Artificial Intelligence in Healthcare

Published on Oct 1, 2018in Nature Biomedical Engineering18.952
· DOI :10.1038/S41551-018-0305-Z
Kun-Hsing Yu17
Estimated H-index: 17
(Harvard University),
Andrew L. Beam20
Estimated H-index: 20
(Harvard University),
Isaac S. Kohane107
Estimated H-index: 107
(Harvard University)
Artificial intelligence (AI) is gradually changing medical practice. With recent progress in digitized data acquisition, machine learning and computing infrastructure, AI applications are expanding into areas that were previously thought to be only the province of human experts. In this Review Article, we outline recent breakthroughs in AI technologies and their biomedical applications, identify the challenges for further progress in medical AI systems, and summarize the economic, legal and social implications of AI in healthcare.
📖 Papers frequently viewed together
3 Authors (Yann LeCun, ..., Geoffrey E. Hinton)
26.8k Citations
10 Authors (Andre Esteva, ..., Jeffrey Dean)
605 Citations
7 Authors (Andre Esteva, ..., Sebastian Thrun)
3,982 Citations
#1Kun-Hsing Yu (Harvard University)H-Index: 17
#2Isaac S. Kohane (Harvard University)H-Index: 107
On a clear January morning in Florida, a Tesla enthusiast and network entrepreneur was driving his new Tesla Model S on US Highway 27A, returning from a family trip. He had posted dozens of widely circulated YouTube tutorial videos on his vehicle and clearly understood many of the technical details of his car. That day, he let the vehicle run autonomously on Autopilot mode for 37 min, before it crashed into the trailer of a truck turning left. The Autopilot did not identify the white side of the...
63 CitationsSource
#1Scott Lundberg (UW: University of Washington)H-Index: 16
#2Bala G. Nair (UW: University of Washington)H-Index: 16
Last. Su-In Lee (UW: University of Washington)H-Index: 27
view all 11 authors...
Although anaesthesiologists strive to avoid hypoxaemia during surgery, reliably predicting future intraoperative hypoxaemia is not possible at present. Here, we report the development and testing of a machine-learning-based system that predicts the risk of hypoxaemia and provides explanations of the risk factors in real time during general anaesthesia. The system, which was trained on minute-by-minute data from the electronic medical records of over 50,000 surgeries, improved the performance of ...
205 CitationsSource
The risk stratification of prostate cancer and breast cancer tumours from patients relies on histopathology, selective genomic testing, or on other methods employing fixed formalin tissue samples. However, static biomarker measurements from bulk fixed-tissue samples provide limited accuracy and actionability. Here, we report the development of a live-primary-cell phenotypic-biomarker assay with single-cell resolution, and its validation with prostate cancer and breast cancer tissue samples for t...
20 CitationsSource
#2Philip T. LavinH-Index: 1
Last. James C. Folk (UI: University of Iowa)H-Index: 41
view all 5 authors...
Artificial Intelligence (AI) has long promised to increase healthcare affordability, quality and accessibility but FDA, until recently, had never authorized an autonomous AI diagnostic system. This pivotal trial of an AI system to detect diabetic retinopathy (DR) in people with diabetes enrolled 900 subjects, with no history of DR at primary care clinics, by comparing to Wisconsin Fundus Photograph Reading Center (FPRC) widefield stereoscopic photography and macular Optical Coherence Tomography ...
161 CitationsSource
#1Holger A. Haenssle (Heidelberg University)H-Index: 15
#2Christian Fink (Heidelberg University)H-Index: 63
Last. Iris ZalaudekH-Index: 74
view all 66 authors...
Background Deep learning convolutional neural networks (CNN) may facilitate melanoma detection, but data comparing a CNN's diagnostic performance to larger groups of dermatologists are lacking. Methods Google's Inception v4 CNN architecture was trained and validated using dermoscopic images and corresponding diagnoses. In a comparative cross-sectional reader study a 100-image test-set was used (level-I: dermoscopy only; level-II: dermoscopy plus clinical information and images). Main outcome mea...
408 CitationsSource
#1Charlene Liew (CGH: Changi General Hospital)H-Index: 8
#1Charlene Liew (CGH: Changi General Hospital)H-Index: 1
Abstract The rapid development of Artificial Intelligence/deep learning technology and its implementation into routine clinical imaging will cause a major transformation to the practice of radiology. Strategic positioning will ensure the successful transition of radiologists into their new roles as augmented clinicians. This paper describes an overall vision on how to achieve a smooth transition through the practice of augmented radiology where radiologists-in-the-loop ensure the safe implementa...
71 CitationsSource
#1Travers Ching (U.H.: University of Hawaii at Manoa)H-Index: 18
#2Daniel Himmelstein (UPenn: University of Pennsylvania)H-Index: 11
Last. Casey S. Greene (UPenn: University of Pennsylvania)H-Index: 38
view all 36 authors...
Deep learning describes a class of machine learning algorithms that are capable of combining raw inputs into layers of intermediate features. These algorithms have recently shown impressive results...
696 CitationsSource
#1L. D. Jones (Stanford University)H-Index: 1
#2David E. Golan (Barts Health NHS Trust)H-Index: 66
Last. Manoj Ramachandran (Barts Health NHS Trust)H-Index: 27
view all 4 authors...
30 CitationsSource
#1Jonathan Krause (Google)H-Index: 23
#2Varun Gulshan (Google)H-Index: 8
Last. Dale R. Webster (Google)H-Index: 22
view all 8 authors...
