Hub for Healthcare // van der Schaar Lab

The Hub for Healthcare matches medical problems to canonical formalisms and solutions via AI, machine learning, and operations research

Healthcare abounds with complex and difficult problems. Many of these are apparent to the clinician in the challenges they face every day in the diagnosis, treatment and management of patients, and are often defined descriptively in terms that are suitable for the profession. Our lab’s objective is to work closely with clinicians to understand these problems and create canonical formalisms from which AI, machine learning and operations research methods can provide rigorous solutions.

This page, known as the Hub for Healthcare, contains a classification of some medical problems and associated examples, and then provides formalisms and methods by which they can be solved. Many medical problems that are traditionally described in terms of clinical domain or disease can thus be reduced to a few common, canonical formalisms and, through these formalisms, solved. The intent here is to help move medicine from art to science.

The Hub for Healthcare is intended as a support resource for the clinical, AI, machine learning and operations research communities to help many of us who struggle to convert the narratives of medicine into strict formalisms that can be solved.

The table below consists of medical problems submitted by clinicians and organized by clinical domain and clinical problem type. For each of these problems, we show the canonical formalism(s) through which these problems should be viewed and solutions using AI, machine learning and operations research that use these formalisms.

Why do we need formalisms?

In this short video, Mihaela van der Schaar explains what we mean by “formalisms,” and why they’re an essential part of the process of solving healthcare problems through the use of AI, machine learning, and operations research.

Using the Hub for Healthcare

The Hub for Healthcare maps problems or questions raised by clinicians to the formalisms that can be used to understand and define these problems, and then to machine learning solutions. These are color-coded, allowing users to see the parts of questions that correspond to specific formalisms.

The table below is fully searchable, filterable, and sortable: you can either browse it, or—if you already know what you’re looking for—use specific keywords and phrases to find problems and discussions related to diseases, medical scenarios, or even by machine learning sub-fields. To search for a particular phrase, use the “Search” box directly above the table.

Hub for Healthcare video tutorial

In this short video, Nick Maxfield explains how the Hub for Healthcare ties real-world medical problems and questions explicitly to formalisms, and then to solutions based on AI, machine learning, and operations research.

Currently the Hub contains problems, formalisms, and solutions primarily related to the acute care medical domain. As this project progresses (in tandem with our lab’s engagement sessions for the clinical community), the Hub will expand to cover medical domains including cancer, cardiovascular disease, respiratory disease, organ transplantation, and many more.

Finally, we include a “Software” column in the table, which contains links to our software packages which are most relevant to addressing each of the problems.

Medical domain(s):

Problem type(s):

Canonical formalism(s):

Software:

Sort	wdt_ID	Medical domain(s)	Problem type(s)	Raised by	Description of problem	Canonical formalism(s)	Solution(s)	Software
2	34	Acute care	Intervention	Dr. Paul Elbers (NDL)	Getting the right dose to the right patient at the right time may save lives. The pharmaco-kinetic models we currently use to guide our dosing strategy consider a very limited number of covariates. How can machine learning utilize high-quality intensive care data to better inform our dosing models?	Causal inference/individual treatment effects	I. Bica, J. Jordon, M. van der Schaar, "Estimating the Effects of Continuous-valued Interventions using Generative Adversarial Networks," Neural Information Processing Systems (NeurIPS), 2020. [Link] I. Bica, A. Alaa, C. Lambert, M. van der Schaar, "From real-world patient data to individualized treatment effects using machine learning: Current and future methods to address underlying challenges," Clinical Pharmacology & Therapeutics, 2020. [Link] I. Bica, A. M. Alaa, J. Jordon, M. van der Schaar, “Estimating Counterfactual Treatment Outcomes over Time through Adversarially Balanced Representations,” International Conference on Learning Representations (ICLR), 2020. [Link] B. Lim, A. Alaa, M. van der Schaar, “Forecasting Treatment Responses Over Time Using Recurrent Marginal Structural Networks,” Neural Information Processing Systems (NeurIPS), 2018. [Link]	TemporAI / Causal Inference
2	26	Acute care, Critical care/ICU	Monitoring, Treatment effects, Intervention	Dr. Ari Ercole (UK)	What is the additional predictive benefit to be gained from keeping a particular patient at high risk of readmission in the ICU for another day of monitoring? If this predictive gain is small, it may be more resource-effective to institute a higher level of monitoring on the ward instead for this individual.	Causal inference/individual treatment effects Active sensing and value of information	I. Bica, A. M. Alaa, J. Jordon, M. van der Schaar, “Estimating Counterfactual Treatment Outcomes over Time through Adversarially Balanced Representations,” International Conference on Learning Representations (ICLR), 2020. [Link] B. Lim, A. Alaa, M. van der Schaar, “Forecasting Treatment Responses Over Time Using Recurrent Marginal Structural Networks,” Neural Information Processing Systems (NeurIPS), 2018. [Link] J. Yoon, W. R. Zame, M. van der Schaar, “Deep Sensing: Active Sensing using Multi-directional Recurrent Neural Networks,” ICLR, 2018. [Link] J. Yoon, J. Jordon, M. van der Schaar, “ASAC: Active Sensing using Actor-Critic Models,” Machine Learning for Healthcare Conference (MLHC), 2019. [Link] A. M. Alaa and M. van der Schaar, “Balancing Suspense and Surprise: Timely Decision Making with Endogenous Information Acquisition,” NeurIPS, 2016. [Link] [Poster] Methods and software available here
2	29	Acute care, Emergency medicine, Hospital medicine	Capacity planning, Clinical manifestations, Competing risks, Intervention, Triaging	Dr. James Ray (UK)	How can machine learning provide tools that help emergency clinicians determine the severity/acuity of patients coming into the department so they can stratify emergency patients and decide what kind of emergency care is needed? Straightforward score systems used at admission time are limited in their utility, and there are a lot of risk factors (such as age, ethnicity, and obesity) that aren’t taken into account, despite being linked to vulnerability.	Prediction Active sensing and value of information Clustering	A. M. Alaa, M. van der Schaar, "AutoPrognosis: Automated Clinical Prognostic Modeling via Bayesian Optimization with Structured Kernel Learning," ICML, 2018. [Link] A. M. Alaa, T. Bolton, E. Di Angelantonio, J. H. F. Rudd, M. van der Schaar, “Cardiovascular Disease Risk Prediction using Automated Machine Learning: A Prospective Study of 423,604 UK Biobank Participants,” PloS One, 2019. [Link] K. Ahuja, M. van der Schaar, "Risk-Stratify: Confident Stratification Of Patients Based On Risk," submitted for publication, 2018. [Link] C. Lee, M. van der Schaar, "Temporal Phenotyping using Deep Predicting Clustering of Disease Progression," International Conference on Machine Learning (ICML), 2020. [Link]	AutoPrognosis TemporAI
2	30	Acute care	Diagnosis, Phenotyping, Clinical manifestations	Dr. James Ray (UK)	What kind of data-driven support software can machine learning provide for differential diagnosis (including phenotyping)?	Clustering	K. Ahuja, M. van der Schaar, "Risk-Stratify: Confident Stratification Of Patients Based On Risk," submitted for publication, 2018. [Link] C. Lee, M. van der Schaar, "Temporal Phenotyping using Deep Predicting Clustering of Disease Progression," International Conference on Machine Learning (ICML), 2020. [Link]
