- About CSAIL
- News + Events
- Alumni & Friends
Health Care of the Future
August 02, 2011
By Abby Abazorius, MIT CSAIL
Pictured above: Professor Peter Szolovits (left) and Principal Research Scientist William Long.
Photo: Jason Dorfman, CSAIL photographer
In 1974 Professor Peter Szolovits made a prediction: By the 1980s a majority of large hospitals would have adopted the use of electronic medical records. While the necessary technology did not progress as quickly as expected to allow for this transition, the U.S. government is currently making a major push to ensure that hospitals switch from paper folders stuffed with memos to a secure and efficient electronic system for collecting, storing and retrieving medical records. Now Szolovits, the leader of the Clinical Decision Making Group at CSAIL, is at the forefront of the movement to make health IT more effective and useful for both professionals and patients.
While Szolovits was originally interested in building decision support systems that could analyze well-structured medical records and provide possible diagnoses and therapy advice, today he is also focused on using natural language processing to make better sense of medical records, which often contain unstructured narrative notes and abbreviations.
As part of the government’s push towards electronic medical records, Szolovits is participating in one of the four Office of the National Coordinator for Health Information Technology’s Strategic Health IT Advanced Research Projects (SHARP). Led by colleagues at Mayo Clinic, it focuses on secondary use of electronic health records, providing a means for using clinical data sets for research, quality assessment and support of public health.The principal technical challenges include developing natural language processing methods that allow computer programs to automatically extract clinical files, events and relationships from the narrative text in records, and to combine the resulting data with existing tabular data from laboratory tests and prescription orders to identify what is wrong with and what is being done to each patient.
“My interest in natural language processing was rekindled about 12 years ago by the observation that a lot of critical medical data was actually locked up in these narrative notes and we had to have some way of digging them out in order to make use of them,” explained Szolovits.
William Long, a principal research scientist in the Clinical Decision Making Group who has worked with Szolovits for over 30 years, has developed several programs that scan through pages of electronic nurses reports and intensive care unit (ICU) discharge summaries, searching for keywords and phrases that provide clues to a patient’s condition. Relying on information gathered from the Uniform Medical Language System (UMLS), a compilation of over 150 medical dictionaries, the Clinical Decision Making Group has programmed the system to identify a comprehensive list of terms and key concepts. The program can then offer doctors a brief summary of the compiled information.
Thus far, this technology has been used more for clinical research than diagnostic purposes. For example, the technology has been used to gather a group of patients who are all suffering from the same medical condition, but who reacted differently to identical treatment methods. Thanks to systems that can organize and parse medical records, physicians can uncover whether genetics, outside medications or personal habits affected the patient, and learn more about which treatments are, and are not, effective.
Szolovits still believes in applying artificial intelligence to the diagnostic process, but in a different manner than he originally envisioned. In collaboration with Dr. Roger Mark and Dr. George Verghese, a collaborative group including CSAIL, LIDS, HST and the BIDMC has collected data on approximately 35,000 intensive care unit admissions to a major Boston hospital. CSAIL graduate Caleb Hug used the data to create predictive models that estimate, each time something significant changes in a patient's state, how they are likely to fare in the future. Such acuity models can warn clinicians of danger and are also useful in determining the resources needed to assist a particular patient.
The same methodology can also be used to make more fine-grained predictions. Hug's research has applied this technique to predicting when it is safe to wean patients from life-assistance machines such as ventilators and intra-aortic balloon pumps, in addition to making predictions about whether a patient has a high probability of experiencing septic shock, hypotension or renal failure.
“We’re now planning a series of experiments where we’re going to try to run these kinds of algorithms at the time the patient is being taken care of, initially without divulging the results to anybody except ourselves so we can check to see whether in that stricter framework, where we’re not just doing it retroactively, if we are still getting the same level of accuracy, “ said Szolovits.
Outside the ICU, the group is tackling the issue of recording interactions between doctor and patient, and translating those conversations into usable information. In a project underway at Children’s Hospital in Boston, group members have recorded about 100 encounters in the Pediatric Environmental Health Center, where doctors often see cases of lead poisoning in children. Each doctor-patient interaction is recorded, translated into English text using a speech-understanding program and then analyzed with a natural language processing program developed by Professor Regina Barzilay's group for key terms and phrases to compile a report.
While the project has proved challenging due to the difficulties of building a speech-understanding component that provides high accuracy, Szolovits believes it could prove useful in making medical visits more efficient for doctors. In the future, Szolovits would also love to see the technology used by hospital nurses, so that they could focus more on patient care rather than compiling notes.
Despite the difficulties posed by transitioning to more technologically advanced systems, Szolovits and Long strongly believe that natural language processing programs like the ones developed by the Clinical Decision Making Group could dramatically improve medical care.
“It will, I think, revolutionize health care. It will make it much easier to get all of the information in a form that we can actually do something with and process it in ways that will be of benefit to everyone,” said Long. “Doctors are going to benefit by being able to look over these years of treating patients and turn that into a study of what works and what doesn’t work, how to improve the process of medicine and how to treat patients better.”
For more on the Clinical Decision Making Group, please visit http://groups.csail.mit.edu/medg/.