Research

NAAMII is delighted to welcome Dr. Prasoon Saurabh as a full-time Research Scientist and the Founding Principal Investigator of the Bhaweshwar Das Center for Advanced Studies (BDCAS). A theoretical quantum physicist, Dr. Saurabh brings expertise in quantum dynamics, topological quantum optics, and quantum-native machine learning. He earned his Ph.D. in Chemical and Material Physics from the University of California, Irvine, where he conducted foundational research on molecular polaritons with Prof. Shaul Mukamel, followed by advanced research as a Grade A Postdoctoral Fellow at the State Key L

By: Krischal Khanal ### Example Suppose you draw a ball from one of three urns, and you are not told which urn it came from: | Urn | Prior $P(H_i)$ | $P(\text{red} \mid H_i)$ | |-----|----------------|--------------------------| | A | 0.2 | 0.9 | | B | 0.5 | 0.4 | | C | 0.3 | 0.1 | You draw a red ball. What is the probability each urn was the source? By: Krischal Khanal ## Coding the Parallel Bayesian update ```python def bayesian_update_multi(priors, likelihoods): """ priors : list of P(H_i) — must sum to 1 likelihoods : list of P(E | H_i) — one per hypothesis Returns : list of posteriors P(H

By: Krischal Khanal In the previous blogs, we saw how to use Bayes' Theorem to update belief. Then we coded that up, and ended with a question on what if result is stochastic? However, to understand that we must understand one missing piece of the Bayes' Theorem. Bayes' Theorem is classically defined as: > [!Identities] > $$P(H | E) = \frac{P(H) \cdot P(E | H)}{P(E)}$$ > Where, > $$P(E) = P(H) \cdot P(E | H) + P(\neg H)P(E | \neg H)$$ Where, the symbols are defined as: - $H$ : Hypothesis - $E$ : Evidence/event Using Bayes' Theorem we are able to update the belief of hypothesis in the light of

By: Krischal Khanal ## Coding the Bayesian update ```python def bayesian_update(prior, likelihood_given_true, likelihood_given_false): """ prior : P(H) — prior probability of hypothesis likelihood_given_true : P(E|H) — probability of evidence if H is true likelihood_given_false: P(E|¬H) — probability of evidence if H is false """ marginal = (prior * likelihood_given_true) + ((1 - prior) * likelihood_given_false) posterior = (prior * likelihood_given_true) / marginal return posterior # The rare disease example prior = 0.001 # 1 in 1000 people have the disease p_e_given_h = 0.99 # test sensitivi

By: Krischal Khanal We've established the Bayes' Theorem as following formula that allowed inverting the conditional probabilities: $$P(A|B) = \frac{P(A)}{P(B)} \cdot P(B|A)$$ Now let's see how we could use the same theorem for the second, and arguably more profound application: **updating belief**. ## Have you got the disease? Suppose there's a rare disease. Only **1 in 1000 people** have it. You suspect you may have it, and take a diagnostic test. The test comes back positive. How worried should you be? If you thought **it depends on the accuracy of the test**, you are on the right path. The

By: Krischal Khanal ## Textbook definition The following is the mathematical definition for the **Bayes' Theorem** in standard textbook: > [!note]+ Bayes' theorem > > $$P(H | E) = \frac{P(H) \cdot P(E | H)}{P(E)}$$ > > Sometimes it's also written as: > > $$P(H | E) = \frac{P(H) \cdot P(E | H)}{P(H) \cdot P(E | H) + P(\neg H)P(E | \neg H)}$$ > > Where the meaning of the symbols are as follows: > - $H$ : A symbol for a hypothesis > - $E$ : A symbol for an evidence/event > - $\neg$ : Negation symbol ($\neg H$ means the negation of Hypothesis $H$) > - $P(H | E)$: Probability of H conditioned on E

  On 13 June 2026 , Mahesh Shakya, Research Associate at TOGAI Lab, NAAMII , presented ongoing medical imaging research during the "AI in Pediatrics: Extending Health Services in Resource-Limited Settings" panel at the 45th Nepal Pediatric Society Day . The presentation highlighted how AI-powered medical imaging can support early disease screening , strengthen referral pathways from primary to tertiary care , and improve access to timely healthcare for children in resource-limited settings. By assisting healthcare professionals with earlier diagnosis and informed clinical decision making,

Author: Anju Chhetri In a now-famous study, expert radiologists were asked to scan CT images of lungs for nodules. Hidden in one of those scans was something no one expected: a gorilla, 48 times the size of the average nodule. However, interestingly more than half the radiologists never noticed it. Their attention was so finely tuned to detecting tumors that they overlooked an unexpected and obvious anomaly. This phenomenon is known as inattentional blindness, where focused expertise can paradoxically limit perception [1]. While this finding is surprising, its implications extend far beyond hu

After nearly two years of research, collaboration, and continuous refinement, NAAMII, in partnership with Visible Impact and Diyo AI ( a startup incubated at NAAMII ) has successfully concluded the dissemination workshop for its AI-powered Nepali-English bilingual chatbot designed to provide safe abortion information. The in-person workshop brought together around 40 participants representing sexual and reproductive health and rights (SRHR) organisations, healthcare providers, technologists, researchers, and members of civil society. The event marked an important milestone in the project's jou

NAAMII participated in the 4th National Telemedicine & 1st National Digital Health Conference , held on 23–24 January 2026 in Kathmandu , contributing to discussions on the role of artificial intelligence in strengthening digital health systems and improving maternal healthcare access in Nepal. Organized by the Telemedicine Society of Nepal (TMSoN) and the Digital Health Forum Nepal , the conference brought together policymakers, healthcare professionals, researchers, technologists, and innovators to promote collaboration and knowledge sharing in telemedicine and digital health. During the

NAAMII’s TOGAI Lab participated in the AI-Sarosh Confluence , held from 19–21 January 2026 in Singapore , presenting ongoing research on AI-powered task-shifting for high-quality fetal ultrasound services in community healthcare settings . Representing NAAMII, Bishesh Khanal (Principal Investigator), Dr. Pradeep Raj Regmi (Co-Principal Investigator, TUTH), and Bishram Acharya (Research Associate) shared research progress with global experts working at the intersection of artificial intelligence and healthcare. The presentation highlighted how responsibly designed AI systems can support nurses

Dr. Binod Bhattarai, research scientist at NAAMII's B Bhattarai Multimodal Learning Lab,  recently spoke at the Embassy of Nepal in London on AI's role in healthcare, focusing on World Models and Safe AI. World Models enable AI systems to understand contextual relationships in clinical settings, and Safe AI addresses the trustworthiness of these systems when clinical decisions affect patient outcomes. Dr. Bhattarai's presentation brought these technical discussions into the public forum, engaging the audience with what these technologies mean for healthcare delivery and accountability. Re