METHODS: In total, 154 patients (wild-type EGFR, 72 patients; Del19 mutation, 45 patients; and L858R mutation, 37 patients) were retrospectively enrolled and randomly divided into 92 training and 62 test cases. Two support vector machine (SVM) models to distinguish between wild-type and mutant EGFR (mutation [M] classification) as well as between the Del19 and L858R subtypes (subtype [S] classification) were trained using 3DBN features. These features were computed from 3DBN maps by using histogram and texture analyses. The 3DBN maps were generated using computed tomography (CT) images based on the Čech complex constructed on sets of points in the images. These points were defined by coordinates of voxels with CT values higher than several threshold values. The M classification model was built using image features and demographic parameters of sex and smoking status. The SVM models were evaluated by determining their classification accuracies. The feasibility of the 3DBN model was compared with those of conventional radiomic models based on pseudo-3D BN (p3DBN), two-dimensional BN (2DBN), and CT and wavelet-decomposition (WD) images. The validation of the model was repeated with 100 times random sampling.
RESULTS: The mean test accuracies for M classification with 3DBN, p3DBN, 2DBN, CT, and WD images were 0.810, 0.733, 0.838, 0.782, and 0.799, respectively. The mean test accuracies for S classification with 3DBN, p3DBN, 2DBN, CT, and WD images were 0.773, 0.694, 0.657, 0.581, and 0.696, respectively.
CONCLUSION: 3DBN features, which showed a radiogenomic association with the characteristics of the EGFR Del19/L858R mutation subtypes, yielded higher accuracy for subtype classifications in comparison with conventional features.
METHODS: A cross-sectional study of consecutive adult patients who underwent glucose hydrogen breath test was conducted. Factors associated with SIBO were evaluated. Symptom severity and HRQoL of IBS patients with and without SIBO were compared. The independent factors associated with severe IBS were explored.
RESULTS: A total of 160 patients were included (median age 40 years, males 31.3%). IBS was present among 53.8% of subjects, with 33.8% having diarrhea-predominant IBS (IBS-D). SIBO was diagnosed in 22.5% of the study population. Patients with SIBO were more commonly diagnosed with IBS-D than those without (50.0% vs 29.0%, P = 0.019). Severe IBS was associated with SIBO (36.4% vs 15.6%, P = 0.043). SIBO was associated with poorer HRQoL (Euroqol five-dimensional utility score: 0.73 vs 0.80, P = 0.024). SIBO (44.4% vs 20.6%, P = 0.043), anxiety (77.8% vs. 39.7%, P = 0.004), and depression (50.0% vs 19.1%, P = 0.011) were associated with severe IBS in the univariate analysis. However, SIBO was the only independent factor associated with severe IBS in the multivariate analysis (adjusted odds ratio 3.83, 95% confidence interval CI 1.02-14.34, P = 0.046).
CONCLUSIONS: There was a significant association between IBS-D and SIBO. The coexistence of SIBO had a significant negative impact on IBS patients.
DESIGN: Prospective case series, Proof of concept pilot study.
SETTING: Tertiary Health Care Center, Hospital Tuanku Jaafar, Seremban, Malaysia. Department of Surgery.
PARTICIPANTS: A total of 17 patients diagnosed with advanced COJ tumour and who had never undergone any surgical, endoscopic, or chemoradiotherapy and indicated for stenting were recruited.
INTERVENTIONS: The study period was over nine months, and follow-up was one-month post-stenting.
MAIN OUTCOME MEASURES: Endpoint measures were feasibility of deployment of the new design, symptoms relief, early stent migration, early complication, GERD Q score, and (QOL)assessment.
RESULTS: The ART stent was inserted successfully in all cases (17/17, 100%). There were two stent migrations due to the flexibility of the stent at the neck. There were no early or post-stenting one-month complications associated with the procedure. A good flow of contrast was seen in all the stents deployed. GERD Q score was low in all patients pre and post-stenting. Post-stenting there was a relief of dysphagia, weight gain, and a 60% improvement in QOL score.
CONCLUSIONS: ART stent is feasible and technically successful in COJ tumours. It provides good symptom relief, improves the QOL, and has minimal early complications.
FUNDING: None declared.
OBJECTIVE: To determine and quantify lard as an adulterant in a binary blend with palm oil in a cosmetic soap formulations by FT-IR and multivariate analysis.
METHODS: Fatty acids in lard, palm oil and binary blends were extracted via liquid-liquid extraction and were subjected to FTIR spectrometry, combined with principal component analysis (PCA) and discriminant analysis (DA) for the classification of lard in cosmetic soap formulations via two DA models: Model A (percentage of lard in cosmetic soap) and Model B (porcine and non-porcine cosmetic soap). Linear regression (MLR), partial least square regression (PLS-R) and principal components regression (PCR) were used to assess the degree of adulteration of lard in the cosmetic soap.
