Sleep Position Detection for Closed-Loop Treatment of Sleep-Related Breathing Disorders.

Reliable detection of sleep positions is essential for the development of technical aids for patients with position-dependent sleep-related breathing disorders. We compare personalized and generalizable sleeping position classifiers using unobtrusive eight-channel pressure-sensing mats. Data of six male patients with confirmed position-dependent sleep apnea was recorded during three subsequent nights. Personalized position classifiers trained using leave-one-night-out cross-validation on average reached an F1-score of 61.3% for supine/non-supine and an F1-score of 46.2% for supine/lateral-left/lateral-right classification. The generalizable classifiers reached average F1-scores of 62.1% and 49.1% for supine/non-supine and supine/lateral-left/lateral-right classification, respectively. In-bed presence ("bed occupancy") could be detected with an average F1-score of 98.1%. This work shows that personalized sleep-position classifiers trained with data from two nights have comparable performance to classifiers trained with large interpatient datasets. Simple eight-channel sensor mattresses can be used to accurately detect in-bed presence required for closed-loop systems but their use to classify sleep-positions is limited.

Influences affecting radiologists' choices of academic or private practice careers.

The authors surveyed 5,000 practicing radiologists and 3,000 individuals currently in radiology training to determine the aspects of their backgrounds, education, training, and attitudes that most affected their career decisions. The choice of academic radiology was associated with receiving medical school education or radiology training at an institution ranking among the 20 with the most federal grant funding, publishing research articles, and participating in a variety of interpersonal research experiences during radiology training. Academic radiologists were more likely to choose their careers because of their interests, aptitudes, and greater concern for the value of doing research. Private practitioners rated family obligations, leisure time, and level of personal income as more significant influences on their career choices. Programs interested in training more academic radiologists should reconsider how they select trainees and provide an appropriate research environment during training.

Factors influencing radiologists to choose research careers.

The future of radiology is threatened by the paucity of competent researchers who are radiologists. To determine what influences are most important in selecting and training potential radiology researchers, we conducted a survey of 5000 practicing radiologists, including all members of the Association of University Radiologists. We also surveyed 3000 randomly selected radiology trainees. A research career was empirically defined as 20% or more of a radiologist's time being involved with research. Response to the practicing radiologists and radiology trainees surveys was 28% and 19%, respectively. Radiologists who attended medical school or trained in radiology at an institution among the top 20 for research funding more frequently chose careers in research than those who matriculated and trained elsewhere. Publishing at least one research article, having a dedicated radiology research fellowship, having access to grant funds, and using computers during medical school or radiology training were factors typifying radiologists who chose research careers. Research radiologists were more concerned about the value of performing research and less concerned about personal income than those choosing careers not focusing on research. These results suggest that it might be possible to select radiology trainees who are more likely to become researchers based on their backgrounds and attitudes. An appropriate milieu during training enhances the likelihood of radiologists choosing research careers.

Factors influencing the success of academic radiologists in publishing research.

To guide changes that might improve radiologists' research productivity, we surveyed 1400 members of the Association of University Radiologists. We evaluated the impact of influences related to background, education, training, attitudes, and practice environment on 558 respondents' frequency of research publication. Attending medical school, obtaining radiology training, and practicing at an institution among the 20 with the highest amount of research funding was associated with the highest research productivity in academic practice. Taking a radiology research fellowship, regularly attending research seminars, and association with a research mentor during training were also associated with higher career productivity. Virtually all aspects of the academic practice milieu, and particularly having time set aside for research, were significant influences on radiologists' frequency of publication. Men published research more frequently than women. This phenomenon appears related to women being afforded fewer research experiences during radiology training and a greater concern on the part of women about obstacles that hinder their doing research. These data might be employed to guide changes that would improve the selection and nurturing of individuals likely to be productive in research.