Development and validation of a novel risk prediction algorithm to estimate 10-year risk of oesophageal cancer in primary care: prospective cohort study and evaluation of performance against two other risk prediction models
<strong>Background<br></strong> Methods to identify patients at increased risk of oesophageal cancer are needed to better identify those for targeted screening. We aimed to derive and validate novel risk prediction algorithms (CanPredict) to estimate the 10-year risk of oesophageal...
| Main Authors: | , , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
Elsevier
2023
|
| _version_ | 1797110838230777856 |
|---|---|
| author | Hippisley-Cox, J Mei, W Fitzgerald, R Coupland, C |
| author_facet | Hippisley-Cox, J Mei, W Fitzgerald, R Coupland, C |
| author_sort | Hippisley-Cox, J |
| collection | OXFORD |
| description | <strong>Background<br></strong>
Methods to identify patients at increased risk of oesophageal cancer are needed to better identify those for targeted screening. We aimed to derive and validate novel risk prediction algorithms (CanPredict) to estimate the 10-year risk of oesophageal cancer and evaluate performance against two other risk prediction models.
<br><strong>Methods<br></strong>
Prospective open cohort study using routinely collected data from 1804 QResearch® general practices. We used 1354 practices (12.9 M patients) to develop the algorithm. We validated the algorithm in 450 separate practices from QResearch (4.12 M patients) and 355 Clinical Practice Research Datalink (CPRD) practices (2.53 M patients). The primary outcome was an incident diagnosis of oesophageal cancer found in GP, mortality, hospital, or cancer registry data. Patients were aged 25–84 years and free of oesophageal cancer at baseline. Cox proportional hazards models were used with prediction selection to derive risk equations. Risk factors included age, ethnicity, Townsend deprivation score, body mass index (BMI), smoking, alcohol, family history, relevant co-morbidities and medications. Measures of calibration, discrimination, sensitivity, and specificity were calculated in the validation cohorts.
<br><strong>Finding<br></strong>
There were 16,384 incident cases of oesophageal cancer in the derivation cohort (0.13% of 12.9 M). The predictors in the final algorithms were: age, BMI, Townsend deprivation score, smoking, alcohol, ethnicity, Barrett's oesophagus, hiatus hernia, H. pylori infection, use of proton pump inhibitors, anaemia, lung and blood cancer (with breast cancer in women). In the QResearch validation cohort in women the explained variation (R2) was 57.1%; Royston’s D statistic 2.36 (95% CI 2.26–2.46); C statistic 0.859 (95% CI 0.849–0.868) and calibration was good. Results were similar in men. For the 20% at highest predicted risk, the sensitivity was 76%, specificity was 80.1% and the observed risk at 10 years was 0.76%. The results from the CPRD validation were similar.
<br><strong>Interpretation<br></strong>
We have developed and validated a novel prediction algorithm to quantify the absolute risk of oesophageal cancer. The CanPredict algorithms could be used to identify high risk patients for targeted screening.
