--- title: I Built a Medical AI Model That Knows When to Say “I’m... description: An MSc student built a diabetic retinopathy detection system using EfficientNetB0 that incorporates uncertainty estimation via Monte Carlo Dropout and Deep... canonical: https://daily.dev/posts/i-built-a-medical-ai-model-that-knows-when-to-say-i-m-not-sure--ylthvv71p twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: I Built a Medical AI Model That Knows When to Say “I’m Not Sure” | daily.dev og:description: An MSc student built a diabetic retinopathy detection system using EfficientNetB0 that incorporates uncertainty estimation via Monte Carlo Dropout and Deep... og:url: https://daily.dev/posts/i-built-a-medical-ai-model-that-knows-when-to-say-i-m-not-sure--ylthvv71p og:image: https://api.daily.dev/og/posts/ylTHvV71P.png og:image:alt: I Built a Medical AI Model That Knows When to Say “I’m Not Sure” og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # I Built a Medical AI Model That Knows When to Say “I’m Not Sure” **[Medium](https://daily.dev/sources/medium_js)** · 9 min read · 0 upvotes · 0 comments ## Summary An MSc student built a diabetic retinopathy detection system using EfficientNetB0 that incorporates uncertainty estimation via Monte Carlo Dropout and Deep Ensembles, plus a rejection mechanism that flags uncertain predictions for human review instead of forcing automated decisions. MC Dropout halved the Expected Calibration Error (from 0.0457 to 0.0223) compared to the baseline, and at a 23% rejection rate, accepted-set accuracy improved by 6.3 percentage points. Key lessons include: preprocessing quality outweighs architecture choices, calibration matters more than raw accuracy in medical AI, class imbalance silently degrades models, and a system that can say 'I don't know' is more clinically trustworthy than one that always outputs a confident answer. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [What If the AI Is Confident - and Wrong?](https://daily.dev/posts/what-if-the-ai-is-confident---and-wrong--z2x2jxp1q) · Medium · 0 upvotes · 0 comments - [Teaching AI models to say “I’m not sure”](https://daily.dev/posts/teaching-ai-models-to-say-i-m-not-sure--kwyridj4a) · MIT News · 0 upvotes · 0 comments --- Tags: [#python](https://daily.dev/tags/python), [#deep-learning](https://daily.dev/tags/deep-learning), [#tensorflow](https://daily.dev/tags/tensorflow) [View this post on daily.dev](https://daily.dev/posts/i-built-a-medical-ai-model-that-knows-when-to-say-i-m-not-sure--ylthvv71p) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"I Built a Medical AI Model That Knows When to Say “I’m Not Sure”","url":"https://daily.dev/posts/i-built-a-medical-ai-model-that-knows-when-to-say-i-m-not-sure--ylthvv71p","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/i-built-a-medical-ai-model-that-knows-when-to-say-i-m-not-sure--ylthvv71p"},"datePublished":"2026-07-24T04:39:53.066Z","dateModified":"2026-07-24T04:46:16.985Z","description":"An MSc student built a diabetic retinopathy detection system using EfficientNetB0 that incorporates uncertainty estimation via Monte Carlo Dropout and Deep...","image":"https://media.daily.dev/image/upload/s--ZrL_HSsR--/f_auto/v1722860399/public/Placeholder%2006","thumbnailUrl":"https://media.daily.dev/image/upload/s--ZrL_HSsR--/f_auto/v1722860399/public/Placeholder%2006","isAccessibleForFree":true,"articleSection":"Medium","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Medium","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/medium","url":"https://daily.dev/sources/medium_js"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/i-built-a-medical-ai-model-that-knows-when-to-say-i-m-not-sure--ylthvv71p","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"python,deep-learning,tensorflow","timeRequired":"PT9M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Medium","item":"https://daily.dev/sources/medium_js"},{"@type":"ListItem","position":3,"name":"I Built a Medical AI Model That Knows When to Say “I’m Not Sure”"}]} ```