|
Clinical research studies into drug efficacy and side effects have often been laborious and time consuming, new software that analyses "anonymised" patient electronic medical records could reduce investigation times from months to minutes. According to Steven Safyer, president and CEO of the Montefiore Medical Center, clinical studies used to take months, required a committee of physicians and data experts and involved an elaborate research review process. Now, many of these studies can be performed by a single clinic expert in a few of minutes using "deidentified" patient electronic medical records and software called Clinical Looking Glass (CLG). The software mines the vast pool of electronic medical record (EMR) data collected at the Center over ten yeas, explains Safyer, and allows the clinician to interpret the information for entire populations of patients. It allows the user to "rapidly check the collective effectiveness of patient safety measures, conduct clinical research, and even comply with federal regulations," Safyer says, "We believe it offers a glimpse into how health care informatics is shaping the future of medicine." The system has already been used measure the impact of US health insurance, Medicare, regulations on rehabilitation patients, quantify the reduction in radiation exposure for emergency department patients, provide data for professional articles on embolisms and hospital-based physicians, and to check on public health threats. Montefiore now has 700 physicians trained to use Clinical Looking Glass. Critically, the thousands of analyses now being run by clinicians each month as part of Montefiore's approach to healthcare, are run without patient names being identifiable from the analysed records. This allows research questions to be asked without the rules of patient confidentiality being broken in the process. "The goal of these analytics is to gather information and conduct studies that lead to better clinical decision-making," explains Montefiore's Eran Bellin, who was instrumental in the design of CLG. "The queries have provided the quantitative evidence for dozens of peer-review journal articles, presentations at professional meetings, institution-wide patient quality improvement initiatives and programs that benefit entire populations." One application of CLG is in reducing unnecessary patient exposure to radiation. The software was used to demonstrate that for certain embolism patients, a high-radiation CT pulmonary angiography (CTPA) is not needed and a lower-radiation examination, a ventilation-perfusion scan, can provide all the imaging information that is needed. CLG showed that in 2006, there were 1473 CTPA scans, this was before the educational seminars after educating the radiographers about the benefits of using ventilation-perfusion instead, CTPA numbers fell to 920 in 2007. The seminars had changed practice patterns without compromising patient safety. Another benefit to embolism patients came in the form of the discovery that surgical insertion of tiny filters commonly inserted into veins to prevent coagulation in embolism patients offer no advantages over anticoagulation drugs for patients prescribed those drugs. CLG also revealed how hospital physicians, hospitalists, could substantially reduce length of stay for stroke and pneumonia patients without compromising "resident" education. The same software has improved rehabilitation care by demonstrating that restricting access to inpatient rehabilitation on the basis of diagnosis alone resulted in patients being readmitted sooner and dying sooner. The Montefiore researchers were also able to show year on year differences in deaths during the "made-in-China" heparin scare and FDA review. The Montefiore CLG specialists have also identified 14,000 diabetes patients and been able to track their care and progress over time and compare improvements in blood glucose (HbA1C) and cholesterol levels of the patients at one health centre compared with another, and even the patient outcomes for one physician versus another. "CLG allows all clinicians and hospital administration to test hypotheses that just a few years ago would have been impossible to do," Bellin says. "It democratizes the research process. To be able to identify, within minutes, a cohort of patients, qualify them by a specific disease, medication, clinical event, race, time period or neighbourhood provides a new paradigm for population-based medicine and a new level of importance for health care informatics," said Bellin. The developers point out that New York City Department of Health is using CLG in research studies, and is being considered for use by the healthcare system of the US Department of Defence.
Related links:
|
|
