OBJECTIVE: This study examined the performance of 3 ML algorithms in comparison with logistic regression (LR) to predict overweight or obesity status among working adults in Malaysia.
METHODS: Using data from 16,860 participants (mean age 34.2, SD 9.0 years; n=6904, 41% male; n=7048, 41.8% with overweight or obesity) in the Malaysia's Healthiest Workplace by AIA Vitality 2019 survey, predictor variables, including sociodemographic characteristics, job characteristics, health and weight perceptions, and lifestyle-related factors, were modeled using the extreme gradient boosting (XGBoost), random forest (RF), and support vector machine (SVM) algorithms, as well as LR, to predict overweight or obesity status based on a BMI cutoff of 25 kg/m2.
RESULTS: The area under the receiver operating characteristic curve was 0.81 (95% CI 0.79-0.82), 0.80 (95% CI 0.79-0.81), 0.80 (95% CI 0.78-0.81), and 0.78 (95% CI 0.77-0.80) for the XGBoost, RF, SVM, and LR models, respectively. Weight satisfaction was the top predictor, and ethnicity, age, and gender were also consistent predictor variables of overweight or obesity status in all models.
CONCLUSIONS: Based on multi-domain online workplace survey data, this study produced predictive models that identified overweight or obesity status with moderate to high accuracy. The performance of both ML-based and logistic regression models were comparable when predicting obesity among working adults in Malaysia.
Objective: To study the diagnostic modalities used in the evaluation and management of drug allergy/drug hypersensitivity reactions (DHRs) among member societies of the Asia Pacific Association of Allergy, Asthma and Clinical Immunology (APAAACI).
Methods: A questionnaire comprising 41 questions was circulated electronically to member societies and individual members of APAAACI between January 23, 2020 and March 6, 2020.
Results: Twenty-six respondents from 15 member societies and 1 individual member responded. European DHR guidelines were most commonly used. Skin prick and intradermal testing was used by 100%, with only 60% having access to commercial penicillin skin test reagents. In vitro-specific IgE tests were used by 75%, and basophil activation test by 56.3% for immediate DHR. Patch tests were used by 75% in contrast to lymphocyte transformation tests by 25% for nonimmediate DHR. Drug provocation tests were used by 68.8%, the most common indication being to exclude hypersensitivity where history/symptoms were not suggestive of drug hypersensitivity/allergy (93.3%). Human leukocyte antigen (HLA) genotype testing was mandatory among 25% respondents before new carbamazepine prescriptions, and 8.3% for allopurinol prescriptions.
Conclusions: There was increased use of skin testing for iodinated contrast media hypersensitivity and patch testing for nonimmediate DHR. HLA genotype testing prior to new carbamazepine, allopurinol and abacavir prescriptions remain variable despite strong associations for severe cutaneous adverse reactions with Asian ethnicity. Results of this survey form a useful framework for developing educational and training needs and for improving access to drug allergy diagnostic and treatment modalities across APAAACI member societies.