{"id":{"repo_id":"nus","oai_identifier":"oai:scholarbank.nus.edu.sg:10635/309762"},"canonical_url":"https://search.dev.ndltd.org/etd/nus/oai:scholarbank.nus.edu.sg:10635/309762","repository":{"repo_id":"nus","name":"National University of Singapore","base_url":"https://scholarbank.nus.edu.sg/oai/request"},"display":{"title":"DERMAI – A DEEP LEARNING-BASED WEB PLATFORM FOR DERMATOLOGIC DIAGNOSIS","abstract":"Skin diseases represent the fourth leading cause of non-fatal disease burden globally, with primary care consultations frequently resulting in specialist referrals due to diagnostic variance among general practitioners. This study introduces DermAI, an innovative AI-based online diagnostic platform integrating deep learning for skin disease diagnosis with a large language model interface. The diagnostic model, enhanced with large kernel convolutions and a Convolutional Block Attention Module for capsule networks, achieved 99.25% accuracy on the HAM10000 dataset. DermAI enables patients to receive preliminary skin disease diagnoses via internet, potentially improving primary care diagnostic efficiency, reducing unnecessary specialist referrals, lowering healthcare costs, and enhancing patient experience. The platform represents a significant advancement in teledermatology, which is expected to resolve 70% of skin issues, while demonstrating artificial intelligence's potential in dermatological diagnosis and establishing new directions for telemedicine development.","abstract_html":"Skin diseases represent the fourth leading cause of non-fatal disease burden globally, with primary care consultations frequently resulting in specialist referrals due to diagnostic variance among general practitioners. This study introduces DermAI, an innovative AI-based online diagnostic platform integrating deep learning for skin disease diagnosis with a large language model interface. The diagnostic model, enhanced with large kernel convolutions and a Convolutional Block Attention Module for capsule networks, achieved 99.25% accuracy on the HAM10000 dataset. DermAI enables patients to receive preliminary skin disease diagnoses via internet, potentially improving primary care diagnostic efficiency, reducing unnecessary specialist referrals, lowering healthcare costs, and enhancing patient experience. The platform represents a significant advancement in teledermatology, which is expected to resolve 70% of skin issues, while demonstrating artificial intelligence's potential in dermatological diagnosis and establishing new directions for telemedicine development.","abstract_has_math":false,"creators":["LYU SHAOBO"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-08-23","date_published":"2024-08-23","updated_at":"2026-07-24T03:31:38Z","subjects":["healthcare efficiency","DermAI","telemedicine","skin diseases","artificial intelligence","dermatology"],"languages":[],"rights":[],"rights_urls":["https://scholarbank.nus.edu.sg/bitstreams/4428a0a2-3247-4485-a290-061b1d781243/download"],"identifier_entries":[]},"links":{"outbound_url":null,"outbound_label":null,"outbound_source":null},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["LYU SHAOBO"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.issued","label":"Date","values":["2024-08-23"]},{"key":"dc:relation.isreferencedby","label":"Dc Relation Isreferencedby","values":["https://scholarbank.nus.edu.sg/handle/10635/309762"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["healthcare efficiency","DermAI","telemedicine","skin diseases","artificial intelligence","dermatology"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["https://scholarbank.nus.edu.sg/bitstreams/4428a0a2-3247-4485-a290-061b1d781243/download"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://scholarbank.nus.edu.sg/bitstreams/510c4d92-3039-4bd0-a73a-e8ea04664a6a/download"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Skin diseases represent the fourth leading cause of non-fatal disease burden globally, with primary care consultations frequently resulting in specialist referrals due to diagnostic variance among general practitioners. This study introduces DermAI, an innovative AI-based online diagnostic platform integrating deep learning for skin disease diagnosis with a large language model interface. The diagnostic model, enhanced with large kernel convolutions and a Convolutional Block Attention Module for capsule networks, achieved 99.25% accuracy on the HAM10000 dataset. DermAI enables patients to receive preliminary skin disease diagnoses via internet, potentially improving primary care diagnostic efficiency, reducing unnecessary specialist referrals, lowering healthcare costs, and enhancing patient experience. The platform represents a significant advancement in teledermatology, which is expected to resolve 70% of skin issues, while demonstrating artificial intelligence's potential in dermatological diagnosis and establishing new directions for telemedicine development."]},{"key":"dc:format.checksum.md5","label":"Dc Format Checksum Md5","values":["9f3c6f2aa8f96291ef77b0a18484521d","461dc9eafd224d0fe722f6e1544f3408","170db1965744a1796ea6ff6e86e5090e"]},{"key":"dc:title","label":"Title","values":["DERMAI – A DEEP LEARNING-BASED WEB PLATFORM FOR DERMATOLOGIC DIAGNOSIS"]}]}],"canonical_facts":{"dc:creator":["LYU SHAOBO"],"dc:date.issued":["2024-08-23"],"dc:description.abstract":["Skin diseases represent the fourth leading cause of non-fatal disease burden globally, with primary care consultations frequently resulting in specialist referrals due to diagnostic variance among general practitioners. This study introduces DermAI, an innovative AI-based online diagnostic platform integrating deep learning for skin disease diagnosis with a large language model interface. The diagnostic model, enhanced with large kernel convolutions and a Convolutional Block Attention Module for capsule networks, achieved 99.25% accuracy on the HAM10000 dataset. DermAI enables patients to receive preliminary skin disease diagnoses via internet, potentially improving primary care diagnostic efficiency, reducing unnecessary specialist referrals, lowering healthcare costs, and enhancing patient experience. The platform represents a significant advancement in teledermatology, which is expected to resolve 70% of skin issues, while demonstrating artificial intelligence's potential in dermatological diagnosis and establishing new directions for telemedicine development."],"dc:format.checksum.md5":["9f3c6f2aa8f96291ef77b0a18484521d","461dc9eafd224d0fe722f6e1544f3408","170db1965744a1796ea6ff6e86e5090e"],"dc:identifier.uri":["https://scholarbank.nus.edu.sg/bitstreams/510c4d92-3039-4bd0-a73a-e8ea04664a6a/download"],"dc:relation.isreferencedby":["https://scholarbank.nus.edu.sg/handle/10635/309762"],"dc:rights":["https://scholarbank.nus.edu.sg/bitstreams/4428a0a2-3247-4485-a290-061b1d781243/download"],"dc:subject":["healthcare efficiency","DermAI","telemedicine","skin diseases","artificial intelligence","dermatology"],"dc:title":["DERMAI – A DEEP LEARNING-BASED WEB PLATFORM FOR DERMATOLOGIC DIAGNOSIS"],"dc:type":["Thesis"]},"updated_at":"2026-07-24T03:31:38Z"}