Identifying long-term conditions in New Zealand general practice using structured and unstructured data: a cross-sectional study
Objectives This study examined whether incorporating free-text entries into structured general practice records improves the detection of long-term conditions (LTCs) and multimorbidity (MM) in New Zealand (NZ) general practices.Methods Data from 374 071 deidentified individuals in general practices...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMJ Publishing Group
2025-05-01
|
| Series: | BMJ Health & Care Informatics |
| Online Access: | https://informatics.bmj.com/content/32/1/e101393.full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850153061007228928 |
|---|---|
| author | Vanessa Selak Katrina Poppe Sue Wells Yeunhyang Catherine Choi Allan Ronald Moffitt Claris Yee Seung Chung Jane Ullmer |
| author_facet | Vanessa Selak Katrina Poppe Sue Wells Yeunhyang Catherine Choi Allan Ronald Moffitt Claris Yee Seung Chung Jane Ullmer |
| author_sort | Vanessa Selak |
| collection | DOAJ |
| description | Objectives This study examined whether incorporating free-text entries into structured general practice records improves the detection of long-term conditions (LTCs) and multimorbidity (MM) in New Zealand (NZ) general practices.Methods Data from 374 071 deidentified individuals in general practices were analysed to identify 61 LTCs. Structured data were extracted using Read codes from a national master list, and clinical raters independently identified condition-related free-text, including synonyms, negation terms and common misspellings in randomised samples. Keywords were categorised and refined through ten iterative tests. Programmatic text classification was developed and assessed against gold-standard clinician ratings, using sensitivity, specificity, positive predictive value (PPV) and F1-score.Results A quarter of general practitioner classifications contained either unrecognised Read codes or consisted of free-text only. Clinician inter-rater reliability was high (kappa ≥0.9). Compared with clinical gold standard, text classification yielded an average sensitivity of 88%, specificity of 99% and PPV of 95%, with an F1-score range of 82%–95%. Incorporating free text increased LTC prevalence from 42.1% to 46.3%, reducing misclassification of MM diagnoses by identifying 12 626 additional patients with MM and 15 972 additional patients with at least one LTC.Discussion In the course of workflow, general practitioners face barriers to accurate LTC coding or may simply annotate with text-based descriptions. Programmatic text classification has demonstrated high performance and identified many more patients receiving LTC care.Conclusions Combining structured and unstructured data optimises MM detection in NZ general practices and has the potential to improve case management, follow-up care and allocation of healthcare resources. |
| format | Article |
| id | doaj-art-710baa52db5d415e99f847a2f6741b5b |
| institution | OA Journals |
| issn | 2632-1009 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | BMJ Publishing Group |
| record_format | Article |
| series | BMJ Health & Care Informatics |
| spelling | doaj-art-710baa52db5d415e99f847a2f6741b5b2025-08-20T02:25:49ZengBMJ Publishing GroupBMJ Health & Care Informatics2632-10092025-05-0132110.1136/bmjhci-2024-101393Identifying long-term conditions in New Zealand general practice using structured and unstructured data: a cross-sectional studyVanessa Selak0Katrina Poppe1Sue Wells2Yeunhyang Catherine Choi3Allan Ronald Moffitt4Claris Yee Seung Chung5Jane Ullmer6Section of Epidemiology and Biostatistics, School of Population Health, Faculty of Medical and Health Sciences, The University of Auckland, Auckland, New ZealandDepartment of Medicine, University of Auckland, Auckland, New ZealandHospice of St Francis, Berkhamsted, Central London Community Healthcare NHS TrustDepartment of Epidemiology and Biostatistics, University of Auckland, Auckland, New ZealandProcare Health Limited, Auckland, New ZealandDepartment of Accounting and Information Systems, University of Canterbury, Christchurch, New ZealandSchool of Population Health, The University of Auckland Faculty of Medical and Health Sciences, Auckland, New ZealandObjectives This study examined whether incorporating free-text entries into structured general practice records improves the detection of long-term conditions (LTCs) and multimorbidity (MM) in New Zealand (NZ) general practices.Methods Data from 374 071 deidentified individuals in general practices were analysed to identify 61 LTCs. Structured data were extracted using Read codes from a national master list, and clinical raters independently identified condition-related free-text, including synonyms, negation terms and common misspellings in randomised samples. Keywords were categorised and refined through ten iterative tests. Programmatic text classification was developed and assessed against gold-standard clinician ratings, using sensitivity, specificity, positive predictive value (PPV) and F1-score.Results A quarter of general practitioner classifications contained either unrecognised Read codes or consisted of free-text only. Clinician inter-rater reliability was high (kappa ≥0.9). Compared with clinical gold standard, text classification yielded an average sensitivity of 88%, specificity of 99% and PPV of 95%, with an F1-score range of 82%–95%. Incorporating free text increased LTC prevalence from 42.1% to 46.3%, reducing misclassification of MM diagnoses by identifying 12 626 additional patients with MM and 15 972 additional patients with at least one LTC.Discussion In the course of workflow, general practitioners face barriers to accurate LTC coding or may simply annotate with text-based descriptions. Programmatic text classification has demonstrated high performance and identified many more patients receiving LTC care.Conclusions Combining structured and unstructured data optimises MM detection in NZ general practices and has the potential to improve case management, follow-up care and allocation of healthcare resources.https://informatics.bmj.com/content/32/1/e101393.full |
| spellingShingle | Vanessa Selak Katrina Poppe Sue Wells Yeunhyang Catherine Choi Allan Ronald Moffitt Claris Yee Seung Chung Jane Ullmer Identifying long-term conditions in New Zealand general practice using structured and unstructured data: a cross-sectional study BMJ Health & Care Informatics |
| title | Identifying long-term conditions in New Zealand general practice using structured and unstructured data: a cross-sectional study |
| title_full | Identifying long-term conditions in New Zealand general practice using structured and unstructured data: a cross-sectional study |
| title_fullStr | Identifying long-term conditions in New Zealand general practice using structured and unstructured data: a cross-sectional study |
| title_full_unstemmed | Identifying long-term conditions in New Zealand general practice using structured and unstructured data: a cross-sectional study |
| title_short | Identifying long-term conditions in New Zealand general practice using structured and unstructured data: a cross-sectional study |
| title_sort | identifying long term conditions in new zealand general practice using structured and unstructured data a cross sectional study |
| url | https://informatics.bmj.com/content/32/1/e101393.full |
| work_keys_str_mv | AT vanessaselak identifyinglongtermconditionsinnewzealandgeneralpracticeusingstructuredandunstructureddataacrosssectionalstudy AT katrinapoppe identifyinglongtermconditionsinnewzealandgeneralpracticeusingstructuredandunstructureddataacrosssectionalstudy AT suewells identifyinglongtermconditionsinnewzealandgeneralpracticeusingstructuredandunstructureddataacrosssectionalstudy AT yeunhyangcatherinechoi identifyinglongtermconditionsinnewzealandgeneralpracticeusingstructuredandunstructureddataacrosssectionalstudy AT allanronaldmoffitt identifyinglongtermconditionsinnewzealandgeneralpracticeusingstructuredandunstructureddataacrosssectionalstudy AT clarisyeeseungchung identifyinglongtermconditionsinnewzealandgeneralpracticeusingstructuredandunstructureddataacrosssectionalstudy AT janeullmer identifyinglongtermconditionsinnewzealandgeneralpracticeusingstructuredandunstructureddataacrosssectionalstudy |