https://isarar.com/ 2026-08-17T15:00:00Z weekly 1.0 https://isarar.com/isarar-900.jpg Isarar Siddique Isarar Siddique, founder and medical AI researcher, Lucknow https://isarar.com/og-home.jpg I build medical AI that reaches patients https://isarar.com/blog/ 2026-08-17T15:00:00Z weekly 0.9 https://isarar.com/blog/skin-tone-fairness-starts-at-the-camera/ 2026-08-17T15:00:00Z monthly 0.8 https://isarar.com/og-skin.jpg Skin tone fairness starts at the camera, not the model Fairness in dermatology AI gets treated as a loss function problem. Most of the failure happens before the model sees anything, in the dataset and in the phone camera pipeline itse https://isarar.com/blog/the-three-minute-constraint/ 2026-08-17T14:00:00Z monthly 0.8 https://isarar.com/og-window.jpg The three minute constraint None of the things that decide whether a screening tool gets used in a busy outpatient department appear in the paper. Field notes from a trial in a tertiary hospital in India. https://isarar.com/blog/clinical-notes-do-not-translate/ 2026-08-17T13:00:00Z monthly 0.8 https://isarar.com/og-notes.jpg Clinical notes do not translate Annotating Indian, Malaysian and Igbo clinical notes for a healthcare language model dataset. The same illness is written in three different grammars, and a model trained on one re https://isarar.com/blog/base-rates-break-screening-claims/ 2026-08-17T12:00:00Z monthly 0.8 https://isarar.com/og-baserate.jpg A screen that is 95 percent accurate is wrong about half the time Accuracy in an abstract tells you almost nothing about a screening tool. Work the base rate and a very good model still hands you a majority of false positives. The arithmetic, and https://isarar.com/blog/focus-and-the-overlap/ 2026-08-17T11:00:00Z monthly 0.8 https://isarar.com/og-overlap.jpg Focus is advice for people who have not found the overlap I run four companies and everyone tells me to pick one. The advice is correct for most people and wrong for me, and there is a single test that tells you which case you are in. https://isarar.com/blog/the-wrong-person-to-tell-you-about-my-brother/ 2026-08-17T10:00:00Z monthly 0.8 https://isarar.com/og-brother.jpg The wrong person to tell you about my brother My brother started building at eleven, left college at eighteen because he decided the syllabus was years behind what he already did daily, and now runs engineering at my company. https://isarar.com/raiyan-400.jpg Raiyan Siddique Raiyan Siddique, chief technology officer and co-founder of Biotech Wallah https://isarar.com/blog/the-booth-is-the-cost/ 2026-08-17T09:00:00Z monthly 0.8 https://isarar.com/og-booth.jpg The booth is the cost A hearing test is one of the cheapest procedures in medicine, so why does almost nobody in rural India get one? The answer is the room, not the test. What has to be true before you https://isarar.com/blog/a-clinician-who-cannot-see-why/ 2026-08-17T08:00:00Z monthly 0.8 https://isarar.com/og-fusion.jpg A clinician who cannot see why will not act I had a screening model that scored better than the one we deployed. I threw it away. On buying attribution with accuracy, and why explainability is an architectural constraint rat https://isarar.com/blog/icd-11-has-no-clean-map/ 2026-08-17T07:00:00Z monthly 0.8 https://isarar.com/og-icd.jpg ICD-11 has no clean map from ICD-10 Coding is where health data quality is silently won or lost, long before anybody trains a model on it. Four migration cases, three of which need a clinician, and why we kept a huma https://isarar.com/blog/cold-emailing-into-research-labs/ 2026-08-16T09:00:00Z monthly 0.8 https://isarar.com/og-email.jpg How I cold-emailed my way into eleven research labs No application portals, no referrals, no pedigree. The first fifty emails got me nothing. Here is the single change that took the reply rate to roughly one in six.