Healthcare AI | Muhammad Aurangzeb Ahmad

Overview

A doctor seeing a patient has access to a chart, a history, and twenty minutes. An AI system trained on millions of patient records can detect patterns no individual clinician could hold in mind: who is likely to deteriorate in the next 24 hours, who will be readmitted within a month, when a patient is nearing the end of life and may benefit from a different kind of care. When done right, the use of AI can greatly improve health care outcomes.

A few weeks after we deployed a patient prioritization system at a large inner-city hospital, I went back to ask the staff whether it was working. The system predicted which patients in the emergency waiting area were at risk of leaving before being seen (what hospitals call LWBS). It is a quiet crisis: a patient who walks out unexamined often returns sicker.

I asked one of the check-in staff, the person who greets patients when they arrive, what she thought. She said: "I know it works. The other day I was looking at the dashboard and a patient's name jumped to the top of the priority queue. I went over to her and said, 'Ma'am, you don't have to wait. We are prioritizing you. You are next.' She looked at me and said, 'I'm glad you said that, because I was about to get up and leave.'"

That patient stayed. She was seen.

AI systems built through this work are currently deployed across multiple major health systems, reaching approximately 2.5 million patients. These systems are embedded directly in EHR workflows where physicians and nurses see predictions as they care for patients, and in operational platforms used by care coordinators and hospital administrators to manage capacity, flow, and risk. I have led teams that predict treatment response, optimize care pathways, and surface signals of patient deterioration and potential complications earlier than traditional clinical detection. The end users span the full clinical spectrum: bedside physicians making treatment decisions, nurses acting on deterioration alerts, care coordinators managing high-risk populations, and operations teams using simulation to plan capacity and staffing.

My work builds and deploys predictive models in live clinical environments, from pediatric ICUs to emergency departments to post-surgical recovery units. Previous work spans disease prediction, including pressure injury (Ahmad et al., 2021), diabetes onset and progression (Lim et al., 2021), readmission risk (Eckert et al., 2019), surgical outcomes (Lammers et al., 2021), and end-of-life trajectories (Ahmad et al., 2018), patient flow optimization (Padthe et al., 2021; Eckert et al., 2018), fraud and waste detection in healthcare systems (Liu et al., 2018), and algorithmic guidance for implantable cardiac devices (Mahajan et al., 2013). A parallel thread uses simulation to build digital twins of hospital systems (Ahmad et al., 2023): computational replicas of wards and patient flows that let administrators test interventions before implementing them. What if we added two nurses to the overnight shift? What happens to patient wait times if we open a new intake bay? A digital twin answers those questions safely, in simulation. Recent work has extended into algorithmic nudging (how subtle AI suggestions can steer patient behavior and improve health outcomes at scale) and the application of large language models in electronic health records to enhance clinical insight generation and mental health support (Jaiswal et al., 2024). Several of these models have been prospectively validated in live clinical environments: predictions generated on real patients, tracked against real outcomes.

Throughout this work, I hold myself to a standard beyond accuracy: a model deployed in a hospital must be equitable across patient populations, legible to the clinicians using it, robust under distribution shift, and risk-sensitive to rare high-impact events (Preuett et al., 2025). In end-of-life contexts specifically, fairness extends beyond demographic parity: it encompasses moral representation and fidelity to the patient's values, relationships, and worldview (Ahmad, 2025).

Clinical Deployments

In clinical prediction, models for readmission risk, length of stay, discharge disposition, and left-without-being-seen have been deployed across multiple health systems with documented cost savings of $10M+ at multiple sites, a 12% reduction in 30-day readmission rates at a large California health system, and a 7% reduction in average length of stay. Emergency department arrival forecasting, using clustering and phenotyping to identify variability in patient flow, reduced wait times by 50% and LWBS rates by one-third. Trauma ICU deterioration and recovery prediction, including modeling of resilience in patients with chronic critical illness, improved time to intervention by 9% at a hospital in the northeast. COVID-19 and influenza forecasting (3–4 week horizon) is currently deployed and in active use for health system planning.

On the operational side, cascading machine learning and simulation models inform resource allocation, staffing, and long-term financial planning across health system operations, with documented savings of $9 million. Unsupervised ML on high-dimensional claims data identified $7.9 million in unwarranted cost variation across provider networks by automatically extracting peer reference groups and flagging high-cost outliers. Fraud detection using supervised, semi-supervised, and unsupervised methods identified $12.3 million in fraudulent activity in a large healthcare system. Lifetime healthcare cost modeling for first responders and families with aerodigestive disease and lung cancer risk improved aggregate prediction by $2.9 million over baseline methods.

