Leading publications and more for machine learning in healthcare linked here.

Artificial Intelligence in Healthcare - 2020 Year in Review   General  

DOI: 10.13140/RG.2.2.29325.05604

Citation: Piyush Mathur, M. D., et al. "Artificial Intelligence in Healthcare: 2020 Year in Review."

BrainX Community

A review of 5000+ peer reviewed publications related to  artificial intelligence  in healthcare published in 2020 with specialist reviews.

A BrainX Community exclusive!

2019 Year in Review: Machine Learning in Healthcare  General

DOI: 10.13140/RG.2.2.34310.52800

BrainX Community

A review of 3000+ peer reviewed publications related to  artificial intelligence  in healthcare published in 2019 with specialist reviews.

A BrainX Community exclusive!


2018 Year in Review: Machine Learning in Healthcare.  General

BrainX Community

A review of 2000+ articles on machine learning in healthcare published in 2018.A BrainX Community exclusive!


Vardhmaan Jain, Agam Bansal,Jacek Cywinksi, Maged Argalious, Maan Fares, et al.

Machine learning models in predicting post liver transplant  cardiovascular events(MACE), all-cause mortality, and cardiovascular mortality.


Viewpoint on impacting perioperative quality using big data analytics and AI.


A muticenter study comparing the performance of seven automated AI-based DR screening algorithms (including one FDA-approved algorithm) against human graders when analyzing real-world retinal imaging data.


Prediction of hypotension events with physiologic vital sign signatures in the intensive care unit  Critical Care

Joo Heung Yoon, Vincent Jeanselme, Gilles Clermont, et al.

Predicting hypotension using machine learning in ICU using MIMIC 3 dataset.

Another associated article:

Predicting hypotension in the ICU using noninvasive physiological signals

Mina Chookhachizadeh Moghadam, et al.


Predicting the Need for Vasopressors in the Intensive Care Unit Using an Attention Based Deep Learning Model  Critical Care

Kwak, Gloria Hyunjung; Ling, Lowell; Hui, Pan

Predicting then need for vasopressors in ICU based on deep learning model using MIMIC 3 dataset.


In response to ‘The clinical artificial intelligence department: a prerequisite for success’  General

Piyush Mathur, Kamal Maheshwari and Frank Papay

The clinical artificial intelligence department: a prerequisite for success General

Christopher V. Cosgriff, David J. Stone,Gary Weissman,Romain Pirracchio and Leo Anthony Celi

Articles discussing formation of clinical AI department in healthcare institutions to facilitate  AI implementation.


BEHRT: Transformer for Electronic Health Records General

A deep neural sequence transduction model for electronic health records (EHR), capable of simultaneously predicting the likelihood of 301 conditions in one’s future visits.


Hypotension Prediction Index for Prevention of Hypotension during Moderate- to High-risk Noncardiac Surgery: A Pilot Randomized Trial Anesthesiology/Surgery

Kamal Maheshwari et al.

Randomized control trial to assess application and validation of hypotension prediction index intra-operatively.Validation of a machine learning model.

 Watch the abstract video here.


Deep representation learning of electronic health records to unlock patient stratification at scale  General


ConvAE: This scalable framework can help better understand varying etiologies in heterogeneous sub-populations and unlock patterns for EHR-based research.


External Evaluation of 3 Commercial Artificial Intelligence Algorithms for Independent Assessment of Screening Mammograms  Imaging/Radiology

Mattie Salim; Erik Wåhlin ; Karin Dembrower, et al.

External evaluation of AI algorithms showing clinician+AI working together achieves better results.


Machine learning models for perioperative research  Anesthesiology/Surgery

Kamal Maheshwari, Piyush Mathur, AlparslanTuran

Editorial on use of machine learning models for peri-operative research.


Deep learning interpretation of echocardiograms Cardiology

,et al.

Using convolutional neural networks on a large new dataset,deep learning applied to echocardiography can identify local cardiac structures, estimate cardiac function, and predict systemic phenotypes that modify cardiovascular risk but not readily identifiable to human interpretation



Explainable machine learning models to understand determinants of COVID-19 mortality in the United States


​Piyush Mathur, Tavpritesh Sethi, Anya Mathur,Kamal Maheshwari, Jacek B Cywinski, Ashish K Khanna, Simran Dua​, Frank Papay
Feature importance based determinants evaluation using two machine learning models.

