Application of optical character recognition with natural language processing for large-scale quality metric data extraction in colonoscopy reports.

BACKGROUND AND AIMS: Colonoscopy is commonly performed for colorectal cancer screening in the United States. Reports are often generated in a non-standardized format and are not always integrated into electronic health records. Thus, this information is not readily available for streamlining quality management, participating in endoscopy registries, or reporting of patient- and center-specific risk factors predictive of outcomes. We aim to demonstrate the use of a new hybrid approach using natural language processing of charts that have been elucidated with optical character recognition processing (OCR/NLP hybrid) to obtain relevant clinical information from scanned colonoscopy and pathology reports, a technology co-developed by Cleveland Clinic and eHealth Technologies (West Henrietta, NY, USA). METHODS: This was a retrospective study conducted at Cleveland Clinic, Cleveland, Ohio, and the University of Minnesota, Minneapolis, Minnesota. A randomly sampled list of outpatient screening colonoscopy procedures and pathology reports was selected. Desired variables were then collected. Two researchers first manually reviewed the reports for the desired variables. Then, the OCR/NLP algorithm was used to obtain the same variables from 3 electronic health records in use at our institution: Epic (Verona, Wisc, USA), ProVation (Minneapolis, Minn, USA) used for endoscopy reporting, and Sunquest PowerPath (Tucson, Ariz, USA) used for pathology reporting. RESULTS: Compared with manual data extraction, the accuracy of the hybrid OCR/NLP approach to detect polyps was 95.8%, adenomas 98.5%, sessile serrated polyps 99.3%, advanced adenomas 98%, inadequate bowel preparation 98.4%, and failed cecal intubation 99%. Comparison of the dataset collected via NLP alone with that collected using the hybrid OCR/NLP approach showed that the accuracy for almost all variables was >99%. CONCLUSIONS: Our study is the first to validate the use of a unique hybrid OCR/NLP technology to extract desired variables from scanned procedure and pathology reports contained in image format with an accuracy >95%.

Does academic assessment system type affect levels of academic stress in medical students? A cross-sectional study from Pakistan.

INTRODUCTION: Stress among medical students induced by academic pressures is on the rise among the student population in Pakistan and other parts of the world. Our study examined the relationship between two different systems employed to assess academic performance and the levels of stress among students at two different medical schools in Karachi, Pakistan. METHODS: A sample consisting of 387 medical students enrolled in pre-clinical years was taken from two universities, one employing the semester examination system with grade point average (GPA) scores (a tiered system) and the other employing an annual examination system with only pass/fail grading. A pre-designed, self-administered questionnaire was distributed. Test anxiety levels were assessed by The Westside Test Anxiety Scale (WTAS). Overall stress was evaluated using the Perceived Stress Scale (PSS). RESULTS: There were 82 males and 301 females while four did not respond to the gender question. The mean age of the entire cohort was 19.7 ± 1.0 years. A total of 98 participants were from the pass/fail assessment system while 289 were from the GPA system. There was a higher proportion of females in the GPA system (85% vs. 59%; p < 0.01). Students in the pass/fail assessment system had a lower score on the WTAS (2.4 ± 0.8 vs. 2.8 ± 0.7; p = 0.01) and the PSS (17.0 ± 6.7 vs. 20.3 ± 6.8; p < 0.01), indicating lower levels of test anxiety and overall stress than in students enrolled in the GPA assessment system. More students in the pass/fail system were satisfied with their performance than those in the GPA system. CONCLUSION: Based on the present study, we suggest governing bodies to revise and employ a uniform assessment system for all the medical colleges to improve student academic performance and at the same time reduce stress levels. Our results indicate that the pass/fail assessment system accomplishes these objectives.

Professionalism in medical students at a private medical college in Karachi, Pakistan.

OBJECTIVE: To determine levels of professionalism in undergraduate medical students at a private medical college and assess how changes emerge during their training. METHODS: The study was conducted at Aga Khan University, a tertiary care teaching hospital, during November and December 2011. Freshmen, Year 3 and Year 5 students were requested to fill out a questionnaire. It was designed to assess the participants' levels of professionalism and how they perceived the professional environment around them by incorporating previously described scales. The questionnaire was re-validated on a random sample of practising clinicians at the same hospital. SPSS 17 was used for statistical analysis. RESULTS: The study sample comprised 204 participants. The mean score for level of individual professionalism was 7.72+/-3.43. Only 13 (6.4%) students had a score one standard deviation above the faculty mean. About 24 (11.8%) were one standard deviation and 35 (17.2%) were 2 standard deviations below the faculty mean. The remaining 130 (63.7%) were >2 standard deviations below the faculty mean. Considering the level of education, the mean score for level of professionalism was 8.00+/-3.39 for freshmen, 6.85+/-3.41 for year 3 students, and 8.40+/-3.34 for year 5 students. CONCLUSION: The currently employed teaching practices inculcating the values of professionalism in medical students are serving as a buffer to maintain the pre-training levels of professionalism from declining.