Scopus and Google Scholar between July and August 2021. Studies from January 2010 to January 2021 were eligible for review. Nine articles were eligible and included in this systematic review. The risk of bias assessment used the National Institutes of Health quality assessment tool for observational cohort and cross-sectional studies. The WHO-ICF helped to guide the categorization of fall risk factors.
RESULTS: Seven screening tools adequately predicted fall risk among community-dwelling older adults. Six screening tools covered most of the components of the WHO-ICF, and three screening tools omitted the environmental factors. The modified 18-item Stay Independent Brochure demonstrated most of the predictive values in predicting fall risk. All tools are brief and easy to use in community or outpatient settings.
CONCLUSION: The review explores the literature evaluating fall risk screening tools for nurses and other healthcare providers to assess fall risk among independent community-dwelling older adults. A fall risk screening tool consisting of risk factors alone might be able to predict fall risk. However, further refinements and validations of the tools before use are recommended.