At the population scale, care deferral prediction for vulnerable populations and patients with chronic conditions reduced deferral rates by 10%, with documented savings of $7.5 million over a decade. Nudge-based recommendation systems built on knowledge graph foundation models operate at scale to improve health outcomes. Lead a team that built generative AI systems to extract actionable insights from EHRs and longitudinal healthcare data for executives, case managers, physicians, and nurse practitioners; separate models for treatment response prediction, care pathway optimization, and early detection of patient deterioration and complications are in active clinical use.

Research Areas

Clinical Prediction & Decision Support

Predictive models for patient deterioration, readmission risk, pressure injury, disease onset, surgical outcomes, and care deferral. Emphasis on prospective validation, equitable performance across patient populations, and deployment in live clinical workflows.

Foundation Models in Clinical Care

Large language models and retrieval-augmented generation systems applied to electronic health records, clinical decision support, and mental health. Building trustworthy, hallucination-resistant clinical AI and personality-adaptive conversational agents for therapeutic support.

Hospital Digital Twins & Operations

Combining machine learning with agent-based simulation to build digital replicas of hospital systems. Optimizing patient flow, staffing, resource allocation, and long-term financial planning, virtually testing operational decisions before implementing them in the real world.

End-of-Life & Palliative Care AI

Predictive models for end-of-life trajectories to improve the timing and quality of palliative care. Examining algorithmic fairness in these predictions (whose death an algorithm anticipates, and whose it misses) and the broader ethics of AI involvement in the most consequential clinical decisions.

Selected Publications

2025

RLC
Reinforcement Learning under State and Outcome Uncertainty: A Foundational Distributional Perspective

Larry Preuett, Qiuyi Zhang, and Muhammad Aurangzeb Ahmad

In Reinforcement Learning Conference (RLC), 2025

Abs arXiv Bib HTML PDF Code

In many real-world planning tasks, agents must tackle uncertainty about the environment’s state and variability in the outcomes of any chosen policy. We address both forms of uncertainty as a first step toward safer algorithms in partially observable settings. Specifically, we extend Distributional Reinforcement Learning (DistRL) — which models the entire return distribution for fully observable domains — to Partially Observable Markov Decision Processes (POMDPs), allowing an agent to learn the distribution of returns for each conditional plan. Concretely, we introduce new distributional Bellman operators for partial observability and prove their convergence under the supremum p-Wasserstein metric. We also propose a finite representation of these return distributions via psi-vectors, generalizing the classical alpha-vectors in POMDP solvers. Building on this, we develop Distributional Point-Based Value Iteration (DPBVI), which integrates psi-vectors into a standard point-based backup procedure — bridging DistRL and POMDP planning. By tracking return distributions, DPBVI naturally enables risk-sensitive control in domains where rare, high-impact events must be carefully managed.
@inproceedings{preuett2025distributional, category = {selected_research}, title = {Reinforcement Learning under State and Outcome Uncertainty: A Foundational Distributional Perspective}, author = {Preuett, Larry and Zhang, Qiuyi and Ahmad, Muhammad Aurangzeb}, booktitle = {Reinforcement Learning Conference (RLC)}, year = {2025}, }
arXiv
Algorithmic Fairness in AI Surrogates for End-of-Life Decision-Making

Muhammad Aurangzeb Ahmad

2025

Abs arXiv Bib HTML PDF

Artificial intelligence surrogates are systems designed to infer preferences when individuals lose decision-making capacity. Fairness in such systems is a domain that has been insufficiently explored. Traditional algorithmic fairness frameworks are insufficient for contexts where decisions are relational, existential, and culturally diverse. This paper explores an ethical framework for algorithmic fairness in AI surrogates by mapping major fairness notions onto potential real-world end-of-life scenarios. It then examines fairness across moral traditions. The authors argue that fairness in this domain extends beyond parity of outcomes to encompass moral representation, fidelity to the patient’s values, relationships, and worldview.
@misc{ahmad2025algorithmic, category = {selected_research}, title = {Algorithmic Fairness in AI Surrogates for End-of-Life Decision-Making}, author = {Ahmad, Muhammad Aurangzeb}, year = {2025}, }

2024

ACM BCB
Building Personality-Adaptive Conversational AI for Mental Health Therapy

