Recent notable scientific publications in the field of applied clinical informatics. #4

by Vitaly Herasevich, MD, PhD, MSc, FCCM, CPHIMS, Associate Professor of Anesthesiology and Medicine in Department of Anesthesiology, Mayo Clinic

Our monthly digest of recently peer-reviewed publications in the area of applied clinical informatics covers a couple of interesting publications, which drew attention in June.

In recent months, literature was more and more focused on educational aspects of Clinical Informatics. An article published in JAMIA, authored by Dr. Ted Shortliffe, suggests certain guidelines for graduate students who are pursuing doctoral studies and dissertations in informatics.1 The article “Embedding Nursing Informatics Education Into an Australian Undergraduate Nursing Degree” describes the process an Australian university uses to integrate nursing informatics throughout the undergraduate curriculum for nursing degrees, to ensure entry-level nurses have a basic level of skills in the use of informatics.2

Due to the accessible clinical data on health care, more research is being done on the constriction of prediction models. An excellent editorial by Dr. Moorman and colleagues provides “prescriptions” on how to do this kind of work.3 An editorial by Dr. Dziadzko and others4 outlines the challenges of constricting prediction models, especially in regard to inpatient and ICU practices. Data mining could be applied not only to clinical information but also to other sources. Literature reviews in the Journal of Biomedical Informatics summarize information about process mining, focusing on extracting knowledge from data generated and stored in corporate information systems, in order to analyze executed processes.5 Another paper in the same journal delineates a model that can extract pertinent health care topics from social media data.6

Commercial virtual visits are becoming a popular model of health care management of common acute illnesses. A recent paper in JAMA assesses variations in the quality of urgent health care visits among telemedicine companies. Researchers audited six acute illnesses: ankle pain, streptococcal pharyngitis, viral pharyngitis, acute rhinosinusitis, lower back pain, and recurring urinary-tract infections in females. Eight websites with the highest web traffic serving commercial virtual visits were selected for the study. Sixty-seven standardized patients completed 599 commercial virtual visits during the study period. The review found that 70 percent of individual histories and physical examinations were completed properly; 77 percent of diagnoses were correctly named; and 54 percent of key management decisions adhered to established guidelines. These numbers represent significant variations in quality among companies providing virtual visits for management of common acute illnesses.7 A similar study in JAMA Dermatology assessed the performance of direct-to-consumer (DTC) telemedicine websites and smartphone apps that diagnose and treat skin diseases. Researchers studied 62 clinical encounters from 16 DTC telemedicine websites. Only in 26 percent of the encounters did providers disclose information about clinicians’ licensure, and some services used internationally based physicians who did not have California licenses. A diagnosis or likely diagnosis was suggested in 77 percent of cases. Major diagnoses were repeatedly missed, including secondary syphilis. Prescription medications were ordered in 65 percent of diagnosed cases. The results of the study raise concerns about the quality of skin-disease diagnoses and treatment provided by many DTC telemedicine websites.8

Interesting systematic reviews were published last month. A systematic literature review investigated studies aiming to use online social networks (OSN) to detect and track pandemics. Twenty studies were analyzed, and a comparison of OSN with official information from health agencies was made. Most of the studies used Twitter as their data source. OSN data using API could be collected in real time, essentially. The reviews show that OSN surveillance has a high correlation to official information. However, the authors concluded that OSN surveillance probably never will replace traditional forms of surveillance, but could be complementary.9

To effectively use EMR systems requires significant investments from practices—investments estimated at $250,000 per facility. In a recent time-driven, activity-based, micro-costing analysis, the authors estimated the cost of meeting meaningful use (MU) criteria for an oral and maxillofacial surgery practice. The results of this analysis show that MU is associated with substantial recurring costs beyond the initial implementation expenses, training time, and loss of productivity, due to change in clinical workflow.10 Another relevant study explored the cost of EHR implementation used by nurses at the super-users roles. Driven by financial constraints, the innovative super-user workforce model reduced labor costs of implementation associated with super-user staffing by 31.8 percent, in contrast to the proposal by the vendor model.11



1.          Shortliffe EH. The organization and content of informatics doctoral dissertations. J Am Med Inform Assoc. 2016. PMID: 27274024

2.          Cummings E, Shin EH, Mather C, Hovenga E. Embedding Nursing Informatics Education into an Australian Undergraduate Nursing Degree. Stud Health Technol Inform. 2016;225:329–33. PMID: 27332216

3.          Moorman JR, Lake DE, Moss TJ. Computers in White Coats: How to Devise Useful Clinical Decision Support Software. Crit Care Med. 2016;44(7):1449–50. PMID: 27309173

4.          Dziadzko MA, Pickering BW, Herasevich V. Predicting Outcomes From Respiratory Distress: Does Another Score Help to Solve the Problem? Crit Care Med. 2016;44(7):1437–8. PMID: 27309167

5.          Rojas E, Munoz-Gama J, Sepúlveda M, Capurro D. Process mining in healthcare: A literature review. J Biomed Inform. 2016;61:224–36. PMID: 27109932

6.          Wang T, Huang Z, Gan C. On mining latent topics from healthcare chat logs. J Biomed Inform. 2016;61:247–59. PMID: 27132766

7.          Schoenfeld AJ, Davies JM, Marafino BJ, et al. Variation in Quality of Urgent Health Care Provided During Commercial Virtual Visits. JAMA Intern Med. 2016;176(5):635–42. PMID: 27042813

8.          Resneck JS, Abrouk M, Steuer M, et al. Choice, Transparency, Coordination, and Quality Among Direct-to-Consumer Telemedicine Websites and Apps Treating Skin Disease. JAMA dermatology. 2016. PMID: 27180232

9.          Al-Garadi MA, Khan MS, Varathan KD, Mujtaba G, Al-Kabsi AM. Using online social networks to track a pandemic: A systematic review. J Biomed Inform. 2016. PMID: 27224846

10.        Inverso G, Flath-Sporn SJ, Monoxelos L, Labow BI, Padwa BL, Resnick CM. What Is the Cost of Meaningful Use? J Oral Maxillofac Surg. 2016;74(2):227–9. PMID: 26546846

11.        Bullard KL. Cost Effective Staffing for an EHR Implementation. Nurs Econ. 34(2):72–6. PMID: 27265948

 About the Contributor

Vitaly Herasevich, MD, PhD, MSc, FCCM, CPHIMS is Associate Professor of Anesthesiology and Medicine in Department of Anesthesiology at Mayo Clinic. His interest in the area of medical informatics extends back to 1995 with specific concentration on the applied clinical informatics in critical care and science of healthcare delivery. Dr. Herasevich has interest in studying and development clinical syndromic surveillance alerting systems ("sniffers"), clinical data visualization (novel patient-centered EMR) and complex large data warehousing for healthcare predictive and prescriptive analytics as well as outcome reporting. He is author of more than 60 Pubmed cited articles and wrote two editions of book "Computer for Physician". As a part of education effort Dr. Herasevich serves Clinical Informatics Fellowship program as Associate Program Director, appointed with full faculty privileges in Mayo Graduate School and teaching class “Health Information Technology evaluation”. He is active within informatics and professional societies serving number of committees.

More information at lab web page - http://www.mayo.edu/research/labs/clinical-informatics-intensive-care/