1	37	Transplants	Clinical manifestations, Comorbodities, Diagnosis, Early warning systems, Imaging, Phenotyping, Prognosis, Resource optimization, Risk assessment, Triaging	Dr. William Bernal (UK)	How can I identify those patients who will need transplantation at an earlier stage of their illness?	Time series analysis and forecasting		TemporAI / Prediction TemporAI / Time-to-event Analysis
2	23	Acute care, Critical care/ICU	Risk assessment, Treatment	Dr. Lucas Fleuren (NLD)	Can we predict whether and when a patient on mechanical ventilation can be safely extubated? For a given patient, would the chance of successful extubation change from an additional day on the ventilator?	Causal inference/individual treatment effects (over time)	I. Bica, A. M. Alaa, J. Jordon, M. van der Schaar, “Estimating Counterfactual Treatment Outcomes over Time through Adversarially Balanced Representations,” International Conference on Learning Representations (ICLR), 2020. [Link] B. Lim, A. Alaa, M. van der Schaar, “Forecasting Treatment Responses Over Time Using Recurrent Marginal Structural Networks,” Neural Information Processing Systems (NeurIPS), 2018. [Link] Methods and software available here	TemporAI / Prediction TemporAI / Causal Inference
2	24	Acute care, Hospital medicine, Perioperative medicine	Personalized monitoring, Risk assessment	Dr. Brent Ershoff (USA)	What is the optimal frequency of vital sign measurements for a specific patient in the hospital? For a given patient, do the observed vital signs indicate an increased risk of clinical deterioration and necessitate transferring the patient to a higher level of care?	Active sensing and value of information Time series analysis and forecasting Causal inference/individual treatment effects	J. Yoon, W. R. Zame, M. van der Schaar, “Deep Sensing: Active Sensing using Multi-directional Recurrent Neural Networks,” ICLR, 2018. [Link] J. Yoon, J. Jordon, M. van der Schaar, “ASAC: Active Sensing using Actor-Critic Models,” Machine Learning for Healthcare Conference (MLHC), 2019. [Link] A. M. Alaa and M. van der Schaar, “Balancing Suspense and Surprise: Timely Decision Making with Endogenous Information Acquisition,” NeurIPS, 2016. [Link] [Poster] A. M. Alaa, M. van der Schaar, “Attentive State-Space Modeling of Disease Progression,” Neural Information Processing Systems (NeurIPS), 2019. [Link] C. Lee, J. Yoon, M. van der Schaar, “Dynamic-DeepHit: A Deep Learning Approach for Dynamic Survival Analysis with Competing Risks based on Longitudinal Data,” IEEE Transactions on Biomedical Engineering (TBME), 2019. [Link] D. Jarrett, J. Yoon, and M. van der Schaar, “MATCH-Net: Dynamic Prediction in Survival Analysis using Convolutional Neural Networks,” NeurIPS Machine Learning for Health Workshop, 2018. – Selected as spotlight talk [Link] [Poster] A. Bellot, M. van der Schaar, "Flexible Modelling of Longitudinal Medical Data: A Bayesian Nonparametric Approach,” ACM Transactions on Computing for Healthcare, 2020. [Link] A.M. Alaa, M. van der Schaar, "Deep Multi-task Gaussian Processes for Survival Analysis with Competing Risks," NeurIPS, 2017. [Link] J. Yoon, J. Jordon, M. van der Schaar, “GANITE: Estimation of Individualized Treatment Effects using Generative Adversarial Nets,” ICLR, 2018.[Link] A. M. Alaa, M. van der Schaar, “Validating Causal Inference Models via Influence Functions,” International Conference on Machine Learning (ICML), 2019. [Link] I. Bica, A. M. Alaa, J. Jordon, M. van der Schaar, “Estimating Counterfactual Treatment Outcomes over Time through Adversarially Balanced Representations,” International Conference on Learning Representations (ICLR), 2020. [Link] B. Lim, A. Alaa, M. van der Schaar, “Forecasting Treatment Responses Over Time Using Recurrent Marginal Structural Networks,” Neural Information Processing Systems (NeurIPS), 2018. [Link] Methods and software available here	TemporAI
2	25	Acute care, Perioperative medicine	Risk assessment, Treatment effects	Dr. Brent Ershoff (USA)	Given a patient's preoperative history of either chronic pain or opioid use, can we determine which subgroup of patients may benefit from either an inpatient acute care pain consult or treatment with nonopioid adjunctive medications?	Clustering Causal inference/individual treatment effects	C. Lee, M. van der Schaar, "Temporal Phenotyping using Deep Predicting Clustering of Disease Progression," International Conference on Machine Learning (ICML), 2020. [Link] C. Lee, J. Rashbass, M. van der Schaar, "Outcome-Oriented Deep Temporal Phenotyping of Disease Progression,” accepted to IEEE Transactions on Biomedical Engineering, 2020. A.M. Alaa, M. van der Schaar, "Deep Multi-task Gaussian Processes for Survival Analysis with Competing Risks," NeurIPS, 2017. [Link] J. Yoon, J. Jordon, M. van der Schaar, “GANITE: Estimation of Individualized Treatment Effects using Generative Adversarial Nets,” ICLR, 2018.[Link] A. M. Alaa, M. van der Schaar, “Validating Causal Inference Models via Influence Functions,” International Conference on Machine Learning (ICML), 2019. [Link] I. Bica, A. M. Alaa, J. Jordon, M. van der Schaar, “Estimating Counterfactual Treatment Outcomes over Time through Adversarially Balanced Representations,” International Conference on Learning Representations (ICLR), 2020. [Link] Methods and software available here
