METHODS: A cross-sectional study was conducted among 134 geriatric patients with a mean age of 68.9 ± 8.4 who stayed at acute care wards in Hospital Tuanku Ampuan Rahimah, Klang from July 2017 to August 2017. The SGA, MNA, and GNRI were administered through face-to-face interviews with all the participants who gave their consent. The sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of the GNRI and MNA were analyzed against the SGA. Receiver-operating characteristic (ROC) curve analysis was used to obtain the area under the curve (AUC) and suitable optimal cutoff values for both the GNRI and MNA.
RESULTS: According to the SGA, MNA, and GNRI, 26.9%, 42.5%, and 44.0% of the participants were malnourished, respectively. The sensitivity, specificity, PPV, and NPV for the GNRI were 0.622, 0.977, 0.982, and 0.558, respectively, while those for the MNA were 0.611, 0.909, 0.932, and 0.533, respectively. The AUC of the GNRI was comparable to that of the MNA (0.831 and 0.898, respectively). Moreover, the optimal malnutrition cutoff value for the GNRI was 94.95.
CONCLUSIONS: The prevalence of malnutrition remains high among hospitalized elderly patients. Validity of the GNRI is comparable to that of the MNA, and use of the GNRI to assess the nutritional status of this group is proposed with the new suggested cutoff value (GNRI ≤ 94.95), as it is simpler and more efficient. Underdiagnosis of malnutrition can be prevented, possibly reducing the prevalence of malnourished hospitalized elderly patients and improving the quality of the nutritional care process practiced in Malaysia.
METHODS: Healthy participants consumed pure forms of a non-nutritive sweetener (NNS) mixed with water that were standardized to doses of 14% (0.425 g) of the acceptable daily intake (ADI) for aspartame and 20% (0.136 g) of the ADI for sucralose every day for two weeks. Blood samples were collected and analysed for glucose, insulin, active glucagon-like peptide-1 (GLP-1), and leptin.
RESULTS: Seventeen participants (10 females and 7 males; age 24 ± 6.8 years; BMI 22.9 ± 2.5 kg/m2) participated in the study. The total area under the curve (AUC) values of glucose, insulin, active GLP-1 and leptin were similar for the aspartame and sucralose treatment groups compared to the baseline values in healthy participants. There was no change in insulin sensitivity after NNS treatment compared to the baseline values.
CONCLUSIONS: These findings suggest that daily repeated consumption of pure sucralose or aspartame for 2 weeks had no effect on glucose metabolism among normoglycaemic adults. However, these results need to be tested in studies with longer durations. Novelty: • Daily consumption of pure aspartame or sucralose for 2 weeks had no effect on glucose metabolism. • Daily consumption of pure aspartame or sucralose for 2 weeks had no effect on insulin sensitivity among healthy adults.
METHOD: A set of three psychophysics conditions of hearing (critical band spectral estimation, equal loudness hearing curve, and the intensity loudness power law of hearing) is used to estimate the auditory spectrum. The auditory spectrum and all-pole models of the auditory spectrums are computed and analyzed and used in a Gaussian mixture model for an automatic decision.
RESULTS: In the experiments using the Massachusetts Eye & Ear Infirmary database, an ACC of 99.56% is obtained for pathology detection, and an ACC of 93.33% is obtained for the pathology classification system. The results of the proposed systems outperform the existing running-speech-based systems.
DISCUSSION: The developed system can effectively be used in voice pathology detection and classification systems, and the proposed features can visually differentiate between normal and pathological samples.
METHODS: EEG single trials are decomposed with discrete wavelet transform (DWT) up to the [Formula: see text] level of decomposition using a biorthogonal B-spline wavelet. The coefficients of DWT in each trial are thresholded to discard sparse wavelet coefficients, while the quality of the signal is well maintained. The remaining optimum coefficients in each trial are encoded into bitstreams using Huffman coding, and the codewords are represented as a feature of the ERP signal. The performance of this method is tested with real visual ERPs of sixty-eight subjects.