<br><strong>Funding<br></strong>
Innovate UK and CRUK (grant 105857). |
| first_indexed | 2024-03-07T08:00:21Z |
| format | Journal article |
| id | oxford-uuid:595ee69e-1461-4d55-9831-fc82c0dbd517 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T08:00:21Z |
| publishDate | 2023 |
| publisher | Elsevier |
| record_format | dspace |
| spelling | oxford-uuid:595ee69e-1461-4d55-9831-fc82c0dbd5172023-09-26T13:29:51ZDevelopment and validation of a novel risk prediction algorithm to estimate 10-year risk of oesophageal cancer in primary care: prospective cohort study and evaluation of performance against two other risk prediction modelsJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:595ee69e-1461-4d55-9831-fc82c0dbd517EnglishSymplectic ElementsElsevier2023Hippisley-Cox, JMei, WFitzgerald, RCoupland, C<strong>Background<br></strong> Methods to identify patients at increased risk of oesophageal cancer are needed to better identify those for targeted screening. We aimed to derive and validate novel risk prediction algorithms (CanPredict) to estimate the 10-year risk of oesophageal cancer and evaluate performance against two other risk prediction models. <br><strong>Methods<br></strong> Prospective open cohort study using routinely collected data from 1804 QResearch® general practices. We used 1354 practices (12.9 M patients) to develop the algorithm. We validated the algorithm in 450 separate practices from QResearch (4.12 M patients) and 355 Clinical Practice Research Datalink (CPRD) practices (2.53 M patients). The primary outcome was an incident diagnosis of oesophageal cancer found in GP, mortality, hospital, or cancer registry data. Patients were aged 25–84 years and free of oesophageal cancer at baseline. Cox proportional hazards models were used with prediction selection to derive risk equations. Risk factors included age, ethnicity, Townsend deprivation score, body mass index (BMI), smoking, alcohol, family history, relevant co-morbidities and medications. Measures of calibration, discrimination, sensitivity, and specificity were calculated in the validation cohorts. <br><strong>Finding<br></strong> There were 16,384 incident cases of oesophageal cancer in the derivation cohort (0.13% of 12.9 M). The predictors in the final algorithms were: age, BMI, Townsend deprivation score, smoking, alcohol, ethnicity, Barrett's oesophagus, hiatus hernia, H. pylori infection, use of proton pump inhibitors, anaemia, lung and blood cancer (with breast cancer in women). In the QResearch validation cohort in women the explained variation (R2) was 57.1%; Royston’s D statistic 2.36 (95% CI 2.26–2.46); C statistic 0.859 (95% CI 0.849–0.868) and calibration was good. Results were similar in men. For the 20% at highest predicted risk, the sensitivity was 76%, specificity was 80.1% and the observed risk at 10 years was 0.76%. The results from the CPRD validation were similar. <br><strong>Interpretation<br></strong> We have developed and validated a novel prediction algorithm to quantify the absolute risk of oesophageal cancer. The CanPredict algorithms could be used to identify high risk patients for targeted screening. <br><strong>Funding<br></strong> Innovate UK and CRUK (grant 105857). |
| spellingShingle | Hippisley-Cox, J Mei, W Fitzgerald, R Coupland, C Development and validation of a novel risk prediction algorithm to estimate 10-year risk of oesophageal cancer in primary care: prospective cohort study and evaluation of performance against two other risk prediction models |
| title | Development and validation of a novel risk prediction algorithm to estimate 10-year risk of oesophageal cancer in primary care: prospective cohort study and evaluation of performance against two other risk prediction models |
| title_full | Development and validation of a novel risk prediction algorithm to estimate 10-year risk of oesophageal cancer in primary care: prospective cohort study and evaluation of performance against two other risk prediction models |
| title_fullStr | Development and validation of a novel risk prediction algorithm to estimate 10-year risk of oesophageal cancer in primary care: prospective cohort study and evaluation of performance against two other risk prediction models |
| title_full_unstemmed | Development and validation of a novel risk prediction algorithm to estimate 10-year risk of oesophageal cancer in primary care: prospective cohort study and evaluation of performance against two other risk prediction models |
| title_short | Development and validation of a novel risk prediction algorithm to estimate 10-year risk of oesophageal cancer in primary care: prospective cohort study and evaluation of performance against two other risk prediction models |
| title_sort | development and validation of a novel risk prediction algorithm to estimate 10 year risk of oesophageal cancer in primary care prospective cohort study and evaluation of performance against two other risk prediction models |
| work_keys_str_mv | AT hippisleycoxj developmentandvalidationofanovelriskpredictionalgorithmtoestimate10yearriskofoesophagealcancerinprimarycareprospectivecohortstudyandevaluationofperformanceagainsttwootherriskpredictionmodels AT meiw developmentandvalidationofanovelriskpredictionalgorithmtoestimate10yearriskofoesophagealcancerinprimarycareprospectivecohortstudyandevaluationofperformanceagainsttwootherriskpredictionmodels AT fitzgeraldr developmentandvalidationofanovelriskpredictionalgorithmtoestimate10yearriskofoesophagealcancerinprimarycareprospectivecohortstudyandevaluationofperformanceagainsttwootherriskpredictionmodels AT couplandc developmentandvalidationofanovelriskpredictionalgorithmtoestimate10yearriskofoesophagealcancerinprimarycareprospectivecohortstudyandevaluationofperformanceagainsttwootherriskpredictionmodels |