Anomaly and signature filtering improve classifier performance for detection of suspicious access to EHRs.

Our objective is to facilitate semi-automated detection of suspicious access to EHRs. Previously we have shown that a machine learning method can play a role in identifying potentially inappropriate access to EHRs. However, the problem of sampling informative instances to build a classifier still remained. We developed an integrated filtering method leveraging both anomaly detection based on symbolic clustering and signature detection, a rule-based technique. We applied the integrated filtering to 25.5 million access records in an intervention arm, and compared this with 8.6 million access records in a control arm where no filtering was applied. On the training set with cross-validation, the AUC was 0.960 in the control arm and 0.998 in the intervention arm. The difference in false negative rates on the independent test set was significant, P=1.6×10(-6). Our study suggests that utilization of integrated filtering strategies to facilitate the construction of classifiers can be helpful.

Does self-management education benefit all populations with arthritis? A randomized controlled trial in a primary care physician network.

OBJECTIVE: Studies have suggested that the Arthritis Self-Management Program (ASMP) course is effective at reducing arthritis pain and health care costs in volunteer participants. There have been no reports of trials of the ASMP in the context of primary care physicians' practices, where the potential for spreading the program may be greatest. We conducted a randomized controlled trial of the ASMP course in a large primary care physician network. METHODS: Patients with osteoarthritis, rheumatoid arthritis, or fibromyalgia were recruited for the study. Subjects in the intervention practices received the 6 week course and those in the control practices received only the ASMP book, without course. Disability, pain, self-efficacy, mental health, and satisfaction were measured using validated instruments at baseline and at 4 months. RESULTS: One hundred thirteen patients were recruited for the ASMP course (intervention) and completed baseline and 4 month followup questionnaires. Eighty-four percent completed at least 4 of 6 classes. Seventy-four patients received the ASMP manual (controls) and completed both questionnaires. Patients in the intervention and control groups had similar baseline pain (p = 0.94), self-efficacy to control pain (p = 0.90), mental health (p = 0.10), and vitality scores (p = 0.21), but those in the intervention arm had slightly less disability (p = 0.04). At 4 months, there was no significant improvement from baseline in any endpoint and no difference between patients in the intervention and control groups (all p > 0.2). Patient satisfaction with arthritis care and outcomes was no different for intervention and control patients (all p > 0.3). All types of health care resource use were similar at baseline and followup for both intervention and control groups (all p > 0.2). CONCLUSION: While the ASMP course has been found to be effective in other patient groups, there were no significant clinical benefits noted at 4 months in patients recruited from primary care practices.

Implementing patient access to electronic health records under HIPAA: lessons learned.

In 2001, the Institute of Medicine (IOM) and the Health Insurance Portability and Accountability Act (HIPAA) emphasized the need for patients to have greater control over their health information. We describe a Boston healthcare system's approach to providing patients access to their electronic health records (EHRs) via Patient Gateway, a secure, Web-based portal. Implemented in 19 clinic sites to date, Patient Gateway allows patients to access information from their medical charts via the Internet in a secure manner. Since 2002, over 19,000 patients have enrolled in Patient Gateway, more than 125,000 patients have logged into the system, and over 37,000 messages have been sent by patients to their practices. There have been no major security concerns. By providing access to EHR data, secure systems like Patient Gateway allow patients a greater role in their healthcare process, as envisioned by the IOM and HIPAA.