C. Beau Hilton,Alex Milinovich et al.

Peronalized machine learning prediction models during and after hospitalization.

Generation and evaluation of artificial mental health records for Natural Language Processing   Behavioral science/Psychiatry

Julia Ive,Natalia Viani,et al.

Application of various Natural Language processing techniques to generate and evaluate health records.


Federated learning in medicine: facilitating multi-institutional collaborations without sharing patient data  General

Micah J. Sheller,Brandon Edwards, et al.

Use of federated learning to support collaboration across institutions while addressing concerns around patient data privacy.


Preoperative CT-based Deep Learning Model for Predicting Disease-Free Survival in Patients with Lung Adenocarcinomas  Imaging

Hyungjin Kim,Jin Mo Goo et al.

Combined use of clinical and imaging data for predictions.


Perioperative intelligence: applications of artificial intelligence in perioperative medicine  Surgery/Anesthesiology

Kamal Maheshwari, Kurt Ruetzler, Bernd Saugel

Commentary highlighting use of AI in perioperative medicine.

A Multicenter, Scan-Rescan, Human and Machine Learning CMR Study to Test Generalizability and Precision in Imaging Biomarker Analysis  General/Cardiology

Anish N. Bhuva, MBBS et al

Interesting approach to assess accuracy of ML algorithms and their reproducibility/generalizability

A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis  General

Xiaoxuan Liu, et al.

A challenge for ML in healthcare is to demonstrate external validation,generalizability and scalability.A detailed review with some great insights.


How to Read Articles That Use Machine Learning  Users’ Guides to the Medical Literature  General

Yun Liu, PhD ; Po-Hsuan Cameron Chen, PhD ; Jonathan Krause, PhD ; et al

Excellent review article on interpreting ML research literature.


High-throughput phenotyping with electronic medical record data using a common semi-supervised approach (PheCAP)  General

Yichi Zhang,et al.

A semisupervised pipeline for generation of diagnostic groups from electronic health records.

Screening for cardiac contractile dysfunction using an artificial intelligence–enabled electrocardiogram  Cardiology

Zachi I. Attia,Paul A. Friedman,et al.

Neural network to screen ECGs to discover asymptomatic heart failure.

Human–machine partnership with artificial intelligence for chest radiograph diagnosis  Imaging

Bhavik N. Patel

Novel use of swarm AI to improve prediction of chest x-day diagnosis.


Dissecting racial bias in an algorithm used to manage the health of populations  General

Ziad Obermeyer,Brian Powers,Christine Vogeli,Sendhil Mullainathan

Bias in algorithms can be at all levels.This article highlights a few mechanisms.


Multimodal Machine Learning for Automated ICD Coding General

Keyang Xu, Mike Lam, Jingzhi Pang, Xin Gao, Charlotte Band, Piyush Mathur MD, Frank Papay MD, Ashish K. Khanna MD, Jacek B. Cywinski MD, Kamal Maheshwari MD, Pengtao Xie, Eric Xing
Innovative multimodal machine learning modal with high accuracy for automated generation of diagnosis and associated ICD-10 codes.

Genomic Biomarkers to Predict Resistance to Hypomethylating Agents in Patients With Myelodysplastic Syndromes Using Artificial Intelligence   Cancer

Aziz Nazha, MD et al.

Use of genetic markers to predict treatment efficacy using AI.


A systematic analysis of studies comparing deep learning models against human performance for diagnosis.

Alex Zhavoronkov,et al.

Drug development using machine learning-a real life example


Evaluation of  of AutoML for medical image classification models.


An artificial intelligence-enabled ECG algorithm for the identification of patients with atrial fibrillation during sinus rhythm: a retrospective analysis of outcome prediction Cardiology

Zachi I Attia, MS,Peter A Noseworthy, MD,et al.

Identification of patients with episodes of  Atrial Fibrillation during normal sinus rhythm using convolutional neural network.

A clinically applicable approach to continuous prediction of future acute kidney injury Nephrology

Nenad Tomašev,Xavier Glorot

An artificial Intelligence algorithm to identify patients at risk for acute kidney injury as early as 48 hours before onset.


Artificial Intelligence in Critical Care  Critical care

Piyush Mathur MD, FCCM; Michael L. Burns, MD, PhD

A primer on AI and review of AI research/applications in critical care.