1	39	Transplants	Competing risks, Phenotyping, Prognosis	Dr. Thom Daniels (UK)	How can we account for major seismic and rapid changes in care, such as occurred with the introduction of CFTR modulators in 2020, when making predictions about the future risk of death or the need for lung transplantation?	Causal inference/individual treatment effects		TemporAI / Causal Inference
2	33	Acute care, Critical care/ICU	Capacity planning, Early warning systems, Prognosis, Risk assessment, Treatment effects	Dr. Steve Harris (UK)	How do we identify the point at which we transition from non-invasive to invasive ventilation? On one hand, intensive ventilation is not a decision to take lightly; on the other hand, lack of invasive ventilation may in some cases lead to self-induced lung injury.	Time series analysis and forecasting Causal inference/individual treatment effects	A. M. Alaa, M. van der Schaar, “Attentive State-Space Modeling of Disease Progression,” Neural Information Processing Systems (NeurIPS), 2019. [Link] I. Bica, A. M. Alaa, J. Jordon, M. van der Schaar, “Estimating Counterfactual Treatment Outcomes over Time through Adversarially Balanced Representations,” International Conference on Learning Representations (ICLR), 2020. [Link] B. Lim, A. Alaa, M. van der Schaar, “Forecasting Treatment Responses Over Time Using Recurrent Marginal Structural Networks,” Neural Information Processing Systems (NeurIPS), 2018. [Link] Methods and software available here	TemporAI / Causal Inference
2	32	Acute care, Critical care/ICU, Emergency medicine, Hospital medicine	Early warning systems, Resource optimization, Risk assessment	Dr. Thom Daniels (UK)	Existing early warning score systems are blunt tools: they only look at data from a single time point, exclude pathology data or demographics, and don't learn over time. How can machine learning improve early warning scores using all the data clinicians have access to?	Time series analysis and forecasting	A. M. Alaa, M. van der Schaar, "AutoPrognosis: Automated Clinical Prognostic Modeling via Bayesian Optimization with Structured Kernel Learning," ICML, 2018. [Link] J. Yoon, A. M. Alaa, S. Hu, M. van der Schaar, “ForecastICU: A Prognostic Decision Support System for Timely Prediction of Intensive Care Unit Admission,” ICML, 2016. [Link] Methods and software available here	TemporAI / Prediction
2	31	Acute care	Diagnosis, Imaging, Resource optimization	Dr. James Ray (UK)	Given the amount of time tests and scans can take to process, how can machine learning analyze patterns within tests or scans and interpret them more quickly?	Prediction Operations research	T. Kyono, F. J. Gilbert, and M. van der Schaar, "MAMMO: A Deep Learning Solution for Facilitating Radiologist-Machine Collaboration in Breast Cancer Diagnosis," 2018. [Link] A. M. Alaa, T. Bolton, E. Di Angelantonio, J. H. F. Rudd, M. van der Schaar, “Cardiovascular Disease Risk Prediction using Automated Machine Learning: A Prospective Study of 423,604 UK Biobank Participants,” PloS One, 2019. [Link] C. Tekin, O. Atan and M. van der Schaar, “Discover the Expert: Context-Adaptive Expert Selection for Medical Diagnosis,” IEEE Transactions on Emerging Topics in Computing, vol. 3, no. 2, pp. 220-234, June 2015. [Link]
2	27	Acute care, Critical care/ICU	Intervention, Monitoring, Phenotyping, Readmission, Risk assessment, Treatment effects	Dr. Ari Ercole (UK)	Is it possible to better understand and predict the temporal course of unplanned readmissions in order to try and predict a subset of patients that would have benefited from bespoke enhanced monitoring or intervention after discharge, and distinguish them from a group at high risk of unexpected but ultimately sudden deterioration?	