Google Tech Talk April 23, 2009 ABSTRACT A Practical Computer Program that Diagnoses Diseases in Actual Patients, presented by Carlos Feder. Several so called "computer medical diagnosis programs" have been devised. We had a chance to review Internist, Quick Medical Reference (QMR), DXplain, Iliad, Gideon, Isabel, and others; some are no longer available. All this systems evoke a typically long differential diagnosis list, based on patient's symptoms, providing an excellent reminder of unusual diagnoses; however, they are unable to pinpoint the actual disease or diseases that indeed afflict a specific patient. Consequently, they are considered rather teaching or training tools for medical students or inexperienced physicians, as admitted by some of the program authors; for this reason and being quite time consuming to consult, these programs are poorly accepted and used by practicing health care providers. Our novel diagnostic system overcomes the drawbacks of existing programs, emulating as close as possible the natural reasoning of human clinicians. The core of our system is the novel mini-max procedure that computes the probability of each potential diagnosis more accurately than Bayes formula, Bayesian networks, and other similar methods; the system also diagnoses concurrent diseases that simultaneously afflict a single patient. Mini-max procedure enables to determine probabilistically and recommend at each diagnostic step the best cost-benefit clinical data next to investigate in a patient. This facilitates important overall cost saving-cost comprising expense, risk, and discomfort of obtaining clinical data-for patents and saving of available medical resources, by discouraging the ordering of futile tests or procedures. Our system is capable of diagnosing complex clinical presentations and precludes overlooking diagnoses associated with confirmed diagnoses. For all its virtues, our diagnostic system offers important socio-economic benefits that have the potential to change the way medicine will be practiced in the future; it is expected to provide invaluable benefits to patients, physicians, nurses, hospitals, health insurance companies, malpractice insurance companies and lawyers, and the entire medical establishment. Presented by Carlos Feder Carlos Feder was born in Vienna, Austria. He graduated from the School of Medicine, University of Buenos Aires, Argentina. In that country he practiced internal medicine for 30 years and at the same time taught this specialty at the University Hospital. For the past half century, his obsession to invent and improve an algorithm of computerizing medical diagnosis led him to review existing relevant literature, publish papers, and secure research grants from Roemmers pharmaceuticals. In 1983, he immigrated to Palo Alto, California, where he practiced his specialty for another 19 years before retiring in 2002. Since then he dedicated most of his time organizing his experience and novel ideas, and describing his medical diagnostic algorithm that promises to be a breakthrough in the field. Author of two books: Computerized Medical Diagnosis: a Novel Solution to an Old Problem (2006), and A Practical Computer Program that Diagnoses Diseases in Actual Patients (2008), coauthored with Tomás Feder. Email: caline@earthlink.net Tomas Feder Tomás Feder, son of Carlos, was born and grew up in Buenos Aires, Argentina. He obtained, with honors, his baccalaureate from the French School in the mentioned city. In 1983 he immigrated with his parents and sister to the United States, where he received his PHD in Computer Sciences from Stanford University. He was one of the outstanding students of his prestigious adviser Donald Knuth. Tomás worked for several years as a researcher at IBM. His curriculum includes over 120 publications, personal and with coauthors around the world. With Moshe Vardi as coauthor, they publish a landmark paper in 1993 (conference version) and in 1998 (journal version) that created a new specialty of Computer Sciences named Constraint Satisfaction, crossroads of mathematics, logic, and computer science, which became important in the field, with congresses hold worldwide, to which Tomás is always invited. Email: tomas@theory.stanford.edu http://theory.stanford.edu/~tomas

• published: 24 Apr 2009
• views: 9663