Artificial Intelligence for Clinical Trial Design Research

Deep Learning to Assess Long-term Mortality From Chest Radiographs Imaging/Radiology

Michael T. Lu, MD, MPH; Alexander Ivanov, BS; Thomas Mayrhofer, PhD; et al

Use of Deep Learning for prognosis using Chest X-Rays.

Machine learning as a supportive tool to recognize cardiac arrest in emergency calls Emergency Medicine

Fredrik Folke,Annette Kjær Ersbøll,Helle Collatz Christensen,et al.

Use of machine learning to recognize out of hospital cardiac arrests from dispatcher calls.

Assessment of Deep Natural Language Processing in Ascertaining Oncologic Outcomes From Radiology Reports  Cancer

Kenneth L. Kehl, MD, MPH; Haitham Elmarakeby, PhD; Mizuki Nishino, MD, MPH; et al

Use of natural language processing to predict outcomes more efficiently in cancer patients.

Outcome Prediction in Postanoxic Coma With Deep Learning Critical care

Tjepkema-Cloostermans,et al.

Outcome prediction using EEG waveform derived deep learning model in patients who had cardiac arrest.

Intensive Care Unit Telemedicine in the Era of Big Data, Artificial Intelligence, and Computer Clinical Decision Support Systems  Critical care

Interesting article combining aspects of Telemedicine and machine learning.

Applications of Machine Learning in Real-Life Digital Health Interventions: Review of the Literature General

Triantafyllidis AK, Tsanas A

An exhaustive review of literature on real life interventions using machine learning applications.


Multitask Learning and Benchmarking with Clinical Time Series Data  General

Hrayr Harutyunyan, Hrant Khachatrian, David C. Kale, Greg Ver Steeg, Aram Galstyan

Interesting use of multimodal architecture and feature engineering for developing prediction models using MIMIC data.


Radiology:Artificial Intelligence Imaging/Radiology

Radiology Society of North America's journal on Artificial Intelligence.Key Imaging publications on AI published here periodically.


The Lancet Digital Health  General

Lancet's digital health focused Journal with new publications posted periodically.

Machine Learning in Medicine  General

Alvin Rajkomar, M.D.,Jeffrey Dean, Ph.D., Isaac Kohane, M.D., Ph.D.

A basic but thorough review of machine learning modeling for healthcare and its challenges.

Applications of machine learning in drug discovery and development  General

Jessica Vamathevan,et al.

An overview of machine learning applications and challenges in drug discovery.

Development and Validation of a Deep Learning–Based Automated Detection Algorithm for Major Thoracic Diseases on Chest Radiographs  Imaging/Radiology

Eui Jin Hwang, MD; Sunggyun Park, MS; Kwang-Nam Jin, MD; et al

Moving from development to validation and generalizability of deep learning algorithms for Chest X-Ray interpretation.

Artificial intelligence in healthcare: past, present and future  General

Fei Jiang, et al.

Review of ML in healthcare.A good primer and interesting data on ML applications.

An investigation of patterns in hemodynamic data indicative of impending hypotension in intensive care  Critical care

Joon Lee, Roger G Mark

Prediction of hypotension in ICU using waveform and other data.

Ease of adoption of clinical natural language processing software: An evaluation of five systems  General

KaiZheng V.G. , et al.

Excellent evaluation of NLP in healthcare and its challenges.

Evaluation of Machine-Learning Algorithms for Predicting Opioid Overdose Risk Among Medicare Beneficiaries With Opioid Prescriptions  General

Wei-Hsuan Lo-Ciganic, PhD ; James L. Huang, PhD ; Hao H. Zhang, PhD ; et al

Machine learning models for prediction of at risk population for opioid overdose.

Modeling and prediction of clinical symptom trajectories in Alzheimer’s disease using longitudinal data  Neurology

Nikhil Bhagwat ,Joseph D. Viviano,Aristotle N. Voineskos,M. Mallar Chakravarty 

Modeling of symptoms to predict  trajectory of Alzheimer's disease.