Time series analysis and forecasting Clustering Causal inference/individual treatment effects Active sensing and value of information	J. Yoon, A. M. Alaa, S. Hu, M. van der Schaar, “ForecastICU: A Prognostic Decision Support System for Timely Prediction of Intensive Care Unit Admission,” ICML, 2016. [Link] A. Alaa, J. Yoon, S. Hu, and M. van der Schaar, “Personalized Risk Scoring for Critical Care Prognosis using Mixtures of Gaussian Processes,” IEEE Transactions on Biomedical Engineering, 2017. [Link] C. Lee, J. Yoon, M. van der Schaar, “Dynamic-DeepHit: A Deep Learning Approach for Dynamic Survival Analysis with Competing Risks based on Longitudinal Data,” IEEE Transactions on Biomedical Engineering (TBME), 2019. [Link] C. Lee, M. van der Schaar, "Temporal Phenotyping using Deep Predicting Clustering of Disease Progression," International Conference on Machine Learning (ICML), 2020. [Link] C. Lee, J. Rashbass, M. van der Schaar, "Outcome-Oriented Deep Temporal Phenotyping of Disease Progression,” accepted to IEEE Transactions on Biomedical Engineering, 2020. I. Bica, A. M. Alaa, J. Jordon, M. van der Schaar, “Estimating Counterfactual Treatment Outcomes over Time through Adversarially Balanced Representations,” International Conference on Learning Representations (ICLR), 2020. [Link] B. Lim, A. Alaa, M. van der Schaar, “Forecasting Treatment Responses Over Time Using Recurrent Marginal Structural Networks,” Neural Information Processing Systems (NeurIPS), 2018. [Link] J. Yoon, W. R. Zame, M. van der Schaar, “Deep Sensing: Active Sensing using Multi-directional Recurrent Neural Networks,” ICLR, 2018. [Link] J. Yoon, J. Jordon, M. van der Schaar, “ASAC: Active Sensing using Actor-Critic Models,” Machine Learning for Healthcare Conference (MLHC), 2019. [Link] A. M. Alaa and M. van der Schaar, “Balancing Suspense and Surprise: Timely Decision Making with Endogenous Information Acquisition,” NeurIPS, 2016. [Link] [Poster] Methods and software available here	TemporAI
1	38	Transplants	Competing risks, Phenotyping, Prognosis	Dr. Thom Daniels (UK)	How can we use the most up to date research or data to adapt predictions (usually based on data from 10-15 years prior to the time the prediction is made) so that they reflect probable future outcomes, taking into account a change of trajectory in clinical care?	Time series analysis and forecasting		TemporAI / Time-to-event Analysis
2	28	Acute care, Critical care/ICU, Emergency medicine, Hospital medicine	Capacity planning, Early warning systems, Monitoring, Resource optimization, Risk assessment	Dr. Vishnu Chandrabalan (UK)	Healthcare is a finite resource. Is there a way we can model the collective physiological burden of a cohort of patients (based on the physiology of individual patients), and then model the mismatch between that collective burden and the healthcare resources available to treat them? Furthermore, can we look at how this might impact patient flow through various parts of the healthcare system?	Time series analysis and forecasting Operations research	J. Yoon, A. M. Alaa, S. Hu, M. van der Schaar, “ForecastICU: A Prognostic Decision Support System for Timely Prediction of Intensive Care Unit Admission,” ICML, 2016. [Link] A. Alaa, J. Yoon, S. Hu, and M. van der Schaar, “Personalized Risk Scoring for Critical Care Prognosis using Mixtures of Gaussian Processes,” IEEE Transactions on Biomedical Engineering, 2017. [Link] A. M. Alaa, M. van der Schaar, “Attentive State-Space Modeling of Disease Progression,” Neural Information Processing Systems (NeurIPS), 2019. [Link] C. Lee, J. Yoon, M. van der Schaar, “Dynamic-DeepHit: A Deep Learning Approach for Dynamic Survival Analysis with Competing Risks based on Longitudinal Data,” IEEE Transactions on Biomedical Engineering (TBME), 2019. [Link] Z. Qian, A. Alaa, M. van der Schaar, "CPAS: the UK’s National Machine Learning-based Hospital Capacity Planning System for COVID-19," accepted to Machine Learning, 2020. C. Tekin, O. Atan and M. van der Schaar, “Discover the Expert: Context-Adaptive Expert Selection for Medical Diagnosis,” IEEE Transactions on Emerging Topics in Computing, vol. 3, no. 2, pp. 220-234, June 2015. [Link]	TemporAI / Prediction
1	36	Transplants	Clinical manifestations, Comorbodities, Diagnosis, Early warning systems, Imaging, Phenotyping, Prognosis, Resource optimization, Risk assessment, Triaging	Dr. William Bernal (UK)	How can I determine if my patient is too unwell to undergo successful liver transplantation?	Prediction		AutoPrognosis
1	40	Acute care, Cancer, Chronic care, Chronic diseases, Critical care/ICU, Emergency medicine, Health, Hospital medicine, Perioperative medicine, Preventative care, Transplants	Diagnosis, Early warning systems, Intervention, Prevention, Risk assessment	Prof. Chris Watson	How do you analyse data where there are a number of parameters repeatedly collected over time where you perceive the trend to be important, and where no one parameter is believed to be sufficient to predict outcome?	Time series analysis and forecasting Active sensing and value of information		TemporAI
1	41	Transplants	Competing risks, Intervention, Prognosis, Risk assessment, Treatment effects	Dr. Carsten Niemann (DEN)	How can I tell whether a specific patient would benefit from transplant compared to other options for this specific patient (overall survival and quality of life adjusted years)?	Causal inference/individual treatment effects

