Objective: To evaluate the safety and effectiveness of the community-based cardiac rehabilitation (CBCR) program that we had developed. Methods: Individuals aged >40 years with cardiovascular disease or its risk factors who were residing in a rural area were recruited as study subjects. The CBCR program, which consisted of 10 education sessions and 20 weeks of customized exercises (twice a week), was conducted in a public health center for 22 weeks. Comprehensive outcomes including body weight, blood glucose level, and 6-minute walk distance (6MWD) were measured at baseline, 11th week, and completion. Furthermore, the outcomes of young-old (65–74 years) and old-old (≥75 years) female subjects were compared. Results: Of 31 subjects, 21 completed the program (completion rate, 67.7%). No adverse events were observed, and none of the subjects discontinued the exercise program because of chest pain, dyspnea, and increased blood pressure. Body weight and blood glucose level were significantly decreased, and 6MWD was significantly increased following program implementation (p<0.05). Both young-old and old-old women exhibited an improvement in blood glucose level and 6MWD test (p<0.05). Conclusion We reported the results of the first attempted CBCR in South Korea that was implemented without adverse events during the entire program. Improved aerobic exercise ability and reduced risk factors in all participants were observed. These improvements were also achieved by older adults aged ≥75 years.

BACKGROUND: We described a novel multi-step retinal fundus image reading system for providing high-quality large data for machine learning algorithms, and assessed the grader variability in the large-scale dataset generated with this system. METHODS: A 5-step retinal fundus image reading tool was developed that rates image quality, presence of abnormality, findings with location information, diagnoses, and clinical significance. Each image was evaluated by 3 different graders. Agreements among graders for each decision were evaluated. RESULTS: The 234,242 readings of 79,458 images were collected from 55 licensed ophthalmologists during 6 months. The 34,364 images were graded as abnormal by at-least one rater. Of these, all three raters agreed in 46.6% in abnormality, while 69.9% of the images were rated as abnormal by two or more raters. Agreement rate of at-least two raters on a certain finding was 26.7%–65.2%, and complete agreement rate of all-three raters was 5.7%–43.3%. As for diagnoses, agreement of at-least two raters was 35.6%–65.6%, and complete agreement rate was 11.0%–40.0%. Agreement of findings and diagnoses were higher when restricted to images with prior complete agreement on abnormality. Retinal/glaucoma specialists showed higher agreements on findings and diagnoses of their corresponding subspecialties. CONCLUSION: This novel reading tool for retinal fundus images generated a large-scale dataset with high level of information, which can be utilized in future development of machine learning-based algorithms for automated identification of abnormal conditions and clinical decision supporting system. These results emphasize the importance of addressing grader variability in algorithm developments.
Dataset ; Decision Support Systems, Clinical ; Diagnosis ; Machine Learning* ; Reading ; Retinaldehyde ; Specialization