Fast and accurate view classification of echocardiograms using deep learning  Cardiology

Ali Madani,Ramy Arnaout,Mohammad Mofrad Rima Arnaout 

Accurate echocardiogram view classification using deep learning

Predicting Progression from Mild Cognitive Impairment to Alzheimer's Dementia Using Clinical, MRI, and Plasma Biomarkers via Probabilistic Pattern Classification  Neurology

Igor O. Korolev, Laura L. Symonds, Andrea C. Bozoki

Using multimodal technique to predict progression of Alzheimer's dementia.


Machine learning in healthcare: Nature biomedical engineering  General

Continuously updated Nature journal's collection of  machine learning in healthcare articles.


KenSci publications  General

A comprehensive list of publications of research articles from experts at KenSci.Ranging from predictive analytic applications in healthcare to various frameworks for value based healthcare using machine learning.


Also watch webinar on : "Explainable Machine Learning models for Healthcare AI."

High-performance medicine: the convergence of human and artificial intelligence  General

Eric J.Topol

Excellent article from Dr.Topol,describing advances made in AI/ML application amongst various medical specialities.

BrainX Community's  2018 AI/ML Year in Review is a great supplement to this article.


The reproducibility crisis in the age of digital medicine  General

Aaron Stupple,David Singerman,Leo Anthony Celi 

Reproducibility and validation issues with AI/ML in healthcare addressed in this article.

Machine learning and medical education  General

Vijaya B. Kolachalama,Priya S. Garg 

Perspective on integrating ML training into medical curriculum.

An explainable deep-learning algorithm for the detection of acute intracranial haemorrhage from small datasets  Neurology

Hyunkwang Lee,Sehyo Yune,Mohammad Mansouri,Myeongchan Kim,Shahein H. Tajmir,Claude E. Guerrier,Sarah A. Ebert,Stuart R. Pomerantz,Javier M. Romero,Shahmir Kamalian,Ramon G. Gonzalez,Michael H. Lev & Synho Do 

Deep learning for ICH detection, classification with explainability.

Publications from Laboratory of Quantitative Imaging and Artificial Intelligence (QIAI)  General/Imaging

Excellent and exhaustive research  from Daniel L. Rubin, MD, MS lab at Stanford University, especially focused on Imaging.

Article collection on ML/AI with focus on Imaging/Radiology  Imaging

Good collection of ML articles posted by Canadian Association of Radiologists.Some really good as primers.

Image reconstruction by domain-transform manifold learning  Imaging

Bo Zhu, Jeremiah Z. Liu, Stephen F. Cauley, Bruce R. Rosen & Matthew S. Rosen

AUTOMAP:Innovative image reconstruction process using machine learning.

An Interpretable Machine Learning Model for Accurate Prediction of Sepsis in the ICU  Critical Care

Nemati S, Holder A, Razmi F, Stanley MD, Clifford GD, Buchman TG.

AISE(Artificial Intelligence Sepsis Expert) for Sepsis prediction.

Machine learning for real-time prediction of complications in critical care: a retrospective study  Critical Care

Alexander Meyer, Dina Zverinski, Boris Pfahringer, Jörg Kempfert, Titus Kuehne, Simon H Sündermann, Christof Stamm, Thomas Hofmann, Volkmar Falk, Carsten Eickhoff

Machine learning model for prediction of complications in critically ill patients.

The Artificial Intelligence Clinician learns optimal treatment strategies for sepsis in intensive care  Critical Care

Matthieu Komorowski,Leo A. Celi,Omar Badawi,Anthony C. Gordon & A. Aldo Faisal 

Machine learning to optimize management of sepsis.

Identify and monitor clinical variation using machine intelligence: a pilot in colorectal surgery   Anesthesiology/Surgery

Maheshwari K, Cywinski J, Mathur P, Cummings KC 3rd, Avitsian R, Crone T, Liska D, Campion FX, Ruetzler K, Kurz A.
Machine learning used to identify  variations in clinical practice.

Prediction Models of Functional Outcomes for Individuals in the Clinical High-Risk State for Psychosis or With Recent-Onset Depression.  Behavioral sciences

Nikolaos Koutsouleris, MD; Lana Kambeitz-Ilankovic, PhD; Stephan Ruhrmann, MD; et al

Machine learning predictive model using multimodal data for prediction of functional outcomes in patients with psychiatric disorders.

Informatics, Data Science, and Artificial Intelligence  General

Lisha Zhu, PhD ; W. Jim Zheng, PhD

Viewpoint on relationship of health informatics, data and AI.

