健康与医学信息学杂志

Health care transportation costs have increased dramatically in the United States and in many developed countries. Public health programs in the U.S that includes the Medicare and Medicaid programs rely on nonemergency transport companies to provide access to health care providers and facilities for vulnerable populations. Spending on these services are expected to increase to over $4 Billion in coming years. Recent studies from government sources and other research finds that these programs have fraud and waste associated with providing the service. We find that much of the waste and fraud is a direct result of inefficiencies largely driven by outmoded legacy technology systems and further suggest that blockchain applications can mitigate fraud, waste and abuse while providing better access to care and improved health outcomes for vulnerable populations.

Background: Smartphone has emerged common place within the medical field. Most health care experts desire current clinical facts and decisions that support at the point of patients’ care. The study was carried out to ascertain the use of smartphones in medical education and practice in Emergency Department of BP Koirala institute of Health Sciences (BPKIHS), Nepal.

Method: A cross-sectional study was done in all the medical officers, residents and faculties working in emergency department of BPKIHS.

Result: Ninety-nine percent (99%) of participants reported using smartphones and 89% of participants used smartphones over more than two years. 55% bought smartphone to use in medical education and 98% of participants found using medical apps in clinical practice. 99% believed that smartphone apps were supportive to learning especially in clinical exam tests and findings 75%. Ninety-six (96%) of the participants believed the concept of smartphones was useful. 66% of respondents expressed their views regarding smartphone use in medical education.

Conclusion: The study confirms that smartphones are ubiquitously adopted by residents, medical officers and faculties which enhance both learning and continuing patients’ care. It is advisable to understand its need and maximize its benefits in field of medical education.

Background: Prediction tool for incident renal replacement therapy (iRRT) use could potentially improve outcomes in ICU population. We used the data from the Medical Information Mart for Intensive Care III (MIMIC III) database to create artificial intelligence (AI) iRRT use prediction model.

Methods: Based on routinely collected data in ICU we identified and engineered 679 candidate predictors of iRRT use. The iRRT was defined as any dialysis-related event charted in the electronic medical record (EMR) within the seven days following the first 24 hours of ICU admission. ICU stays of patients on dialysis before ICU admission, and with dialysis-related events charted before the end of first 24 hours were excluded. Remaining 18379 ICU stays were randomly divided 400 times, into training and testing datasets. For each random training dataset, AI-model for iRRT prediction was trained. Predictions of AI, SOFA, OASIS, and APSIII, were validated on testing dataset against the known use of iRRT with the area under the curve (AUC) of receiver-operator characteristics curve (ROC) recorded.

Result: For all 400 iterations, AUC of ROC for AI-model was 0.88 [95% CI 0.88-0.89] and was higher than SOFA, APSIII and OASIS: 0.82 [0.82-0.82], 0.81 [0.81-0.81], and 0.7 [0.69-0.7] AUCs respectively (p<0.001).

Conclusion: AI-model was accurate in predicting patients who survive until, consent and undergo iRRT after ICU admission. High AUC for the AI model trained only on data from first 24 hours of ICU stay emphasizes the importance of initial ICU management on renal outcomes.