Sugam Jaiswal, Joyce Lee, Joe Berria, and 4 more authors

In Proceedings of the 15th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, 2024

Abs Bib

Many people with mental health problems cannot get professional help for various reasons such as lack of awareness, unavailability, unaffordability, etc. A virtual conversational agent can offer an alternative to deliver mental health care that is accessible, affordable, and scalable. However, building such agents using a one-size-fits-all approach may not be effective for everyone, as different individuals have different personality types that dictate how they communicate with chatbots. Therefore, developing therapy chatbots that can adjust to the user’s personality is important. In this work, we present the important role of personality-adaptive conversational agents (PACAs) in the context of mental healthcare. We designed an architecture around traditional machine learning (ML) models and open-source large language models (LLMs) to build a PACA for mental health therapy, developed a working prototype based on it, and conducted a user study to conclude that personality-adaptiveness is indeed an important feature for mental health chatbots.
@inproceedings{jaiswal2024building, title = {Building Personality-Adaptive Conversational AI for Mental Health Therapy}, author = {Jaiswal, Sugam and Lee, Joyce and Berria, Joe and Tanikella, Raviteja and Zolyomi, Annuska and Ahmad, Muhammad Aurangzeb and Si, Dong}, booktitle = {Proceedings of the 15th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics}, pages = {1--1}, year = {2024}, url = {https://dl.acm.org/doi/abs/10.1145/3698587.3701489}, }

2023

ICHI
Validation of a Hospital Digital Twin with Machine Learning

Muhammad Aurangzeb Ahmad, Vijay Chickarmane, Farinaz Sabz Ali Pour, and 2 more authors

2023

Abs Bib PDF

Recently there has been a surge of interest in developing Digital Twins of process flows in healthcare to better understand bottlenecks and areas of improvement. A key challenge is in the validation process. We describe a work in progress for a digital twin using an agent based simulation model for determining bed turnaround time for patients in hospitals. We employ a strategy using machine learning for validating the model and implementing sensitivity analysis.
@article{aurangzeb2023validation, category = {selected_research}, title = {Validation of a Hospital Digital Twin with Machine Learning}, author = {Ahmad, Muhammad Aurangzeb and Chickarmane, Vijay and Pour, Farinaz Sabz Ali and Shariari, Nima and Dutta Roy, Taposh}, booktitle = {2023 IEEE 11th International Conference on Healthcare Informatics (ICHI)}, pages = {465--469}, year = {2023}, organization = {IEEE}, url = {https://arxiv.org/pdf/2303.04117}, }

2021

IEEE ICHI
Machine learning approaches for pressure injury prediction

Muhammad Aurangzeb Ahmad, Barrett Larson, Steve Overman, and 5 more authors

In 2021 IEEE 9th International Conference on Healthcare Informatics (ICHI), 2021

Abs Bib PDF

Pressure Injuries are localized damages to the skin caused by sustained pressure. It is a common yet preventable disease affecting millions of patients. While there are multiple scales to determine if a patient has pressure injury, these methods suffer from high inter-rater subjectivity. To address this problem we create predictive models for pressure injury using Centers for Medicare Medicaid Services claims data. The models show relatively good predictive performance, we also explore aspects of the model where they will be deployed in a real world clinical settings.
@inproceedings{ahmad2021machine, title = {Machine learning approaches for pressure injury prediction}, author = {Ahmad, Muhammad Aurangzeb and Larson, Barrett and Overman, Steve and Kumar, Vikas and Xie, Jing and Rossington, Alan and Patel, Ankur and Teredesai, Ankur}, booktitle = {2021 IEEE 9th International Conference on Healthcare Informatics (ICHI)}, pages = {427--431}, year = {2021}, organization = {IEEE}, url = {https://ieeexplore.ieee.org/abstract/document/9565729}, }
ArXiV
Machine Learning Approaches for Type 2 Diabetes Prediction and Care Management

