An artificial intelligence based app for skin cancer detection evaluated in a population based setting
Abstract Artificial intelligence (AI) based algorithms for classification of suspicious skin lesions have been implemented in mobile phone apps (mHealth), but their effect on healthcare systems is undocumented. In 2019, a large Dutch health insurance company offered 2.2 million adults free access to...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-05-01
|
| Series: | npj Digital Medicine |
| Online Access: | https://doi.org/10.1038/s41746-023-00831-w |
| _version_ | 1797422457563381760 |
|---|---|
| author | Anna M. Smak Gregoor Tobias E. Sangers Lytske J. Bakker Loes Hollestein Carin A. Uyl – de Groot Tamar Nijsten Marlies Wakkee |
| author_facet | Anna M. Smak Gregoor Tobias E. Sangers Lytske J. Bakker Loes Hollestein Carin A. Uyl – de Groot Tamar Nijsten Marlies Wakkee |
| author_sort | Anna M. Smak Gregoor |
| collection | DOAJ |
| description | Abstract Artificial intelligence (AI) based algorithms for classification of suspicious skin lesions have been implemented in mobile phone apps (mHealth), but their effect on healthcare systems is undocumented. In 2019, a large Dutch health insurance company offered 2.2 million adults free access to an mHealth app for skin cancer detection. To study the impact on dermatological healthcare consumption, we conducted a retrospective population-based pragmatic study. We matched 18,960 mHealth-users who completed at least one successful assessment with the app to 56,880 controls who did not use the app and calculated odds ratios (OR) to compare dermatological claims between both groups in the first year after granting free access. A short-term cost-effectiveness analysis was performed to determine the cost per additional detected (pre)malignancy. Here we report that mHealth-users had more claims for (pre)malignant skin lesions than controls (6.0% vs 4.6%, OR 1.3 (95% CI 1.2–1.4)) and also a more than threefold higher risk of claims for benign skin tumors and nevi (5.9% vs 1.7%, OR 3.7 (95% CI 3.4–4.1)). The costs of detecting one additional (pre)malignant skin lesion with the app compared to the current standard of care were €2567. Based on these results, AI in mHealth appears to have a positive impact on detecting more cutaneous (pre)malignancies, but this should be balanced against the for now stronger increase in care consumption for benign skin tumors and nevi. |
| first_indexed | 2024-03-09T07:32:35Z |
| format | Article |
| id | doaj.art-b94b3b48fe434d1b8be9fee3709df98c |
| institution | Directory Open Access Journal |
| issn | 2398-6352 |
| language | English |
| last_indexed | 2024-03-09T07:32:35Z |
| publishDate | 2023-05-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Digital Medicine |
| spelling | doaj.art-b94b3b48fe434d1b8be9fee3709df98c2023-12-03T06:06:46ZengNature Portfolionpj Digital Medicine2398-63522023-05-01611810.1038/s41746-023-00831-wAn artificial intelligence based app for skin cancer detection evaluated in a population based settingAnna M. Smak Gregoor0Tobias E. Sangers1Lytske J. Bakker2Loes Hollestein3Carin A. Uyl – de Groot4Tamar Nijsten5Marlies Wakkee6Department of Dermatology, Erasmus MC Cancer Institute, University Medical Center RotterdamDepartment of Dermatology, Erasmus MC Cancer Institute, University Medical Center RotterdamErasmus School of Health Policy & Management, Erasmus University RotterdamDepartment of Dermatology, Erasmus MC Cancer Institute, University Medical Center RotterdamErasmus School of Health Policy & Management, Erasmus University RotterdamDepartment of Dermatology, Erasmus MC Cancer Institute, University Medical Center RotterdamDepartment of Dermatology, Erasmus MC Cancer Institute, University Medical Center RotterdamAbstract Artificial intelligence (AI) based algorithms for classification of suspicious skin lesions have been implemented in mobile phone apps (mHealth), but their effect on healthcare systems is undocumented. In 2019, a large Dutch health insurance company offered 2.2 million adults free access to an mHealth app for skin cancer detection. To study the impact on dermatological healthcare consumption, we conducted a retrospective population-based pragmatic study. We matched 18,960 mHealth-users who completed at least one successful assessment with the app to 56,880 controls who did not use the app and calculated odds ratios (OR) to compare dermatological claims between both groups in the first year after granting free access. A short-term cost-effectiveness analysis was performed to determine the cost per additional detected (pre)malignancy. Here we report that mHealth-users had more claims for (pre)malignant skin lesions than controls (6.0% vs 4.6%, OR 1.3 (95% CI 1.2–1.4)) and also a more than threefold higher risk of claims for benign skin tumors and nevi (5.9% vs 1.7%, OR 3.7 (95% CI 3.4–4.1)). The costs of detecting one additional (pre)malignant skin lesion with the app compared to the current standard of care were €2567. Based on these results, AI in mHealth appears to have a positive impact on detecting more cutaneous (pre)malignancies, but this should be balanced against the for now stronger increase in care consumption for benign skin tumors and nevi.https://doi.org/10.1038/s41746-023-00831-w |
| spellingShingle | Anna M. Smak Gregoor Tobias E. Sangers Lytske J. Bakker Loes Hollestein Carin A. Uyl – de Groot Tamar Nijsten Marlies Wakkee An artificial intelligence based app for skin cancer detection evaluated in a population based setting npj Digital Medicine |
| title | An artificial intelligence based app for skin cancer detection evaluated in a population based setting |
| title_full | An artificial intelligence based app for skin cancer detection evaluated in a population based setting |
| title_fullStr | An artificial intelligence based app for skin cancer detection evaluated in a population based setting |
| title_full_unstemmed | An artificial intelligence based app for skin cancer detection evaluated in a population based setting |
| title_short | An artificial intelligence based app for skin cancer detection evaluated in a population based setting |
| title_sort | artificial intelligence based app for skin cancer detection evaluated in a population based setting |
| url | https://doi.org/10.1038/s41746-023-00831-w |
| work_keys_str_mv | AT annamsmakgregoor anartificialintelligencebasedappforskincancerdetectionevaluatedinapopulationbasedsetting AT tobiasesangers anartificialintelligencebasedappforskincancerdetectionevaluatedinapopulationbasedsetting AT lytskejbakker anartificialintelligencebasedappforskincancerdetectionevaluatedinapopulationbasedsetting AT loeshollestein anartificialintelligencebasedappforskincancerdetectionevaluatedinapopulationbasedsetting AT carinauyldegroot anartificialintelligencebasedappforskincancerdetectionevaluatedinapopulationbasedsetting AT tamarnijsten anartificialintelligencebasedappforskincancerdetectionevaluatedinapopulationbasedsetting AT marlieswakkee anartificialintelligencebasedappforskincancerdetectionevaluatedinapopulationbasedsetting AT annamsmakgregoor artificialintelligencebasedappforskincancerdetectionevaluatedinapopulationbasedsetting AT tobiasesangers artificialintelligencebasedappforskincancerdetectionevaluatedinapopulationbasedsetting AT lytskejbakker artificialintelligencebasedappforskincancerdetectionevaluatedinapopulationbasedsetting AT loeshollestein artificialintelligencebasedappforskincancerdetectionevaluatedinapopulationbasedsetting AT carinauyldegroot artificialintelligencebasedappforskincancerdetectionevaluatedinapopulationbasedsetting AT tamarnijsten artificialintelligencebasedappforskincancerdetectionevaluatedinapopulationbasedsetting AT marlieswakkee artificialintelligencebasedappforskincancerdetectionevaluatedinapopulationbasedsetting |