Artificial Intelligence in Healthcare

Deep Learning for Identifying Metastatic Breast Cancer (Dayong Wang et al., 2017)

Artificial Intelligence and Machine Learning is revolutionizing the healthcare industry. Here’s what you need to know.

Machine Learning is a growing and diverse field of Artificial Intelligence which studies algorithms that are capable of automatically learning from data and making predictions based on data. Machine learning is one of the most exciting technological areas of study today. Each week there are new advancements, new technologies, new applications, and new opportunities. It’s inspiring, but also overwhelming. That’s why we created this guide to help you keep pace with all these exciting developments.

Whether you’re currently employed in the healthcare industry, working with Produvia or just pursuing an interest in the subject, there will always be something here to inspire you!

Diagnosis

Radiology

Google (USA) used deep learning to detect metastatic breast cancer with 92.5% accuracy [1].

King’s College London (UK) used deep learning to detect medical devices with 91% accuracy and enlarged hearts with 91% accuracy [2].

Stress & Influenza

Institut Teknologi Bandung (Indonesia) used machine learning to predict stress and influenza response by analyzing heart rate data [3].

Disease Progression

Duke University (USA) used machine learning to predict Chronic Kidney Disease (CKD) progression by analyzing multivariate longitudinal data [4].

Hospital Admissions

Duke University and Purdue University (USA) used machine learning to predict hospital admissions by analyzing hierarchical point processes [5].

Clinical Events

Georgia Institute of Technology and Sutter Health (USA) used machine learning to predict clinical events using electronic health records (EHR) [6].

Microscopy Tasks

Makerere University (Uganda) used machine learning to diagnose malaria (in blood smear samples), tuberculosis (in sputum samples) and intestinal parasites (in stool samples) [7].

Voice Disorders

Massachusetts Institute of Technology, Ann Arbor, Harvard Medical School, and Massachusetts General Hospital (USA) used machine learning to diagnose behavioural voice disorders using behavioural differences [8].

Renal Cancer

Memorial Sloan Kettering Cancer Center and Weill Cornell Medicine (USA) used machine learning to achieve mitochondria-based subtyping of renal cancer with an accuracy of 89% [9].

Seizure Detection

McGill University (USA) and University of Toronto (Canada) used machine learning to detect seizures using EEG recordings, seizure type (clonic, atonic, tonic), and gender data [10].

Chronic Diseases

Massachusetts Institute of Technology (USA) and National Cheng Kung University (Taiwan) used machine learning to predict the onset of five chronic diseases based on age group, gender data [11].

Surgery Locations

University of Oxford (UK), Memorial Sloan Kettering Cancer Center (USA), University Hospital Zurich, and ETH Zurich (Switzerland) used machine learning to predict surgery locations for Lumbar Spinal Stenosis (LSS) with 85.4% accuracy [12].

Parkinson’s Disease

University of Barcelona, Hospital Clínic de Barcelona, and Institut d’Investigacions Biomèdiques August Pi i Sunyer (Spain) used machine learning to classify mild cognitive impairment of Parkinson’s disease with 82.6% accuracy [13].

Intensive Unit Care (ICU)

Rochester Institute of Technology and Georgia Institute of Technology (USA) used machine learning to predict ICU mortality with 80% accuracy based on patient’s medications, diagnoses, and lab tests [14].

White Blood Cells (WBCs)

Athelas (USA) used deep learning to classify White Blood Cell (WBC) as Polynuclear or Mononuclear with an accuracy of 98% [15]

Treatment

Bed-Ridden Body Poses

University of California, West Virginia University, and Santa Barbara Cottage Hospital (USA) used artificial intelligence to classify body poses of bed-ridden patients using multimodal and multiview camera data [16]

References

Assisting Pathologists in Detecting Cancer with Deep Learning (Yun Liu et. la, 2017)
Learning what to look in chest X-rays with a recurrent visual attention model (Ypsilantis et. la, 2017)
Shesop Healthcare: Stress and influenza classification using support vector machine kernel (Andrien Ivander Wijaya, 2016)
Predicting Disease Progression with a Model for Multivariate Longitudinal Clinical Data (Joseph Futora et. al., 2016)
A Multitask Point Process Predictive Model (Wenzhao Lian et al., 2015)
Doctor AI: Predicting Clinical Events via Recurrent Neural Networks (Edward Choi et al, 2016)
Deep Convolutional Neural Networks for Microscopy-Based Point of Care Diagnostics (John A Quinn et al., 2016)
Uncovering Voice Misuse Using Symbolic Mismatch (Marzyeh Ghassemi et al., 2016)
Mitochondria-based Renal Cell Carcinoma Subtyping: Learning from Deep vs. Flat Feature Representations (Peter J. Schüffler et al. 2016)
Learning Robust Features using Deep Learning for Automatic Seizure Detection (Pierre Thodoroff et al., 2016)
Transferring Knowledge from Text to Predict Disease Onset (Yun Liu et al., 2016)
MRI-based Surgical Planning for Lumbar Spinal Stenosis (Gabriele Abbati et al, 2017)
Discriminating cognitive status in Parkinson’s disease through functional connectomics and machine learning (Alexandra Abós et al, 2017)
Machine Learning Model Interpretability for Precision Medicine (Gajendra Jung Katuwal et al, 2016)
Classifying White Blood Cells With Deep Learning (Dhruv Parthasarathy, 2017)
Eye-CU: Sleep Pose Classification for Healthcare using Multimodal Multiview Data (Carlos Torres et al., 2016)

If you know of any machine learning applications related to healthcare, please leave a comment below.

If you like the post, please give it a ? below:

Artificial Intelligence in Healthcare was originally published in Produvia Blog on Medium, where people are continuing the conversation by highlighting and responding to this story.

Table of Contents