Machine learning using longitudinal prescription and medical claims for the detection of non-alcoholic steatohepatitis (NASH)
Objectives To develop and evaluate machine learning models to detect patients with suspected undiagnosed non-alcoholic steatohepatitis (NASH) for diagnostic screening and clinical management.Methods In this retrospective observational non-interventional study using administrative medical claims data...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMJ Publishing Group
2022-02-01
|
| Series: | BMJ Health & Care Informatics |
| Online Access: | https://informatics.bmj.com/content/29/1/e100510.full |
| _version_ | 1797782364501311488 |
|---|---|
| author | Orla Doyle Ozge Yasar Patrick Long Brett Harder Hanna Marshall Sanjay Bhasin Suyin Lee Mark Delegge Stephanie Roy Nadea Leavitt John Rigg |
| author_facet | Orla Doyle Ozge Yasar Patrick Long Brett Harder Hanna Marshall Sanjay Bhasin Suyin Lee Mark Delegge Stephanie Roy Nadea Leavitt John Rigg |
| author_sort | Orla Doyle |
| collection | DOAJ |
| description | Objectives To develop and evaluate machine learning models to detect patients with suspected undiagnosed non-alcoholic steatohepatitis (NASH) for diagnostic screening and clinical management.Methods In this retrospective observational non-interventional study using administrative medical claims data from 1 463 089 patients, gradient-boosted decision trees were trained to detect patients with likely NASH from an at-risk patient population with a history of obesity, type 2 diabetes mellitus, metabolic disorder or non-alcoholic fatty liver (NAFL). Models were trained to detect likely NASH in all at-risk patients or in the subset without a prior NAFL diagnosis (at-risk non-NAFL patients). Models were trained and validated using retrospective medical claims data and assessed using area under precision recall curves and receiver operating characteristic curves (AUPRCs and AUROCs).Results The 6-month incidences of NASH in claims data were 1 per 1437 at-risk patients and 1 per 2127 at-risk non-NAFL patients . The model trained to detect NASH in all at-risk patients had an AUPRC of 0.0107 (95% CI 0.0104 to 0.0110) and an AUROC of 0.84. At 10% recall, model precision was 4.3%, which is 60× above NASH incidence. The model trained to detect NASH in the non-NAFL cohort had an AUPRC of 0.0030 (95% CI 0.0029 to 0.0031) and an AUROC of 0.78. At 10% recall, model precision was 1%, which is 20× above NASH incidence.Conclusion The low incidence of NASH in medical claims data corroborates the pattern of NASH underdiagnosis in clinical practice. Claims-based machine learning could facilitate the detection of patients with probable NASH for diagnostic testing and disease management. |
| first_indexed | 2024-03-13T00:09:56Z |
| format | Article |
| id | doaj.art-b20dd3b5a65044889ee42c2709b7563a |
| institution | Directory Open Access Journal |
| issn | 2632-1009 |
| language | English |
| last_indexed | 2024-03-13T00:09:56Z |
| publishDate | 2022-02-01 |
| publisher | BMJ Publishing Group |
| record_format | Article |
| series | BMJ Health & Care Informatics |
| spelling | doaj.art-b20dd3b5a65044889ee42c2709b7563a2023-07-12T15:30:07ZengBMJ Publishing GroupBMJ Health & Care Informatics2632-10092022-02-0129110.1136/bmjhci-2021-100510Machine learning using longitudinal prescription and medical claims for the detection of non-alcoholic steatohepatitis (NASH)Orla Doyle0Ozge Yasar1Patrick Long2Brett Harder3Hanna Marshall4Sanjay Bhasin5Suyin Lee6Mark Delegge7Stephanie Roy8Nadea Leavitt9John Rigg10Real World Solutions, IQVIA, London, UKReal World Solutions, IQVIA, London, UKReal World Solutions, IQVIA, Plymouth Meeting, Pennsylvania, USAReal World Solutions, IQVIA, Plymouth Meeting, Pennsylvania, USAReal World Solutions, IQVIA, Plymouth Meeting, Pennsylvania, USAReal World Solutions, IQVIA, Plymouth Meeting, Pennsylvania, USAReal World Solutions, IQVIA, Plymouth Meeting, Pennsylvania, USATherapeutic Center of Excellence, IQVIA, Durham, North Carolina, USAReal World Solutions, IQVIA, Plymouth Meeting, Pennsylvania, USAReal World Solutions, IQVIA, Plymouth Meeting, Pennsylvania, USAReal World Solutions, IQVIA, London, UKObjectives To develop and evaluate machine learning models to detect patients with