Note: many of the machine learning algorithms referenced in this table are available as software packages, or research code implementations, that can all be found in our GitHub org.

Our Clinical Advisory Group

Machine learning for medicine is an inherently interdisciplinary area, and cannot be successfully approached unilaterally from the perspective of machine learning.

Our lab has been fortunate enough to benefit from expert guidance and collaborative support from an international network of doctors who are leaders in their respective domains of specialization. Some of our collaborators have kindly agreed to serve as members of a Clinical Advisory Group for the Hub for Healthcare.

Each Clinical Advisory Group member helps us to define the scope and boundaries of their area of specialization, and advises us regarding the problems encountered by clinicians working in their domain.

Notes:
– Affiliations are accurate at the time of writing, but may change; some individuals may have multiple affiliations that are not listed.
– This list generally follows the title/suffix/prefix conventions used by each individual’s affiliated organization, although the “MD” suffix has been homogenized to the “Dr.” prefix where it occurs.

Clinical Advisory Group

Dr. Alexander Gimson

Consultant transplant hepatologist, Cambridge University Hospitals NHS Foundation Trust

Dr. Eoin McKinney

University lecturer in renal medicine, University of Cambridge; Honorary consultant in nephrology and transplantation, Cambridge University Hospitals NHS Foundation Trust

Acute care subgroup

Dr. Maxime Cannesson

Ronald L. Katz, MD, Chair of the UCLA Department of Anesthesiology and Perioperative Medicine

Dr. Paul Elbers

Intensivist at VU medical center, Amsterda; Organizer, Amsterdam Medical Data Science Group

Dr. Ari Ercole

Consultant in anesthesia & intensive care; deputy chief clinical informatics officer, Cambridge University Hospitals NHS Foundation Trust

Dr. Brent Ershoff

Assistant Professor-In-Residence, Department of Anesthesiology
David Geffen School of Medicine, University of California, Los Angeles, USA

Hub for Healthcare