Machine beats medics at predicting heart attacks

• Autores: Aviva Rutkin
• Localización: New scientist, ISSN 0262-4079, Nº. 2981, 2014, pág. 19
• Idioma: inglés
• Texto completo no disponible (Saber más ...)
• Resumen

  • When someone shouts "Code Blue!" in a hospital, it usually means a patient needs immediate help. Sriram Somanchi of Carnegie Mellon University in Pittsburgh, and his colleagues wanted to see if a computer could predict when these emergencies were imminent. The researchers trained a machine-learning algorithm on data from 133,000 patients who visited the NorthShore University HealthSystem, a partnership of four Chicago hospitals, between 2006 and 2011. By looking at 72 parameters in patients' medical history including vital signs, age, blood glucose and platelet counts, the system guessed correctly about two-thirds of the time, while a scorecard flagged just 30% of events.