FINDINGS: The FTIR spectrum of palm oil slightly differed from that of lard at the wavenumber range of 1453 cm -1 and 1415 cm -1 in palm oil and lard, respectively, indicating the bending vibrations of CH2 and CH3 aliphatic groups and OH carboxyl group respectively. Both of the DA models could accurately classify 100% of cosmetic soap formulations. Nevertheless, less than 100% of verification value was obtained when it was further used to predict the unknown cosmetic soap sample suspected of containing lard or a different percentage of lard. The PCA for Model A and Model B explained a similar cumulative variability (CV) of 92.86% for the whole dataset. MLR and PCR showed the highest determination coefficient (R2) of 0.996, and the lowest relative standard error (RSE) and mean square error (MSE), indicating that both regression models were effective in quantifying the lard adulterant in cosmetic soap.
CONCLUSION: FTIR spectroscopy coupled with chemometrics with DA, PCA and MLR or PCR can be used to analyse the presence of lard and quantify its percentage in cosmetic soap formulations.
OBJECTIVES: The main objective of the research is to develop a robust and high-performance human action recognition techniques. A combination of local and holistic feature extraction methods used through analyzing the most effective features to extract to reach the objective, followed by using simple and high-performance machine learning algorithms.
METHODS: This paper presents three robust action recognition techniques based on a series of image analysis methods to detect activities in different scenes. The general scheme architecture consists of shot boundary detection, shot frame rate re-sampling, and compact feature vector extraction. This process is achieved by emphasizing variations and extracting strong patterns in feature vectors before classification.
RESULTS: The proposed schemes are tested on datasets with cluttered backgrounds, low- or high-resolution videos, different viewpoints, and different camera motion conditions, namely, the Hollywood-2, KTH, UCF11 (YouTube actions), and Weizmann datasets. The proposed schemes resulted in highly accurate video analysis results compared to those of other works based on four widely used datasets. The First, Second, and Third Schemes provides recognition accuracies of 57.8%, 73.6%, and 52.0% on Hollywood2, 94.5%, 97.0%, and 59.3% on KTH, 94.5%, 95.6%, and 94.2% on UCF11, and 98.9%, 97.8% and 100% on Weizmann.
CONCLUSION: Each of the proposed schemes provides high recognition accuracy compared to other state-of-art methods. Especially, the Second Scheme as it gives excellent comparable results to other benchmarked approaches.
METHODS: This study was a two-arm parallel randomized controlled trial. Twenty-eight patients with coronary heart disease were randomly assigned to either the intervention group, receiving a 12-week technology-assisted intervention (n = 14), or the control group (n = 14), receiving usual care. Guided by the Health Belief Model, the intervention group received three center-based, supervised exercise training sessions, a fitness watch that served as a cue to action, six educational videos, and a weekly video call. The Self-efficacy for Exercise, exercise capacity, and Health Promoting Lifestyle Profile II were assessed at baseline and immediately post-intervention (12-weeks).
RESULTS: Among the 28 patients who participated in this study, 85.7% completed the program, with a relatively low attrition rate (14.3%). The number of exercise training sessions accomplished by the participants in the intervention group was 51.27 ± 19.41 out of 60 sessions (85.5%) compared to 36.46 ± 23.05 (60.8%) in the control group. No cardiac adverse events or hospitalizations were reported throughout the study. Participants in the intervention group showed greater improvement in health-promoting behaviors when compared with the control group at 12 weeks. Within-group effects demonstrated improvement in exercise self-efficacy and exercise capacity among participants in the intervention group. A participant satisfaction survey conducted immediately post-intervention revealed that participants were "very satisfied" (23.1%) and "satisfied" (76.9%) with the technology-assisted intervention.
CONCLUSIONS: The findings demonstrated that technology-assisted intervention in a hybrid cardiac rehabilitation program was feasible and suggested to be beneficial in improving exercise self-efficacy, exercise capacity, and health promoting behavior among patients with coronary heart disease. A full-scale study is needed to determine its effectiveness in the long term.
TRIAL AND PROTOCOL REGISTRATION: ClinicalTrials.gov NCT04862351. https://clinicaltrials.gov/ct2/show/NCT04862351.
METHODS: FS measures at 1 and 4 kHz center frequencies were obtained using a custom-made software in normal-hearing (NH), slight SNHL and mild-to-moderate SNHL subjects. For comparison, subjects were also assessed with the Malay Digit Triplet Test (DTT) and the shortened Malay Speech, Spatial and Qualities of Hearing Scale (SSQ) questionnaire.
RESULTS: Compared to DTT and SSQ, the FS measure at 4 kHz was able to distinguish NH from slight and mild-to-moderate SNHL subjects, and was strongly correlated with their thresholds in quiet determined separately in 1-dB step sizes at the similar test frequency. Further analysis with receiver operating characteristic (ROC) curves indicated area under the curve (AUC) of 0.77 and 0.83 for the FS measure at 4 kHz when PTA thresholds of NH subjects were taken as ≤ 15 dB HL and ≤ 20 dB HL, respectively. At the optimal FS cut-off point for 4 kHz, the FS measure had 77.8% sensitivity and 86.7% specificity to detect 20 dB HL hearing loss.
CONCLUSION: FS measure was superior to DTT and SSQ questionnaire in detecting early frequency-specific threshold shifts in SNHL subjects, particularly at 4 kHz. This method could be used for screening subjects at risk of noise-induced hearing loss.