Aloysius Lim, Ashish Singh, Jody Chiam, and 4 more authors

arXiv preprint arXiv:2104.07820, 2021

Abs Bib PDF

Prediction of diabetes and its various complications has been studied in a number of settings, but a comprehensive overview of problem setting for diabetes prediction and care management has not been addressed in the literature. In this document we seek to remedy this omission in literature with an encompassing overview of diabetes complication prediction as well as situating this problem in the context of real world healthcare management. We illustrate various problems encountered in real world clinical scenarios via our own experience with building and deploying such models. In this manuscript we illustrate a Machine Learning (ML) framework for addressing the problem of predicting Type 2 Diabetes Mellitus (T2DM) together with a solution for risk stratification, intervention and management. These ML models align with how physicians think about disease management and mitigation, which comprises these four steps: Identify, Stratify, Engage, Measure.
@article{lim2021machine, title = {Machine Learning Approaches for Type 2 Diabetes Prediction and Care Management}, author = {Lim, Aloysius and Singh, Ashish and Chiam, Jody and Eckert, Carly and Kumar, Vikas and Ahmad, Muhammad Aurangzeb and Teredesai, Ankur}, journal = {arXiv preprint arXiv:2104.07820}, year = {2021}, url = {https://arxiv.org/pdf/2104.07820}, }
Annals of Surgery
A surgeon’s guide to machine learning

Daniel T Lammers, Carly M Eckert, Muhammad A Ahmad, and 2 more authors

Annals of Surgery Open, 2021

Abs Bib HTML

Machine learning (ML) represents a collection of advanced data modeling techniques beyond the traditional statistical models and tests with which most clinicians are familiar. While a subset of artificial intelligence, ML is far from the science fiction impression frequently associated with AI. At its most basic, ML is about pattern finding, sometimes with complex algorithms. The advanced mathematical modeling of ML is seeing expanding use throughout healthcare and increasingly in the day-to-day practice of surgeons. As with any new technique or technology, a basic understanding of principles, applications, and limitations are essential for appropriate implementation. This primer is intended to provide the surgical reader an accelerated introduction to applied ML and considerations in potential research applications or the review of publications, including ML techniques.
@article{lammers2021surgeon, title = {A surgeon’s guide to machine learning}, author = {Lammers, Daniel T and Eckert, Carly M and Ahmad, Muhammad A and Bingham, Jason R and Eckert, Matthew J}, journal = {Annals of Surgery Open}, volume = {2}, number = {3}, pages = {e091}, year = {2021}, publisher = {LWW}, url = {https://journals.lww.com/aosopen/abstract/2021/09000/a_surgeon_s_guide_to_machine_learning.21.aspx}, }
ArXiV
Emergency Department Optimization and Load Prediction in Hospitals

Karthik K Padthe, Vikas Kumar, Carly M Eckert, and 4 more authors

arXiv preprint arXiv:2102.03672, 2021

Abs Bib PDF

Over the past several years, across the globe, there has been an increase in people seeking care in emergency departments (EDs). ED resources, including nurse staffing, are strained by such increases in patient volume. Accurate forecasting of incoming patient volume in emergency departments (ED) is crucial for efficient utilization and allocation of ED resources. Working with a suburban ED in the Pacific Northwest, we developed a tool powered by machine learning models, to forecast ED arrivals and ED patient volume to assist end-users, such as ED nurses, in resource allocation. In this paper, we discuss the results from our predictive models, the challenges, and the learnings from users’ experiences with the tool in active clinical deployment in a real world setting.
@article{padthe2021emergency, title = {Emergency Department Optimization and Load Prediction in Hospitals}, author = {Padthe, Karthik K and Kumar, Vikas and Eckert, Carly M and Mark, Nicholas M and Zahid, Anam and Ahmad, Muhammad Aurangzeb and Teredesai, Ankur}, journal = {arXiv preprint arXiv:2102.03672}, year = {2021}, url = {https://arxiv.org/pdf/2102.03672}, }

2019

ACI
Development and prospective validation of a machine learning-based risk of readmission model in a large military hospital

Carly Eckert, Neris Nieves-Robbins, Elena Spieker, and 8 more authors

Applied clinical informatics, 2019

Abs Bib HTML

Thirty-day hospital readmissions are a quality metric for health care systems. Predictive models aim to identify patients likely to readmit to more effectively target preventive strategies. Many risk of readmission models have been developed on retrospective data, but prospective validation of readmission models is rare. To the best of our knowledge, none of these developed models have been evaluated or prospectively validated in a military hospital. The objectives of this study are to demonstrate the development and prospective validation of machine learning (ML) risk of readmission models to be utilized by clinical staff at a military medical facility and demonstrate the collaboration between the U.S. Department of Defense’s integrated health care system and a private company. We evaluated multiple ML algorithms to develop a predictive model for 30-day readmissions using data from a retrospective cohort of all-cause inpatient readmissions at Madigan Army Medical Center (MAMC).
@article{eckert2019development, title = {Development and prospective validation of a machine learning-based risk of readmission model in a large military hospital}, author = {Eckert, Carly and Nieves-Robbins, Neris and Spieker, Elena and Louwers, Tom and Hazel, David and Marquardt, James and Solveson, Keith and Zahid, Anam and Ahmad, Muhammad and Barnhill, Richard and others}, journal = {Applied clinical informatics}, volume = {10}, number = {02}, pages = {316--325}, year = {2019}, publisher = {Georg Thieme Verlag KG}, url = {https://www.thieme-connect.com/products/ejournals/html/10.1055/s-0039-1688553}, }

