Reimagining leprosy elimination with AI analysis of a combination of skin lesion images with demographic and clinical data
Summary: Background: Leprosy is an infectious disease that mostly affects underserved populations. Although it has been largely eliminated, still about 200’000 new patients are diagnosed annually. In the absence of a diagnostic test, clinical diagnosis is often delayed, potentially leading to irrev...
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-05-01
|
| Series: | The Lancet Regional Health. Americas |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2667193X22000096 |
| _version_ | 1798031299647111168 |
|---|---|
| author | Raquel R Barbieri Yixi Xu Lucy Setian Paulo Thiago Souza-Santos Anusua Trivedi Jim Cristofono Ricardo Bhering Kevin White Anna M Sales Geralyn Miller José Augusto C Nery Michael Sharman Richard Bumann Shun Zhang Mohamad Goldust Euzenir N Sarno Fareed Mirza Arielle Cavaliero Sander Timmer Elena Bonfiglioli Cairns Smith David Scollard Alexander A. Navarini Ann Aerts Juan Lavista Ferres Milton O Moraes |
| author_facet | Raquel R Barbieri Yixi Xu Lucy Setian Paulo Thiago Souza-Santos Anusua Trivedi Jim Cristofono Ricardo Bhering Kevin White Anna M Sales Geralyn Miller José Augusto C Nery Michael Sharman Richard Bumann Shun Zhang Mohamad Goldust Euzenir N Sarno Fareed Mirza Arielle Cavaliero Sander Timmer Elena Bonfiglioli Cairns Smith David Scollard Alexander A. Navarini Ann Aerts Juan Lavista Ferres Milton O Moraes |
| author_sort | Raquel R Barbieri |
| collection | DOAJ |
| description | Summary: Background: Leprosy is an infectious disease that mostly affects underserved populations. Although it has been largely eliminated, still about 200’000 new patients are diagnosed annually. In the absence of a diagnostic test, clinical diagnosis is often delayed, potentially leading to irreversible neurological damage and its resulting stigma, as well as continued transmission. Accelerating diagnosis could significantly contribute to advancing global leprosy elimination. Digital and Artificial Intelligence (AI) driven technology has shown potential to augment health workers abilities in making faster and more accurate diagnosis, especially when using images such as in the fields of dermatology or ophthalmology. That made us start the quest for an AI-driven diagnosis assistant for leprosy, based on skin images. Methods: Here we describe the accuracy of an AI-enabled image-based diagnosis assistant for leprosy, called AI4Leprosy, based on a combination of skin images and clinical data, collected following a standardized process. In a Brazilian leprosy national referral center, 222 patients with leprosy or other dermatological conditions were included, and the 1229 collected skin images and 585 sets of metadata are stored in an open-source dataset for other researchers to exploit. Findings: We used this dataset to test whether a CNN-based AI algorithm could contribute to leprosy diagnosis and employed three AI models, testing images and metadata both independently and in combination. AI modeling indicated that the most important clinical signs are thermal sensitivity loss, nodules and papules, feet paresthesia, number of lesions and gender, but also scaling surface and pruritus that were negatively associated with leprosy. Using elastic-net logistic regression provided a high classification accuracy (90%) and an area under curve (AUC) of 96.46% for leprosy diagnosis. Interpretation: Future validation of these models is underway, gathering larger datasets from populations of different skin types and collecting images with smartphone cameras to mimic real world settings. We hope that the results of our research will lead to clinical solutions that help accelerate global leprosy elimination. Funding: This study was partially funded by Novartis Foundation and Microsoft (in-kind contribution). |
| first_indexed | 2024-04-11T19:55:15Z |
| format | Article |
| id | doaj.art-ccad78b88ee84cb8805d06dcf969f795 |
| institution | Directory Open Access Journal |
| issn | 2667-193X |
| language | English |
| last_indexed | 2024-04-11T19:55:15Z |
| publishDate | 2022-05-01 |
| publisher | Elsevier |
| record_format | Article |
| series | The Lancet Regional Health. Americas |