Vascular Network Organization via Hough Transform (VaNgOGH): A Novel Radiomic Biomarker for Diagnosis and Treatment Response  Cancer/Imaging

Nathaniel Braman, Prateek Prasanna, Mehdi Alilou, Niha Beig, Anant Madabhushi

Radiomic biomarkers for oncologic diagnosis and treatment management.

Feature Driven Local Cell Graph (FeDeG): Predicting Overall Survival in Early Stage Lung Cancer  Cancer/Imaging

Cheng Lu, et al.

New feature based histopathological approach to predict survival in Lung cancer.

Spatial architecture and arrangement of tumor-infiltrating lymphocytes for predicting likelihood of recurrence in early-stage non-small cell lung cancer  Cancer/Imaging

Germán Corredor,et al.

More and better features being utilized for oncologic disease management.


Classification and mutation prediction from non–small cell lung cancer histopathology images using deep learning  Cancer/Pathology

Nicolas Coudray, Paolo Santiago Ocampo, Theodore Sakellaropoulos, Navneet Narula, Matija Snuderl, David Fenyö, Andre L. Moreira, Narges Razavian & Aristotelis Tsirigos 

Use of convolutional neural networks for classification in Pathology.

Anesthesiology, October 2018 edition focused on Artificial Intelligence.Articles with links below:

Artificial Intelligence for Anesthesia: What the Practicing Clinician Needs to Know: More than Black Magic for the Art of the Dark  Anesthesiology

Michael R. Mathis, M.D.; Sachin Kheterpal, M.D., M.B.A.; Kayvan Najarian, Ph.D.

Development and Validation of a Deep Neural Network Model for Prediction of Postoperative In-hospital Mortality  Anesthesiology

Christine K. Lee, M.S., Ph.D.; Ira Hofer, M.D.; Eilon Gabel, M.D.; Pierre Baldi, Ph.D.; Maxime Cannesson, M.D., Ph.D.

Machine-learning Algorithm to Predict Hypotension Based on High-fidelity Arterial Pressure Waveform Analysis  Anesthesiology

Feras Hatib, Ph.D.; Zhongping Jian, Ph.D.; Sai Buddi, Ph.D.; Christine Lee, M.S.; Jos Settels, M.S.; et al

Supervised Machine-learning Predictive Analytics for Prediction of Postinduction Hypotension  Anesthesiology

Samir Kendale, M.D.; Prathamesh Kulkarni, Ph.D.; Andrew D. Rosenberg, M.D.; Jing Wang, M.D., Ph.D.

AIMed Magazine #04 – Cloud Computing & Big Data  General

AIMed magazine edition focused on healthcare data.

  • Data is the new fuel: a note by Dr Anthony Chang, MD, MBA, MPH, MS
  • The challenge of data protection diversity for AI research by Leo Anthony Celi, MD
  • Great expectations for machine learning in EHRs by Piyush Mathur, MD, FCCM,Ashish Khanna,MD,FCCM
  • Empathy, Values + AI by Jules Sherman, MFA
  • Building a strong future: Diversity & Inclusion in AIMed by Crystal Valentine, PhD; Fran Ayalasomayajula, MPH, PMP; Maxine Mackintosh, PhD; Claire Novorol, PhD


Value of Neighborhood Socioeconomic Status in Predicting Risk of Outcomes in Studies That Use Electronic Health Record Data  General

Nrupen A. Bhavsar, PhD; Aijing GaO, MS, Matthew Phelan, MS; et al

While most studies show the importance of socioeconomic determinants this one demonstrates no value over EHR data.

Machine Learning Applications in Head and Neck Radiation Oncology: Lessons From Open-Source Radiomics Challenges  Cancer/Imaging

Hesham Elhalawami et al.

Lessons learnt from challenge based research in head and neck oncology machine learning applications.

The eICU Collaborative Research Database, a freely available multi-center database for critical care research   General

Tom J. Pollard, Alistair E. W. Johnson, Jesse D. Raffa, Leo A. Celi, Roger G. Mark & Omar Badawi

Article from Nature Journal on description of the EICU Collaborative Research database.

Workshop on Artificial Intelligence in Medical Imaging to foster innovative collaborations in applications for diagnostic medical imaging held by National Institute of Biomedical Imaging and Bioengineering (NIBIB).  General

Watch the videos from the workshop via links below for day 1 and day 2..