suspected undiagnosed non-alcoholic steatohepatitis (NASH) for diagnostic screening and clinical management.Methods In this retrospective observational non-interventional study using administrative medical claims data from 1 463 089 patients, gradient-boosted decision trees were trained to detect patients with likely NASH from an at-risk patient population with a history of obesity, type 2 diabetes mellitus, metabolic disorder or non-alcoholic fatty liver (NAFL). Models were trained to detect likely NASH in all at-risk patients or in the subset without a prior NAFL diagnosis (at-risk non-NAFL patients). Models were trained and validated using retrospective medical claims data and assessed using area under precision recall curves and receiver operating characteristic curves (AUPRCs and AUROCs).Results The 6-month incidences of NASH in claims data were 1 per 1437 at-risk patients and 1 per 2127 at-risk non-NAFL patients . The model trained to detect NASH in all at-risk patients had an AUPRC of 0.0107 (95% CI 0.0104 to 0.0110) and an AUROC of 0.84. At 10% recall, model precision was 4.3%, which is 60× above NASH incidence. The model trained to detect NASH in the non-NAFL cohort had an AUPRC of 0.0030 (95% CI 0.0029 to 0.0031) and an AUROC of 0.78. At 10% recall, model precision was 1%, which is 20× above NASH incidence.Conclusion The low incidence of NASH in medical claims data corroborates the pattern of NASH underdiagnosis in clinical practice. Claims-based machine learning could facilitate the detection of patients with probable NASH for diagnostic testing and disease management.https://informatics.bmj.com/content/29/1/e100510.full |
| spellingShingle | Orla Doyle Ozge Yasar Patrick Long Brett Harder Hanna Marshall Sanjay Bhasin Suyin Lee Mark Delegge Stephanie Roy Nadea Leavitt John Rigg Machine learning using longitudinal prescription and medical claims for the detection of non-alcoholic steatohepatitis (NASH) BMJ Health & Care Informatics |
| title | Machine learning using longitudinal prescription and medical claims for the detection of non-alcoholic steatohepatitis (NASH) |
| title_full | Machine learning using longitudinal prescription and medical claims for the detection of non-alcoholic steatohepatitis (NASH) |
| title_fullStr | Machine learning using longitudinal prescription and medical claims for the detection of non-alcoholic steatohepatitis (NASH) |
| title_full_unstemmed | Machine learning using longitudinal prescription and medical claims for the detection of non-alcoholic steatohepatitis (NASH) |
| title_short | Machine learning using longitudinal prescription and medical claims for the detection of non-alcoholic steatohepatitis (NASH) |
| title_sort | machine learning using longitudinal prescription and medical claims for the detection of non alcoholic steatohepatitis nash |
| url | https://informatics.bmj.com/content/29/1/e100510.full |
| work_keys_str_mv | AT orladoyle machinelearningusinglongitudinalprescriptionandmedicalclaimsforthedetectionofnonalcoholicsteatohepatitisnash AT ozgeyasar machinelearningusinglongitudinalprescriptionandmedicalclaimsforthedetectionofnonalcoholicsteatohepatitisnash AT patricklong machinelearningusinglongitudinalprescriptionandmedicalclaimsforthedetectionofnonalcoholicsteatohepatitisnash AT brettharder machinelearningusinglongitudinalprescriptionandmedicalclaimsforthedetectionofnonalcoholicsteatohepatitisnash AT hannamarshall machinelearningusinglongitudinalprescriptionandmedicalclaimsforthedetectionofnonalcoholicsteatohepatitisnash AT sanjaybhasin machinelearningusinglongitudinalprescriptionandmedicalclaimsforthedetectionofnonalcoholicsteatohepatitisnash AT suyinlee machinelearningusinglongitudinalprescriptionandmedicalclaimsforthedetectionofnonalcoholicsteatohepatitisnash AT markdelegge machinelearningusinglongitudinalprescriptionandmedicalclaimsforthedetectionofnonalcoholicsteatohepatitisnash AT stephanieroy machinelearningusinglongitudinalprescriptionandmedicalclaimsforthedetectionofnonalcoholicsteatohepatitisnash AT nadealeavitt machinelearningusinglongitudinalprescriptionandmedicalclaimsforthedetectionofnonalcoholicsteatohepatitisnash AT johnrigg machinelearningusinglongitudinalprescriptionandmedicalclaimsforthedetectionofnonalcoholicsteatohepatitisnash |