Purpose Use adjudication to quantify errors in diabetic retinopathy (DR) grading based on individual graders and majority decision, and to train an improved automated algorithm for DR grading. Design Retrospective analysis. Participants Retinal fundus images from DR screening programs. Methods Images were each graded by the algorithm, U.S. board-certified ophthalmologists, and retinal specialists. The adjudicated consensus of the retinal specialists served as the reference standard. Main Outcome...
147 CitationsSource
#1Virginia Dignum (TU Delft: Delft University of Technology)H-Index: 30
68 CitationsSource
Cited By300
#1Andrea Duggento (University of Rome Tor Vergata)H-Index: 18
#2Allegra Conti (University of Rome Tor Vergata)H-Index: 9
Last. Nicola Toschi (University of Rome Tor Vergata)H-Index: 37
view all 5 authors...
Deep Learning (DL) algorithms are a set of techniques that exploit large and/or complex real-world datasets for cross-domain and cross-discipline prediction and classification tasks. DL architectures excel in computer vision tasks, and in particular image processing and interpretation. This has prompted a wave of disruptingly innovative applications in medical imaging, where DL strategies have the potential to vastly outperform human experts. This is particularly relevant in the context of histo...
1 CitationsSource
#1Milad Mirbabaie (University of Paderborn)H-Index: 10
#2Lennart Hofeditz (University of Duisburg-Essen)H-Index: 3
Last. Stefan Stieglitz (University of Duisburg-Essen)H-Index: 24
view all 0 authors...
The application of artificial intelligence (AI) in hospitals yields many advantages but also confronts healthcare with ethical questions and challenges. While various disciplines have conducted specific research on the ethical considerations of AI in hospitals, the literature still requires a holistic overview. By conducting a systematic discourse approach highlighted by expert interviews with healthcare specialists, we identified the status quo of interdisciplinary research in academia on ethic...
#1Steven LichtenbergH-Index: 1
#2Oxana P. TrifonovaH-Index: 11
Last. Petr G. LokhovH-Index: 15
view all 0 authors...
Laboratory-developed tests (LDTs) are a subset of in vitro diagnostic devices, which the US Food and Drug Administration defines as "tests that are manufactured by and used within a single laboratory". The review describes the emergence and history of LDTs. The current state and development prospects of LDTs based on metabolomics are analyzed. By comparing LDTs with the scientific metabolomics study of human bio samples, the characteristic features of metabolomic LDT are shown, revealing its ess...
#1He Huang (USST: University of Shanghai for Science and Technology)H-Index: 1
#2Po-Chou Shih (CYUT: Chaoyang University of Technology)
Last. Wei Gao (SJTU: Shanghai Jiao Tong University)H-Index: 2
view all 0 authors...
In the era of artificial intelligence, the healthcare industry is undergoing tremendous innovation and development based on sophisticated AI algorithms. Focusing on diagnosis process and target disease, this study theoretically proposed an integrated model to optimize traditional medical expense system, and ultimately helps medical staff and patients make more reliable decisions. From the new perspective of total expense estimation and detailed expense analysis, the proposed model innovatively c...
#1Prathamesh ChuriH-Index: 5
#2Ambika PawarH-Index: 4
view all 0 authors...
Background: According to the renowned and Oscar award-winning American actor and film director Marlon Brando, “privacy is not something that I am merely entitled to, it is an absolute prerequisite.” Privacy threats and data breaches occur daily, and countries are mitigating the consequences caused by privacy and data breaches. The Indian healthcare industry is one of the largest and rapidly developing industry. Overall, healthcare management is changing from disease-centric into patient-centric ...
Last. Su Ec
view all 0 authors...
Prognostic prediction of prelabor rupture of membrane (PROM) lacks of sample size and external validation. We compared a statistical model, machine learning algorithms, and a deep-insight visible neural network (DI-VNN) for PROM and estimating the time of delivery. We selected visits, including PROM (n=23,791/170,730), retrospectively from a nationwide health insurance dataset. DI-VNN achieved the best prediction (area under receiver operating characteristics curve [AUROC] 0.73, 95% CI 0.72 to 0...
#1Shukufe Amukarimi (IUMS: Iran University of Medical Sciences)
#2Seeram Ramakrishna (NUS: National University of Singapore)H-Index: 162
Last. Masoud Mozafari (IUMS: Iran University of Medical Sciences)H-Index: 52
view all 0 authors...
Abstract null null The emergence of smart materials (also known as stimuli-responsive materials) has significantly developed the boundaries of modern medicine. This class of materials can operate as an ‘on-off’ switch for multiple applications from nano-to macrometer scale due to their unique characteristics responsive to the environmental changes. As for illustration, smart biomaterials can guide stem cells to enhance tissue regeneration, resulting in numerous applications in tissue engineering...
#4Jan Baumbach (TUM: Technische Universität München)H-Index: 2
#1Ningyu ZhangH-Index: 12
#2Zhen BiH-Index: 2
Last. Xin Shang
view all 0 authors...
Artificial Intelligence (AI), along with the recent progress in biomedical language understanding, is gradually changing medical practice. With the development of biomedical language understanding benchmarks, AI applications are widely used in the medical field. However, most benchmarks are limited to English, which makes it challenging to replicate many of the successes in English for other languages. To facilitate research in this direction, we collect real-world biomedical data and present th...
#1Jaap Goudsmit (Harvard University)H-Index: 128
Last. Julia Wei Wu (Harvard University)
view all 0 authors...
The Human Immunomics Initiative (HII), a joint project between the Harvard T.H. Chan School of Public Health and the Human Vaccines Project (HVP), focuses on studying immunity and the predictability of immuneresponsiveness to vaccines in aging populations. This paper describes the hypotheses and methodological approaches of this new collaborative initiative. Central to our thinking is the idea that predictors of age-related non-communicable diseases are the same as predictors for infectious dise...