RESULTS: The proposed method significantly discards the spontaneous EEG activity, extracts the single-trial visual ERPs, represents the ERP waveform into a compact bitstream as a feature, and achieves promising results in classifying the visual objects with classification performance metrics: accuracies 93.60[Formula: see text], sensitivities 93.55[Formula: see text], specificities 94.85[Formula: see text], precisions 92.50[Formula: see text], and area under the curve (AUC) 0.93[Formula: see text] using SVM and k-NN machine learning classifiers.
CONCLUSION: The proposed method suggests that the joint use of discrete wavelet transform (DWT) with Huffman coding has the potential to efficiently extract ERPs from background EEG for studying evoked responses in single-trial ERPs and classifying visual stimuli. The proposed approach has O(N) time complexity and could be implemented in real-time systems, such as the brain-computer interface (BCI), where fast detection of mental events is desired to smoothly operate a machine with minds.
OBJECTIVE: Apply machine learning for the prediction and identification of factors associated with short and long-term mortality in Asian STEMI patients and compare with a conventional risk score.
METHODS: The National Cardiovascular Disease Database for Malaysia registry, of a multi-ethnic, heterogeneous Asian population was used for in-hospital (6299 patients), 30-days (3130 patients), and 1-year (2939 patients) model development. 50 variables were considered. Mortality prediction was analysed using feature selection methods with machine learning algorithms and compared to Thrombolysis in Myocardial Infarction (TIMI) score. Invasive management of varying degrees was selected as important variables that improved mortality prediction.
RESULTS: Model performance using a complete and reduced variable produced an area under the receiver operating characteristic curve (AUC) from 0.73 to 0.90. The best machine learning model for in-hospital, 30 days, and 1-year outperformed TIMI risk score (AUC = 0.88, 95% CI: 0.846-0.910; vs AUC = 0.81, 95% CI:0.772-0.845, AUC = 0.90, 95% CI: 0.870-0.935; vs AUC = 0.80, 95% CI: 0.746-0.838, AUC = 0.84, 95% CI: 0.798-0.872; vs AUC = 0.76, 95% CI: 0.715-0.802, p < 0.0001 for all). TIMI score underestimates patients' risk of mortality. 90% of non-survival patients are classified as high risk (>50%) by machine learning algorithm compared to 10-30% non-survival patients by TIMI. Common predictors identified for short- and long-term mortality were age, heart rate, Killip class, fasting blood glucose, prior primary PCI or pharmaco-invasive therapy and diuretics. The final algorithm was converted into an online tool with a database for continuous data archiving for algorithm validation.
CONCLUSIONS: In a multi-ethnic population, patients with STEMI were better classified using the machine learning method compared to TIMI scoring. Machine learning allows for the identification of distinct factors in individual Asian populations for better mortality prediction. Ongoing continuous testing and validation will allow for better risk stratification and potentially alter management and outcomes in the future.
Methods: This is a cohort study where prevalent ESRD patients' details were recorded between May 2012 and October 2012. Their records were matched with national death record at the end of year 2015 to identify the deceased patients within three years. Four models were formulated with two models were based on logistic regression models but with different number of predictors and two models were developed based on risk scoring technique. The preferred models were validated by using sensitivity and specificity analysis.
Results: A total of 1332 patients were included in the study. Majority succumbed due to cardiovascular disease (48.3%) and sepsis (41.3%). The identified risk factors were mode of dialysis (P < 0.001), diabetes mellitus (P < 0.001), chronic heart disease (P < 0.001) and leg amputation (P = 0.016). The accuracy of four models was almost similar with AUC between 0.680 and 0.711. The predictive models from logistic regression model and risk scoring model were selected as the preferred models based on both accuracy and simplicity. Besides the mode of dialysis, diabetes mellitus and its complications are the important predictors for early mortality among prevalent ESRD patients.
Conclusions: The models either based on logistic regression or risk scoring model can be used to screen high risk prevalent ESRD patients.