| spelling | doaj.art-ccad78b88ee84cb8805d06dcf969f7952022-12-22T04:06:11ZengElsevierThe Lancet Regional Health. Americas2667-193X2022-05-019100192Reimagining leprosy elimination with AI analysis of a combination of skin lesion images with demographic and clinical dataRaquel R Barbieri0Yixi Xu1Lucy Setian2Paulo Thiago Souza-Santos3Anusua Trivedi4Jim Cristofono5Ricardo Bhering6Kevin White7Anna M Sales8Geralyn Miller9José Augusto C Nery10Michael Sharman11Richard Bumann12Shun Zhang13Mohamad Goldust14Euzenir N Sarno15Fareed Mirza16Arielle Cavaliero17Sander Timmer18Elena Bonfiglioli19Cairns Smith20David Scollard21Alexander A. Navarini22Ann Aerts23Juan Lavista Ferres24Milton O Moraes25Laboratório de Hanseníase Instituto Oswaldo Cruz, Fundação Oswaldo Cruz, Fiocruz, Rio de Janeiro, Brazil; Corresponding authors.Microsoft, One Microsoft Way, One Microsoft Way, Redmond, WA, United States; Corresponding authors.Novartis Foundation, Basel, SwitzerlandLaboratório de Hanseníase Instituto Oswaldo Cruz, Fundação Oswaldo Cruz, Fiocruz, Rio de Janeiro, BrazilMicrosoft, One Microsoft Way, One Microsoft Way, Redmond, WA, United StatesMicrosoft, One Microsoft Way, One Microsoft Way, Redmond, WA, United StatesLaboratório de Hanseníase Instituto Oswaldo Cruz, Fundação Oswaldo Cruz, Fiocruz, Rio de Janeiro, BrazilMicrosoft, One Microsoft Way, One Microsoft Way, Redmond, WA, United StatesLaboratório de Hanseníase Instituto Oswaldo Cruz, Fundação Oswaldo Cruz, Fiocruz, Rio de Janeiro, BrazilMicrosoft, One Microsoft Way, One Microsoft Way, Redmond, WA, United StatesLaboratório de Hanseníase Instituto Oswaldo Cruz, Fundação Oswaldo Cruz, Fiocruz, Rio de Janeiro, BrazilMicrosoft, One Microsoft Way, One Microsoft Way, Redmond, WA, United StatesMicrosoft, One Microsoft Way, One Microsoft Way, Redmond, WA, United StatesMicrosoft, One Microsoft Way, One Microsoft Way, Redmond, WA, United StatesUniversity of Basel, Basel, Switzerland; Department of Dermatology, University Medical Center Mainz, Mainz, GermanyLaboratório de Hanseníase Instituto Oswaldo Cruz, Fundação Oswaldo Cruz, Fiocruz, Rio de Janeiro, BrazilNovartis Foundation, Basel, SwitzerlandNovartis Foundation, Basel, SwitzerlandMicrosoft, One Microsoft Way, One Microsoft Way, Redmond, WA, United StatesMicrosoft, One Microsoft Way, One Microsoft Way, Redmond, WA, United StatesUniversity of Aberdeen, Aberdeen, ScotlandRetired, Wilbraham, MA, United StatesUniversity of Basel, Basel, SwitzerlandNovartis Foundation, Basel, SwitzerlandMicrosoft, One Microsoft Way, One Microsoft Way, Redmond, WA, United States; Corresponding authors.Laboratório de Hanseníase Instituto Oswaldo Cruz, Fundação Oswaldo Cruz, Fiocruz, Rio de Janeiro, Brazil; Corresponding authors.Summary: Background: Leprosy is an infectious disease that mostly affects underserved populations. Although it has been largely eliminated, still about 200’000 new patients are diagnosed annually. In the absence of a diagnostic test, clinical diagnosis is often delayed, potentially leading to irreversible neurological damage and its resulting stigma, as well as continued transmission. Accelerating diagnosis could significantly contribute to advancing global leprosy elimination. Digital and Artificial Intelligence (AI) driven technology has shown potential to augment health workers abilities in making faster and more accurate diagnosis, especially when using images such as in the fields of dermatology or ophthalmology. That made us start the quest for an AI-driven diagnosis assistant for leprosy, based on skin images. Methods: Here we describe the accuracy of an AI-enabled image-based diagnosis assistant for leprosy, called AI4Leprosy, based on a combination of skin images and clinical data, collected following a standardized process. In a Brazilian leprosy national referral center, 222 patients with leprosy or other dermatological conditions were included, and the 1229 collected skin images and 585 sets of metadata are stored in an open-source dataset for other researchers to exploit. Findings: We used this dataset to test whether a CNN-based AI algorithm could contribute to leprosy diagnosis and employed three AI models, testing images and metadata both independently and in combination. AI modeling indicated that the most important clinical signs are thermal sensitivity loss, nodules and papules, feet paresthesia, number of lesions and gender, but also scaling surface and pruritus that were negatively associated with leprosy. Using elastic-net logistic regression provided a high classification accuracy (90%) and an area under curve (AUC) of 96.46% for leprosy diagnosis. Interpretation: Future validation of these models is underway, gathering larger datasets from populations of different skin types and collecting images with smartphone cameras to mimic real world settings. We hope that the results of our research will lead to clinical solutions that help accelerate global leprosy elimination. Funding: This study was partially funded by Novartis Foundation and Microsoft (in-kind contribution).http://www.sciencedirect.com/science/article/pii/S2667193X22000096LeprosyArtificial intelligenceAIImage-based diagnosisDermatologySkin lesions |
