Clinical perspective. Population-level purpose.
Dr. Sabrina Chowdhury Tithi is a Bangladeshi physician, general surgeon, public-health professional, researcher and health author. Her professional profile brings together clinical decision-making, epidemiological thinking and accessible health communication.
Her work reflects a belief that better health outcomes depend not only on skilled treatment, but also on prevention, preparedness, clear evidence and systems designed around human dignity. Across surgery, research and public education, she focuses on translating complex medical ideas into practical action.
General surgery
Her clinical outlook is grounded in patient-centred care, careful assessment and the disciplined coordination essential to modern surgery. She connects hands-on medical experience with a broader interest in trauma care, surgical innovation and responsible use of emerging technology.
Evidence into action
In public health, her interests include epidemiological intelligence, outbreak preparedness, emergency response and risk communication. Her perspective joins clinical realities with population data—helping make technical information clearer, timelier and more useful for decision-makers and communities.
Office or Zoom · 15 or 45 minutes
Choose a weekday at least five days ahead. A thoughtful topic and short, specific description make the request easier to review.
Selected writing
An evidence-informed guide exploring healthy ageing through genetics, cellular health, nutrition, metabolism and sustainable lifestyle choices.
View on Apple BooksA practical introduction to nutrition, energy, mindful food choices and long-term habits designed to support everyday wellbeing.
View on Apple BooksSelected public work
Her published work spans surgical technology and accessible public-health education, with an emphasis on making emerging clinical ideas and essential safety information understandable to wider audiences.
Clinical AI Reliability · CAR
Clinical AI Reliability is an open research framework designed to test whether clinical AI systems remain dependable when prompts, context, data quality and operating conditions change. Instead of treating one accuracy score as sufficient, CAR aims to make stability, uncertainty and failure patterns measurable and reproducible.
Why it could matter globally
Clinical AI may reach millions of people, but scale is only responsible when safety evidence can travel with the technology. If empirically validated and adopted, CAR could help move medical AI away from one-off demonstrations and toward transparent, accountable evaluation.
Evaluate how systems respond when wording, context or operating conditions shift, revealing brittle behaviour that a headline score may miss.
Create structured, reviewable evidence of inconsistency, uncertainty and unsafe failure modes before they are encountered in real clinical use.
Give researchers, clinicians and health systems a more reproducible basis for deciding where AI may help, where safeguards are needed and where it should not be used.
Official & public links
Trusted sources
Direct access to official health news, newsletters and research updates from three leading institutions.
Practical health information grounded in findings from National Institutes of Health research.
Read & subscribe WHONewsletter directoryOfficial newsletters covering epidemics, health emergencies, data, AI, immunization and global health.
Browse newsletters MayoResearch newsOfficial reporting on medical studies, discoveries, clinical research and emerging care.
View research updatesWrite from the website
For collaborations, research, speaking, media or general professional enquiries. For a scheduled office or Zoom meeting, use the appointment request above.
Guiding principle
“The strongest health decisions are both scientifically sound and deeply human.”