METHODS: Retrospective data of 347 patients, consisting of maternal demographics and ultrasound parameters collected between the 20th and 25th gestational weeks, were studied. ML models were applied to different combinations of the parameters to predict SGA and severe SGA at birth (defined as 10th and third centile birth weight).
RESULTS: Using second-trimester measurements, ML models achieved an accuracy of 70% and 73% in predicting SGA and severe SGA whereas clinical guidelines had accuracies of 64% and 48%. Uterine PI (Ut PI) was found to be an important predictor, corroborating with existing literature, but surprisingly, so was nuchal fold thickness (NF). Logistic regression showed that Ut PI and NF were significant predictors and statistical comparisons showed that these parameters were significantly different in disease. Further, including NF was found to improve ML model performance, and vice versa.
CONCLUSION: ML could potentially improve the prediction of SGA at birth from second-trimester measurements, and demonstrated reduced NF to be an important predictor. Early prediction of SGA allows closer clinical monitoring, which provides an opportunity to discover any underlying diseases associated with SGA.
MATERIALS AND METHODS: This was a retrospective study conducted at nephrology unit of a tertiary hospital in Kedah. All diabetic ESRD patients who fulfilled the inclusion criteria were identified and recruited for analysis.
RESULTS: The mean duration of DM to ESRD was found to be 14.37 ± 4.42 years. Mean duration for the onset of diabetic nephropathy was 8.73 ± 3.37 years. There was a relative short duration from diabetic nephropathy to ESRD noted, which was 5.63 ± 2.06 years. The mean duration of DM to ESRD for patients receiving RAAS blocker was found to be 18.23 ± 2.38 years as compared to 11.41 ± 2.94 years for those who did not (95% CI: -0.64 to -2.46). For different type of RAAS blockers, namely ACE inhibitor and angiotensin receptor blocker (ARB), there was no significant difference observed pertaining to mean duration of DM to ESRD; 17.89 ± 1.97 years for ACEi and 19.00 ± 4.16 years for ARB (95% CI: -4.74 to 2.52).
DISCUSSION: Time frame from diabetic nephropathy to ESRF among Malaysian population was shorter as compared to findings from other countries with an average period of 15 to 25 years. RAAS blockers should be initiated early in diabetic patients.
METHODS: This non-interventional study was conducted from August 2016 to April 2017. A total of 138 patients (aged 18-65 years) with an active episode of major depression were recruited from Malaysia, Philippines, Singapore and Thailand. Vortioxetine was initiated on the first visit and patients were followed for 3 months. Depression severity was assessed using the PHQ-9 questionnaire (patient assessed) and CGI-S scale (physician assessed); cognitive function was assessed with the PDQ-D questionnaire; work productivity and activity impairment (WPAI) was assessed with the WPAI questionnaire.
RESULTS: At baseline, 89.9% of patients were moderately to severely depressed (PHQ-9 score ≥10). During the 3 month treatment period, mean ± SD PHQ-9 score decreased from 18.7 ± 5.7 to 5.0 ± 5.3, mean ± SD CGI-S score decreased from 4.4 ± 0.7 to 2.2 ± 1.1 and mean ± SD PDQ-D score decreased from 42.1 ± 18.8 to 13.4 ± 13.0. By Month 3, response and remission rates reached 80.8% and 59.0%, respectively. Work productivity loss decreased from 73.6% to 30.5%, while activity impairment decreased from 71.5% to 24.6%. Positive correlations were observed between PHQ-9, PDQ-D, and WPAI work productivity loss and activity impairment. By Month 3, 82.0% of patients were either not depressed or only mildly depressed (PHQ-9 score ≤9).
CONCLUSION: In real-world clinical settings, vortioxetine was effective in reducing depression severity and improving cognitive function and work productivity in SEA patients with major depression.