Publications by authors named "E A Tabak"
Article Synopsis
- This study explored the link between children's attitudes towards physical activity and weight gain, with a specific focus on gender differences.
- Data was collected from over 3,100 students aged 9 to 14 in Türkiye, using a survey to assess their physical activity attitudes and measuring their BMI.
- Findings indicated that normal-weight students had a more positive attitude towards physical activity than those who were overweight or obese, with boys showing higher positivity than girls, but no significant difference in negative attitudes between genders.
Background: Endomyocardial biopsy (EMB) is currently considered the gold standard for diagnosing cardiac allograft rejection. However, significant limitations related to histological interpretation variability are well-recognized. We sought to develop a methodology to evaluate EMB solely based on gene expression, without relying on histology interpretation.
View Article and Find Full Text PDFObjective: Within the scope of semi-occluded vocal tract exercises (SOVTEs), we aimed to examine the effects of four exercise combinations, which involved various fluid densities and tube submersion depths, on acoustic and electroglottographic (EGG) parameters.
Methods: Four procedures (P) were applied consecutively to 30 female participants with normal voices using different tube submersion depths and fluid densities, including P1 (2 cm, water), P2 (2 cm, nectar), P3 (10 cm, water), and P4 (10 cm, nectar). Nasometric (Nasometer II model 6450) and EGG (Electroglottograph model 6103) measurements were taken before the procedures were initiated (pre-test) and at the end of each procedure.
From Reflection to Action: Combining Machine Learning with Expert Knowledge for Nutrition Goal Recommendations.
Proc SIGCHI Conf Hum Factor Comput Syst
May 2021
Article Synopsis
- Self-tracking can enhance chronic condition management by personalizing interventions, but it requires motivation and health literacy.
- Machine learning, while useful for pattern recognition, faces challenges in providing actionable health suggestions; GlucoGoalie attempts to bridge this gap by translating ML insights into personalized nutrition goals for type 2 diabetes (T2D) patients.
- In studies, participants found the goal suggestions both understandable and actionable, but issues arose between abstract goals and real-life eating experiences, highlighting the need for more interactive and feedback-oriented systems in self-management interventions.
Decision-making related to health is complex. Machine learning (ML) and patient generated data can identify patterns and insights at the individual level, where human cognition falls short, but not all ML-generated information is of equal utility for making health-related decisions. We develop and apply attributable components analysis (ACA), a method inspired by optimal transport theory, to type 2 diabetes self-monitoring data to identify patterns of association between nutrition and blood glucose control.
View Article and Find Full Text PDF