Display options
Share it on

BMJ Open. 2011 Nov 14;1(2):e000216. doi: 10.1136/bmjopen-2011-000216. Print 2011.

Mapping physicians' admission diagnoses to structured concepts towards fully automatic calculation of acute physiology and chronic health evaluation score.

BMJ open

Subhash Chandra, Rahul Kashyap, Cesar A Trillo-Alvarez, Mykola Tsapenko, Murat Yilmaz, Andrew C Hanson, Brian W Pickering, Ognjen Gajic, Vitaly Herasevich

Affiliations

  1. Division of Pulmonary and Critical Care Medicine, College of Medicine, Mayo Clinic, Rochester, Minnesota, USA.

PMID: 22102639 PMCID: PMC3221296 DOI: 10.1136/bmjopen-2011-000216

Abstract

Objective Acute Physiology and Chronic Health Evaluation (APACHE) is most widely used as a mortality prediction score in US intensive care units (ICUs), but its calculation is onerous. The authors aimed to develop and validate automatic mapping of physicians' admission diagnoses to structured concepts for automated APACHE IV calculation. Methods This retrospective study was conducted in medical ICUs of a tertiary healthcare and academic centre. Boolean-logic text searches were used to map admission diagnoses, and these were compared with conventional APACHE database entry by bedside nurses and a gold-standard physician chart review. The primary outcome was APACHE IV predicted hospital mortality. The tool was developed in a larger cohort of ICU patients. Results In a derivation cohort of 192 consecutive critically ill patients, the diagnosis coefficient coded by three different methods had a positive correlation, highest between manual and gold standard (r(2)=0.95; mean square error (MSE)=0.040) and least between manual and automatic tool (r(2)=0.88; MSE=0.066). The automatic tool had an area under the curve (95% CI) value of 0.82 (0.74 to 0.90) which was similar to the physician gold standard, 0.83 (0.75 to 0.91) and standard manual entry, 0.81 (0.73 to 0.89). The Hosmer-Lemeshow goodness-of-fit test demonstrated good calibration of automatically calculated APACHE IV score (χ(2)=6.46; p=0.6). The automatic tool demonstrated excellent discrimination with an area under the curve value of 0.87 (95% CI 0.83 to 0.92) and good calibration (p=0.58) in the validation cohort of 593 patients. Conclusion A Boolean-logic text search is an efficient alternative to manual database entry for mapping of ICU admission diagnosis to structured APACHE IV concepts.

References

  1. Intensive Care Med. 2005 Nov;31(11):1471-3 - PubMed
  2. Am J Surg. 1987 Jul;154(1):72-8 - PubMed
  3. Intensive Care Med. 1995 Sep;21(9):703-15 - PubMed
  4. Mayo Clin Proc. 2010 Mar;85(3):247-54 - PubMed
  5. Am J Contact Dermat. 1998 Sep;9(3):176-8 - PubMed
  6. Chest. 1991 Dec;100(6):1619-36 - PubMed
  7. JAMA. 1994 Oct 5;272(13):1049-55 - PubMed
  8. Crit Care Med. 1985 Oct;13(10):818-29 - PubMed
  9. Am J Public Health. 1983 Aug;73(8):878-84 - PubMed
  10. Int J Med Inform. 2002 Jun;65(2):145-57 - PubMed
  11. Crit Care Med. 1981 Aug;9(8):591-7 - PubMed
  12. Anaesth Intensive Care. 2003 Oct;31(5):548-54 - PubMed
  13. Crit Care Med. 2006 May;34(5):1297-310 - PubMed
  14. BMC Med Inform Decis Mak. 2006 Jan 05;6:1 - PubMed
  15. Stud Health Technol Inform. 2008;136:779-84 - PubMed
  16. Crit Care Med. 1999 Sep;27(9):1999-2004 - PubMed
  17. Chest. 2008 Jun;133(6):1319-1327 - PubMed
  18. Intensive Care Med. 2001 Aug;27(8):1365-9 - PubMed
  19. Intensive Care Med. 2001 Sep;27(9):1550-2 - PubMed

Publication Types

Grant support