tetano
Editor, Senior Moderator
BMC Med Inform Decis Mak. 2015 Oct 6;15(1):78. doi: 10.1186/s12911-015-0201-3.
[h=1]Identifying influenza-like illness presentation from unstructured general practice clinical narrative using a text classifier rule-based expert system versus a clinical expert.[/h] MacRae J[SUP]1[/SUP], Love T[SUP]2[/SUP], Baker MG[SUP]3[/SUP], Dowell A[SUP]4[/SUP], Carnachan M[SUP]5[/SUP], Stubbe M[SUP]4[/SUP], McBain L[SUP]4[/SUP].
[h=3]Author information[/h]
[h=3]Abstract[/h] [h=4]BACKGROUND:[/h] We designed and validated a rule-based expert system to identify influenza like illness (ILI) from routinely recorded general practice clinical narrative to aid a larger retrospective research study into the impact of the 2009 influenza pandemic in New Zealand.
[h=4]METHODS:[/h] Rules were assessed using pattern matching heuristics on routine clinical narrative. The system was trained using data from 623 clinical encounters and validated using a clinical expert as a gold standard against a mutually exclusive set of 901 records.
[h=4]RESULTS:[/h] We calculated a 98.2 % specificity and 90.2 % sensitivity across an ILI incidence of 12.4 % measured against clinical expert classification. Peak problem list identification of ILI by clinical coding in any month was 9.2 % of all detected ILI presentations. Our system addressed an unusual problem domain for clinical narrative classification; using notational, unstructured, clinician entered information in a community care setting. It performed well compared with other approaches and domains. It has potential applications in real-time surveillance of disease, and in assisted problem list coding for clinicians.
[h=4]CONCLUSIONS:[/h] Our system identified ILI presentation with sufficient accuracy for use at a population level in the wider research study. The peak coding of 9.2 % illustrated the need for automated coding of unstructured narrative in our study.
PMID: 26445235 [PubMed - in process] PMCID: PMC4596422 Free PMC Article
[h=1]Identifying influenza-like illness presentation from unstructured general practice clinical narrative using a text classifier rule-based expert system versus a clinical expert.[/h] MacRae J[SUP]1[/SUP], Love T[SUP]2[/SUP], Baker MG[SUP]3[/SUP], Dowell A[SUP]4[/SUP], Carnachan M[SUP]5[/SUP], Stubbe M[SUP]4[/SUP], McBain L[SUP]4[/SUP].
[h=3]Author information[/h]
[h=3]Abstract[/h] [h=4]BACKGROUND:[/h] We designed and validated a rule-based expert system to identify influenza like illness (ILI) from routinely recorded general practice clinical narrative to aid a larger retrospective research study into the impact of the 2009 influenza pandemic in New Zealand.
[h=4]METHODS:[/h] Rules were assessed using pattern matching heuristics on routine clinical narrative. The system was trained using data from 623 clinical encounters and validated using a clinical expert as a gold standard against a mutually exclusive set of 901 records.
[h=4]RESULTS:[/h] We calculated a 98.2 % specificity and 90.2 % sensitivity across an ILI incidence of 12.4 % measured against clinical expert classification. Peak problem list identification of ILI by clinical coding in any month was 9.2 % of all detected ILI presentations. Our system addressed an unusual problem domain for clinical narrative classification; using notational, unstructured, clinician entered information in a community care setting. It performed well compared with other approaches and domains. It has potential applications in real-time surveillance of disease, and in assisted problem list coding for clinicians.
[h=4]CONCLUSIONS:[/h] Our system identified ILI presentation with sufficient accuracy for use at a population level in the wider research study. The peak coding of 9.2 % illustrated the need for automated coding of unstructured narrative in our study.
PMID: 26445235 [PubMed - in process] PMCID: PMC4596422 Free PMC Article