2018

IAAI
Death vs. data science: predicting end of life

Muhammad Ahmad, Carly Eckert, Greg McKelvey, and 3 more authors

In Proceedings of the AAAI Conference on Artificial Intelligence, 2018

Abs Bib PDF

Death is an inevitable part of life and while it cannot be delayed indefinitely it is possible to predict with some certainty when the health of a person is going to deteriorate. In this paper, we predict risk of mortality for patients from two large hospital systems in the Pacific Northwest. Using medical claims and electronic medical records (EMR) data we greatly improve prediction for risk of mortality and explore machine learning models with explanations for end of life predictions. The insights that are derived from the predictions can then be used to improve the quality of patient care towards the end of life.
@inproceedings{ahmad2018death, title = {Death vs. data science: predicting end of life}, author = {Ahmad, Muhammad and Eckert, Carly and McKelvey, Greg and Zolfagar, Kiyana and Zahid, Anam and Teredesai, Ankur}, booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence}, volume = {32}, number = {1}, year = {2018}, }
Thorax
S45 predicting likelihood of emergency department admission prior to triage: utilising machine learning within a COPD cohort

C Eckert, M Ahmad, K Zolfaghar, and 3 more authors

2018

Abs Bib HTML

Acute exacerbation of COPD is one of the commonest reasons for emergency department (ED) attendance and admission. Optimising ED patient flow requires early identification of patients needing inpatient care to initiate the admissions process, improve bed management and reduce ED length of stay. Stratifying COPD patients by likelihood of admission and length of stay at triage would potentially facilitate these and other operational efficiencies, such as targeting early supported discharge team review and COPD care bundle. We propose a machine learning (ML) based approach to predicting the need for admission from ED amongst a cohort of COPD patients.
@misc{eckert2018s45, title = {S45 predicting likelihood of emergency department admission prior to triage: utilising machine learning within a COPD cohort}, author = {Eckert, C and Ahmad, M and Zolfaghar, K and McKelvey, G and Carlin, C and Lowe, D}, year = {2018}, publisher = {BMJ Publishing Group Ltd}, url = {https://thorax.bmj.com/content/73/Suppl_4/A28.1}, }
SIAM
Automatic detection of excess healthcare spending and cost variation in ACOs

Eric Liu, Muhammad A Ahmad, Carly Eckert, and 5 more authors

2018

Abs Bib PDF

There are more than nine hundred Accountable Care Organizations (ACOs) in the United States, both in the public and private sector, serving millions of patients across the country in a process to transition from fee-for-service to a value-based-care model for healthcare delivery in an effort to contain expenditures. Identifying fraud, waste, and abuse resulting in superfluous expenditures associated with care delivery is central to the success of ACOs and for making the cost of healthcare sustainable. In theory, such expenditures should be easily identifiable with large amounts of historical data. However, to the best of our knowledge there is no data mining framework that systematically addresses the problem of identifying unwarranted variation in expenditures on high dimensional claims data using unsupervised machine learning techniques. In this paper we propose methods to uncover unwarranted variation in healthcare spending by automatically extracting reference groups of peerproviders from the data and then detecting high cost outliers within these groups. We demonstrate the utility of our proposed framework on datasets from a large ACO in the United States to successfully identify unwarranted variation in therapeutic procedures even in low cost claims that had previously gone unnoticed.
@misc{liu2018automatic, title = {Automatic detection of excess healthcare spending and cost variation in ACOs}, author = {Liu, Eric and Ahmad, Muhammad A and Eckert, Carly and Nascimento, Anderson and De Cock, Martine and Padthe, Karthik and Teredesai, Ankur and McKelvey, Greg}, year = {2018}, publisher = {SIAM}, }

