I have blogged previously about utilizing machine learning software and natural language processing (NLP) to extract meaning from EHR records (see, for example: What Is the Significance of the Roche Acquisition of Flatiron?). This approach to healthcare research is starting to bear fruit (see: Machines Learn To Read Hospital Records, Will Doctor's Handwriting Be Next?). Below is an excerpt from a recent article describing artificial intelligence (AI) and EHR records:
Patient records are unruly; they consist of numbers, images, and text....As a result of the jumble of data types and formats, data mining to identify predictive analytics initially require a careful selection of variables of interest which are abstracted from medical records and put in a machine-readable form....A paper in Nature Partner Journals/Digital Medicine provides a proof of concept that the bottleneck has been removed. The researchers were given access to 216,221 de-identified hospital records from two major teaching hospitals, nearly 46 billion individual pieces of data. Algorithms for natural language processing were unleashed on the data automating the conversion of unruly hospital records into a machine-readable format. The resulting data were then utilized to develop predictive models of patient mortality, readmissions, length of stay and discharge diagnosis. The study was retrospective, but because hospital records are time-stamped, the data could be ordered along a timeline to simulate real-time analysis,
Inpatient mortality was predicted correctly 95% of the time compared to 85% of the time using a commercially available algorithm, and the information was available 24 hours earlier. Hospital readmissions were predicted 77% of the time compared to 70% for the hospitals current systems. Length of stay was predicted correctly 86% of the time compared with 76% for the hospitals current systems The entire set of discharge diagnosis was predicted correctly 87% of the time....Length of stay predictors and discharge diagnosis are more useful to administrators than in clinical care. Predictions of readmissions are clinically relevant because if we can understand the causes of readmission, we may be able to reduce the incidence (which typically runs at 20% of hospitalizations), improving patient care and saving the health system a great deal of money.
I have previously blogged about topics such as the use of artificial intelligence to predict which patients will "code" in the hospital, which is to say suffer cardiac arrest (see: AI Predicts Which Patients Will Code, Allowing Early Intervention). The use in the past of systems like APACHE would theoretically allow earlier intervention. What, then, is the possible value of using AI to predict inpatient mortality with a high degree of accuracy as discussed in the excerpt above. Here is a quote from my blog note referring to the initial intended purpose of the APACHE software:
An early decision support tooI...[APACHE] software ...[can be] used to assess the prognosis of patients in critical care units based on a panel of lab test results and some clinical observations. One of the initial intended uses for an Apache score for an ICU patient was to identify those near death and for whom continuing monitoring and intervention was useless. Such patients could be discharged from the critical care unit, freeing up a bed for a salvageable patient and reducing healthcare costs. However, the use of Apache for this purpose caused an uproar among some patient family members.
I suspect that most astute clinicians these days know with a high degree of certainty which of their most sick patients admitted to the hospital will die there. A discussion of such a situation would ideally be part of conversations with family members at the time of admission. It would be helpful for physicians if such a conclusion was buttressed by AI analysis such as that described above. Under such circumstances, some family members might prefer to have their relative die at home rather than in the ICU. However, such conversations are fraught with difficulty and will never be taken lightly.
Comments