Pivotal trial of an autonomous AI-based diagnostic system for detection of diabetic retinopathy in primary care offices  Ophthalmology

Michael D. Abràmoff  Philip T. Lavin, Michele Birch, Nilay Shah and James C. Folk

From retrospective research to pivotal trial leading to FDA approval.Landmark article for use of AI in healthcare, especially using imaging modalities.


Scalable and accurate deep learning with electronic health records  General

Alvin Rajkomar, et al.

Novel methods to use electronic health record(EHR) data for predictive analytics.A must read for anyone using EHR data.

Deep Lesion  Imaging

NIH release of a annotated 32,000 CT scan image dataset from 4400 unique patients for research and development.

DeepLesion: automated mining of large-scale lesion annotations and universal lesion detection with deep learning

Ke Yan; Xiaosong Wang; Le Lu; Ronald M. Summers

Deep Learning: A Primer for Radiologists  Imaging

Detailed basic review on application of machine learning in Radiology.

Intratumoral and peritumoral radiomics for the pretreatment prediction of pathological complete response to neoadjuvant chemotherapy based on breast DCE-MRI  Cancer

Nathaniel M. Braman, Maryam Etesami , Prateek Prasanna , Christina Dubchuk , Hannah Gilmore , Pallavi Tiwari , Donna Pletcha and Anant Madabhushi

Radiomics using DCE-MRI for  prediction of chemotherapy response.

Prostate shapes on pre-treatment MRI between prostate cancer patients who do and do not undergo biochemical recurrence are different: Preliminary Findings  Cancer/Imaging

Soumya Ghose, Rakesh Shiradkar, Mirabela Rusu , Jhimli Mitra, Rajat Thawani , Michael Feldman, Amar C. Gupta, Andrei S. Purysko, Lee Ponsky & Anant Madabhushi

Using MRI to look at Prostate shapes and predict recurrence of Prostate Cancer.

Radiogenomic analysis of hypoxia pathway is predictive of overall survival in Glioblastoma  Cancer/Imaging

Niha Beig, Jay Patel, Prateek Prasanna, Virginia Hill, Amit Gupta, Ramon Correa, Kaustav Bera, Salendra Singh, Sasan Partovi, Vinay Varadan, Manmeet Ahluwalia, Anant Madabhushi & Pallavi Tiwari

Use of radiomic features on MRI to determine prognosis amongst Glioblastoma patients.

Artificial Intelligence in Cardiology  Cardiology

Kipp W. Johnson, Jessica Torres Soto, Benjamin S. Glicksberg, Khader Shameer, Riccardo Miotto, Mohsin Ali, Euan Ashley and Joel T. Dudley

Detailed discussion of various machine learning techniques and applications in context of cardiovascular disease.Very informative for clinicians who are learning the basics of machine learning and its application in healthcare.

A landmark article demonstrating high accuracy of image recognition technology to arrive at a diagnosis.

Machine learning in cardiovascular medicine: are we there yet?  Cardiology

Shameer K,Johnson KW,Glickberg BS,Dudley JT,Sengupta PP

New publications coming everyday exploring the opportunities for application of machine learning in cardiovascular medicine.Opportunities and challenges discussed in this article.

Improving Palliative Care with Deep Learning  General

This article discusses use of electronic health record data to predict mortality and thereby identifying patients who would benefit from palliative care.

What This Computer Needs Is a Physician. Humanism and Artificial Intelligence  General

Abraham Verghese, MD; Nigam H.Shah,MBBS,PhD;Robert A. Harrington, MD

View point in JAMA,discussing the need for improving Electronic Health Records exploring  possibilities using Machine learning and Artificial Intelligence while also addressing their pitfalls.

Towards Automated ICD Coding Using Deep Learning  General

Haoran Shi, Pengtao Xie, Zhiting Hu, Ming Zhang, Eric P. Xing

Deep learning techniques applied on electronic health record data to generate ICD-10 diagnosis with high grade of accuracy.

Artificial intelligence applications in the intensive care unit

Critical Care

C. William Hanson III, MD, FCCM; Bryan E. Marshall, MD, FRCP, FRCA

Review from 2001 of AI applications in data rich extremely complex environment of Intensive Care Unit.Opportunities to apply advanced technologies in healthcare environment were identified many years ago.