METHODS: A gender-matched case-control study was conducted in the largest public sector cardiac hospital of Pakistan, and the data of 460 subjects were collected. The dataset comprised of eight nonclinical features. Four supervised ML algorithms were used to train and test the models to predict the CVDs status by considering traditional logistic regression (LR) as the baseline model. The models were validated through the train-test split (70:30) and tenfold cross-validation approaches.
RESULTS: Random forest (RF), a nonlinear ML algorithm, performed better than other ML algorithms and LR. The area under the curve (AUC) of RF was 0.851 and 0.853 in the train-test split and tenfold cross-validation approach, respectively. The nonclinical features yielded an admissible accuracy (minimum 71%) through the LR and ML models, exhibiting its predictive capability in risk estimation.
CONCLUSION: The satisfactory performance of nonclinical features reveals that these features and flexible computational methodologies can reinforce the existing risk prediction models for better healthcare services.
Experimental procedure: Fifty-two male Sprague Dawley rats were randomly divided into four groups: 1) control group, 2) goat milk treated group, 3) d-galactose treated group, and 4) goat milk plus d-galactose treated group. Goat milk (1 g/kg orally) and/or d-galactose (120 mg/kg subcutaneously) were administered continuously for six weeks preceded and followed by novel object recognition and T-maze test.
Results and conclusion: Prior to goat milk and d-galactose administration, there was no significant difference (p > 0.05) in memory between all groups. Goat milk administration alone significantly increased short- and long-term memory (p
METHODS: A randomized trial was performed in a University hospital in Malaysia. Term women scheduled for labor induction, Bishop score ≤ 5, singleton, cephalic presentation, intact membrane, and reassuring pre-induction fetal heart rate tracing were recruited. Women with known gross fetal anomaly, allergy to latex and inability to consent or language difficulty were excluded. Participants were randomized to 16F, 22F, or 28F Foley catheter. Primary outcome was insertion failure and main secondary outcomes were insertion duration and pain (assessed by a Visual Numerical Rating Scale [VNRS] 0-10, higher score more pain). Analysis is done by analysis of variance (ANOVA), Kruskal-Wallis, and chi square test across the three arms and by t test and Mann-Whitney U test for pair wise comparisons.
RESULTS: One hundred twenty-seven participants' data were analyzed. The insertion failure 7/43(16%) versus 4/42(10%) versus 5/42(12%), p = 0.64, insertion duration median [IQR] 2.8 [1.8-4.8] versus 2.8 [1.7-3.7] versus 2.8 [1.7-4.3] min, p = 0.68 and insertion pain VNRS mean {SD} 4.2 {2.5} versus 3.4 {2.3} versus 3.6 {2.2}, p = 0.26, insertion to delivery interval 26.0 {9.7} versus 25.6 {9.1} versus 22.8 {7.4} h, p = 0.45, and spontaneous vaginal delivery 20/43 (45%) versus 23/42(55%) versus 25/42(60%), p = 0.48 for 16F versus 22F versus 28F arms, respectively. Pairwise comparisons were not different.
CONCLUSION: Foley catheter 16F versus 22F versus 28F resulted in similar digital insertion performance in the dorsal recumbent position for unripe cervix labor induction.
CLINICAL TRIAL REGISTRATION: https://doi.org/10.1186/ISRCTN21224268.
MATERIALS AND METHODS: A prospective cohort study was carried out among 684 infants attending goverment health clinics in 2 states in Malaysia. Body weight, length, and clinical assessment were measured on the same day for 9 visits, scheduled every month until 6 months of age and every 2 months until 12 months of age. All of the 3 z-scores for weight for age (WAZ), length for age (HAZ), and weight for length (WHZ) were calculated using WHO Anthro for Personal Computers software.
RESULTS: The average sensitivity and specificity for the visual clinical assessment for the detection of thinness were higher using the WHO 2006 standard as compared with using NCHS 1977. However, the overall sensitivity of the visual clinical assessment for the detection of thin and lean children was lower from 1 month of age until a year as compared with the WHO 2006 standard and NCHS 1977 reference. The positive predictive value (PPV) for the visual clinical assessment versus the WHO 2006 standard was almost doubled as compared with the PPV of visual clinical assessment versus the NCHS 1977 reference. The overall average sensitivity, specificity, PPV, and negative predictive value for the detection of stunting was higher for visual clinical assessment versus the WHO 2006 standard as compared with visual clinical assessment versus the NCHS 1977 reference.
CONCLUSION: The sensitivity and specificity of visual clinical assessment for the detection of wasting and stunting among infants are better for the WHO 2006 standard than the NCHS 1977 reference.