2013

Patent
Systems and methods for programming implantable medical devices

Deepa Mahajan, Yanting Dong, and Muhammad A Ahmad

2013

US Patent 8,346,369

Abs Bib HTML

Embodiments of the invention are directed to systems and methods for programming implantable medical devices, amongst other things. In an embodiment, the invention includes a method of programming an implantable medical device. The method can include gathering parameter data representing a set of previously programmed parameter values from a plurality of implanted medical devices. The method can further include performing association analysis on the parameter data to form a set of association rules. The method can further include suggesting parameter choices to a system user regarding a specific patient based on the set of association rules. In an embodiment, the invention can include a medical system including a server configured to perform association analysis on a set of data representing previously programmed parameter values from a plurality of implanted medical devices to derive a set of association rules. Other embodiments are also included herein.
@misc{mahajan2013systems, title = {Systems and methods for programming implantable medical devices}, author = {Mahajan, Deepa and Dong, Yanting and Ahmad, Muhammad A}, year = {2013}, publisher = {United States Patents}, note = {US Patent 8,346,369}, }

Patents

2023

Patent
Hospital Intelligence Platform

Muhammad Aurangzeb Ahmad, Vijay Chickarmane, Farnaz Sabz Ali Pour, and 2 more authors

2023

Patent Pending

Abs Bib

A system and platform for real-time hospital intelligence integrating machine learning, discrete-event simulation, and clinical data streams to support operational decision-making across health systems. Combines predictive modeling of patient flow, resource allocation, and care escalation with a digital twin framework for prospective simulation of hospital interventions.
@misc{ahmad2023hospital, title = {Hospital Intelligence Platform}, author = {Ahmad, Muhammad Aurangzeb and Chickarmane, Vijay and Sabz Ali Pour, Farnaz and Shariari, Nadia and Dutta Roy, Trideep}, year = {2023}, note = {Patent Pending}, }

2013

Patent
Systems and methods for programming implantable medical devices

Deepa Mahajan, Yanting Dong, and Muhammad A Ahmad

2013

US Patent 8,346,369

Abs Bib HTML

Embodiments of the invention are directed to systems and methods for programming implantable medical devices, amongst other things. In an embodiment, the invention includes a method of programming an implantable medical device. The method can include gathering parameter data representing a set of previously programmed parameter values from a plurality of implanted medical devices. The method can further include performing association analysis on the parameter data to form a set of association rules. The method can further include suggesting parameter choices to a system user regarding a specific patient based on the set of association rules. In an embodiment, the invention can include a medical system including a server configured to perform association analysis on a set of data representing previously programmed parameter values from a plurality of implanted medical devices to derive a set of association rules. Other embodiments are also included herein.
@misc{mahajan2013systems, title = {Systems and methods for programming implantable medical devices}, author = {Mahajan, Deepa and Dong, Yanting and Ahmad, Muhammad A}, year = {2013}, publisher = {United States Patents}, note = {US Patent 8,346,369}, }

Awards & Recognition

2019

Award
CMS AI Health Outcomes Challenge — Finalist

Muhammad Aurangzeb Ahmad

2019

Selected as 1 of 25 finalist teams from 300+ applicants

Abs Bib

Selected as one of 25 finalist teams from over 300 applicants for emergency department forecasting work that reduced patient wait times by half and cut left-without-being-seen (LWBS) rates by one-third. The challenge, run by the Centers for Medicare and Medicaid Services, sought AI solutions to improve health outcomes prediction at scale.
@misc{ahmad2019cms, title = {CMS AI Health Outcomes Challenge — Finalist}, author = {Ahmad, Muhammad Aurangzeb}, year = {2019}, note = {Selected as 1 of 25 finalist teams from 300+ applicants}, }

In the Press

OneZero / Medium · April 2021

Health Care A.I. Needs to Get Real

Featured in this piece arguing that healthcare AI is being deployed ahead of the evidence, and that the field needs more rigorous evaluation standards before clinical adoption at scale.

Read →

Spark Dialog · August 2021

The Problems and Promise of AI in Healthcare

I discuss what AI can and cannot do in clinical settings, where the evidence is strong, where it is overhyped, and what equitable healthcare AI looks like in practice.

Listen →

Digethics · August 2021

Using Data to Address Inequities in Healthcare

I examine how data science and machine learning can identify and reduce health disparities, and the risks of perpetuating bias through poorly designed algorithms.

Listen →

Contact

For research collaboration, reach me at maahmad@uw.edu. For health system partnerships, clinical AI deployment inquiries, or advisory engagements, reach me at vonaurum@gmail.com.