| spellingShingle | Raquel R Barbieri Yixi Xu Lucy Setian Paulo Thiago Souza-Santos Anusua Trivedi Jim Cristofono Ricardo Bhering Kevin White Anna M Sales Geralyn Miller José Augusto C Nery Michael Sharman Richard Bumann Shun Zhang Mohamad Goldust Euzenir N Sarno Fareed Mirza Arielle Cavaliero Sander Timmer Elena Bonfiglioli Cairns Smith David Scollard Alexander A. Navarini Ann Aerts Juan Lavista Ferres Milton O Moraes Reimagining leprosy elimination with AI analysis of a combination of skin lesion images with demographic and clinical data The Lancet Regional Health. Americas Leprosy Artificial intelligence AI Image-based diagnosis Dermatology Skin lesions |
| title | Reimagining leprosy elimination with AI analysis of a combination of skin lesion images with demographic and clinical data |
| title_full | Reimagining leprosy elimination with AI analysis of a combination of skin lesion images with demographic and clinical data |
| title_fullStr | Reimagining leprosy elimination with AI analysis of a combination of skin lesion images with demographic and clinical data |
| title_full_unstemmed | Reimagining leprosy elimination with AI analysis of a combination of skin lesion images with demographic and clinical data |
| title_short | Reimagining leprosy elimination with AI analysis of a combination of skin lesion images with demographic and clinical data |
| title_sort | reimagining leprosy elimination with ai analysis of a combination of skin lesion images with demographic and clinical data |
| topic | Leprosy Artificial intelligence AI Image-based diagnosis Dermatology Skin lesions |
| url | http://www.sciencedirect.com/science/article/pii/S2667193X22000096 |
| work_keys_str_mv | AT raquelrbarbieri reimaginingleprosyeliminationwithaianalysisofacombinationofskinlesionimageswithdemographicandclinicaldata AT yixixu reimaginingleprosyeliminationwithaianalysisofacombinationofskinlesionimageswithdemographicandclinicaldata AT lucysetian reimaginingleprosyeliminationwithaianalysisofacombinationofskinlesionimageswithdemographicandclinicaldata AT paulothiagosouzasantos reimaginingleprosyeliminationwithaianalysisofacombinationofskinlesionimageswithdemographicandclinicaldata AT anusuatrivedi reimaginingleprosyeliminationwithaianalysisofacombinationofskinlesionimageswithdemographicandclinicaldata AT jimcristofono reimaginingleprosyeliminationwithaianalysisofacombinationofskinlesionimageswithdemographicandclinicaldata AT ricardobhering reimaginingleprosyeliminationwithaianalysisofacombinationofskinlesionimageswithdemographicandclinicaldata AT kevinwhite reimaginingleprosyeliminationwithaianalysisofacombinationofskinlesionimageswithdemographicandclinicaldata AT annamsales reimaginingleprosyeliminationwithaianalysisofacombinationofskinlesionimageswithdemographicandclinicaldata AT geralynmiller reimaginingleprosyeliminationwithaianalysisofacombinationofskinlesionimageswithdemographicandclinicaldata AT joseaugustocnery reimaginingleprosyeliminationwithaianalysisofacombinationofskinlesionimageswithdemographicandclinicaldata AT michaelsharman reimaginingleprosyeliminationwithaianalysisofacombinationofskinlesionimageswithdemographicandclinicaldata AT richardbumann reimaginingleprosyeliminationwithaianalysisofacombinationofskinlesionimageswithdemographicandclinicaldata AT shunzhang reimaginingleprosyeliminationwithaianalysisofacombinationofskinlesionimageswithdemographicandclinicaldata AT mohamadgoldust reimaginingleprosyeliminationwithaianalysisofacombinationofskinlesionimageswithdemographicandclinicaldata AT euzenirnsarno reimaginingleprosyeliminationwithaianalysisofacombinationofskinlesionimageswithdemographicandclinicaldata AT fareedmirza reimaginingleprosyeliminationwithaianalysisofacombinationofskinlesionimageswithdemographicandclinicaldata AT ariellecavaliero reimaginingleprosyeliminationwithaianalysisofacombinationofskinlesionimageswithdemographicandclinicaldata AT sandertimmer reimaginingleprosyeliminationwithaianalysisofacombinationofskinlesionimageswithdemographicandclinicaldata AT elenabonfiglioli reimaginingleprosyeliminationwithaianalysisofacombinationofskinlesionimageswithdemographicandclinicaldata AT cairnssmith reimaginingleprosyeliminationwithaianalysisofacombinationofskinlesionimageswithdemographicandclinicaldata AT davidscollard reimaginingleprosyeliminationwithaianalysisofacombinationofskinlesionimageswithdemographicandclinicaldata AT alexanderanavarini reimaginingleprosyeliminationwithaianalysisofacombinationofskinlesionimageswithdemographicandclinicaldata AT annaerts reimaginingleprosyeliminationwithaianalysisofacombinationofskinlesionimageswithdemographicandclinicaldata AT juanlavistaferres reimaginingleprosyeliminationwithaianalysisofacombinationofskinlesionimageswithdemographicandclinicaldata AT miltonomoraes reimaginingleprosyeliminationwithaianalysisofacombinationofskinlesionimageswithdemographicandclinicaldata |