Clinical decision support with automated text processing for cervical cancer screening

Abstract

Objective: To develop a computerized clinical decision support system (CDSS) for cervical cancer screening that can interpret free-text Papanicolaou (Pap) reports.

Materials and methods: The CDSS was constituted by two rulebases: the free-text rulebase for interpreting Pap reports and a guideline rulebase. The free-text rulebase was developed by analyzing a corpus of 49 293 Pap reports. The guideline rulebase was constructed using national cervical cancer screening guidelines. The CDSS accesses the electronic medical record (EMR) system to generate patient-specific recommendations. For evaluation, the screening recommendations made by the CDSS for 74 patients were reviewed by a physician.

Results and discussion: Evaluation revealed that the CDSS outputs the optimal screening recommendations for 73 out of 74 test patients and it identified two cases for gynecology referral that were missed by the physician. The CDSS aided the physician to amend recommendations in six cases. The failure case was because human papillomavirus (HPV) testing was sometimes performed separately from the Pap test and these results were reported by a laboratory system that was not queried by the CDSS. Subsequently, the CDSS was upgraded to look up the HPV results missed earlier and it generated the optimal recommendations for all 74 test cases.

Limitations: Single institution and single expert study.

Conclusion: An accurate CDSS system could be constructed for cervical cancer screening given the standardized reporting of Pap tests and the availability of explicit guidelines. Overall, the study demonstrates that free text in the EMR can be effectively utilized through natural language processing to develop clinical decision support tools.

Figure 1

Overview of the clinical decision support system (CDSS). There are three modules: guideline engine, data module and free-text processor. The data module seeks patient information from the Mayo electronic medical record (EMR). It holds the information in a form that is amenable to the guideline engine and depends on the free-text processor to interpret free-text Papanicolaou (Pap) reports. The guideline engine and free-text processor are essentially rule-based.

Figure 2

Schematic diagram shows some of the concepts in Papanicolaou (Pap) report required for applying the national guidelines for cervical cancer screening. ASC-H, high grade squamous intraepithelial lesion; ASC-US, atypical squamous cells of undetermined significance; (ASKS), ; DNOEC, inadequate transformation zone component; GECA, glandular epithelial cell abnormality; HPV, human papillomavirus; HSIL, intraepithelial lesions categorized as high grade; LSIL, intraepithelial lesions categorized as low grade; NHPV, negative HPV test; PHPV, positive HPV test; SCC, squamous cell carcinoma; UNSAR, unsatisfactory for evaluation; NIL, negative for intraepithelial lesion or malignancy.

Figure 3

Flowchart abstraction for the guideline rulebase. ASC-US, atypical squamous cells of undetermined significance; G/C, gynecology clinic; CR, cervical cytology (Pap) report; HPV, human papillomavirus; Pap, Papanicolaou.