Thursday, February 25, 2016


Bad Data In,  Bad Data Out (BDI, BDO)
It's elementary,  my dear Watson!
Attributed to  Sherlock Holmes
As  I work on my new book,   Noise!! Until the 2016 Election Results Are Known, The  Health Debate Is Mostly Noise, two articles came to my attention:
One,  “The Big Data Future Has Arrived, “(WSJ, February 24) by Michael S. Malone,  a prolific writer on social issues,  in which he argues  powerful computers, ubiquitous sensors,  and the Web will transform our lives by making the connections between  man and machine more personal, productive, and empowering.

Two,  “Will Feeding Watson $3 Billion Worth of Healthcare Data Improve Its Decisions “? by  Ross Koppel, PhD and Frank Meissner, MD in The Health Care Blog, February 24.   Koppel is a senior fellow at the Leonard Davis School of Economics (Wharton) and Meissner is  a cardiologist in El Paso,  Texas.    The two ask whether IBM’s purchase of Truven Health Analytics,  and payer and patient data  at the Cleveland Clinic’s “Explory’s” and Phytel, a software company,  will improve health care. 
Watson,   IBM’s  computer system, is designed by  analyzing health care  data to create artificial intelligence  to supplement  human intelligence to improve health care outcomes.   
The two  authors’ central  questions are:
Will flawed  data from payers, physicians,   and patients,  each inaccurate and biased on their own ways,  be misleading or wise guides to future care?   
Will this data, in their words, produce “digital flatulence” or “digital decisiveness”? 
Will Watson’s $3 billion  diet of undigested data produce more noise than knowledge?
Their  answers, like the data, is ambiguous , because: 
 Medicine is an art rather than a science,  data collection  is full of ambiguities.
Clinicians are often rushed and confronted with  limited time constraints, unfriendly EHR interfaces  and a byzantine list of 68.000 codes to pick from,  the EHR output is imprecise and flawed.
Hospitals  often enter EHR data calculated to maximize DRG revenues, that data is biased towards procedures,  such as expensive cardiac workups even though the diagnosis of coronary artery disease is at best,  ambigious.    It’s rare,” they say, “ to find a patient admitted to a hospital with chest pain who is not admitted as anything other than Acute Coronary Syndrome (ACS)—rather than a less expensive diagnosis.
Patients are often not forthcoming about their lives for reasons of embarrassment, privacy concerns.   Patients  have understandable, primarily economic reasons to deceive about their health insurance. They may be using the name of a friend or relative who has health insurance, they may have a spouse’s or ex-spouse’s insurance, they may wish not to have certain procedures or conditions shown on their insurance records.
As I write in my book,   there are other  confusing noise pollution factors as well:
·         The Noise over the clash of cultures between health care proponents and followers. 

·         The Noise between President Obama’s ideology and its economic consequences.

·         The Noise of  physician demoralization,  shortages, and passive resistance.

·         The Noise of middle class discontent over broken promises of lower costs and keeping your doctor and health plan. 

·         The Noise over Negative Forecasts  predicting ObamaCare repeal.
Because of these multiple sources of confusing background Noise and because of the bias inherent in the  payer, physician, and patient sources of data,  Watson’s quest for enlightment through sheer data  may be a case of  BDI, BDO (Bad Data In,   Bad Data Out). 
 Still, as Koppel and Meissner argue,  IBM’s quest for data Holy Grail is worth a try, why not give it a shot?  

No comments: