MaltSci 麦伴科研

Appearance

Curated Papers > Highly Cited Authoritative Literature on "AI Drug Discovery"

Artificial intelligence in healthcare: past, present and future. ​

Literature Information ​

DOI10.1136/svn-2017-000101
PMID29507784
JournalStroke and vascular neurology
Impact Factor4.9
JCR QuartileQ1
Publication Year2017
Times Cited964
Keywordsbig data, deep learning, neural network, stroke, support vector machine
Literature TypeHistorical Article, Journal Article, Review
ISSN2059-8688
Pages230-243
Issue2(4)
AuthorsFei Jiang, Yong Jiang, Hui Zhi, Yi Dong, Hao Li, Sufeng Ma, Yilong Wang, Qiang Dong, Haipeng Shen, Yongjun Wang

TL;DR ​

This paper explores the transformative role of artificial intelligence (AI) in healthcare, highlighting its applications across various data types and major disease areas, particularly in stroke management for early detection, diagnosis, treatment, and outcome prediction. The study underscores the potential of AI, exemplified by systems like IBM Watson, while also addressing the challenges faced in the real-world implementation of these technologies.

Search for more papers on MaltSci.com ​

big data · deep learning · neural network · stroke · support vector machine

Abstract ​

Artificial intelligence (AI) aims to mimic human cognitive functions. It is bringing a paradigm shift to healthcare, powered by increasing availability of healthcare data and rapid progress of analytics techniques. We survey the current status of AI applications in healthcare and discuss its future. AI can be applied to various types of healthcare data (structured and unstructured). Popular AI techniques include machine learning methods for structured data, such as the classical support vector machine and neural network, and the modern deep learning, as well as natural language processing for unstructured data. Major disease areas that use AI tools include cancer, neurology and cardiology. We then review in more details the AI applications in stroke, in the three major areas of early detection and diagnosis, treatment, as well as outcome prediction and prognosis evaluation. We conclude with discussion about pioneer AI systems, such as IBM Watson, and hurdles for real-life deployment of AI.

MaltSci.com AI Research Service ​

Intelligent ReadingAnswer any question about the paper and explain complex charts and formulas
Locate StatementsFind traces of a specific claim within the paper
Add to KBasePerform data extraction, report drafting, and advanced knowledge mining

Primary Questions Addressed ​

  1. How have historical advancements in AI technology influenced current healthcare applications?
  2. What specific challenges do healthcare professionals face when integrating AI into clinical practice?
  3. In what ways can AI improve patient outcomes beyond diagnosis and treatment?
  4. How does the use of AI in healthcare differ across various medical specialties, such as oncology versus cardiology?
  5. What ethical considerations must be addressed as AI continues to evolve in the healthcare sector?

Key Findings ​

Research Background and Purpose ​

Artificial Intelligence (AI) has the potential to revolutionize healthcare by mimicking human cognitive functions and leveraging vast amounts of healthcare data. The purpose of this review is to explore the current status, applications, and future directions of AI in healthcare, with a particular focus on its applications in stroke management.

Main Methods/Materials/Experimental Design ​

The review systematically categorizes AI applications in healthcare into two main components: Machine Learning (ML) and Natural Language Processing (NLP). It discusses the types of healthcare data analyzed by AI systems, which include both structured data (e.g., imaging, genetic, and electrophysiological data) and unstructured data (e.g., clinical notes). The review also details the various ML techniques, such as classical methods (e.g., Support Vector Machines, Neural Networks) and modern deep learning approaches.

Technical Route Overview ​

Mermaid diagram

Key Results and Findings ​

  1. AI Applications: AI has been effectively applied in major disease areas such as cancer, neurology, and cardiology, with a notable focus on stroke management.

  2. Stroke Applications: The review highlights AI's role in:

    • Early detection and diagnosis using ML techniques like SVM and CNN.
    • Treatment prediction, including outcomes of thrombolysis.
    • Prognosis evaluation through predictive modeling of patient outcomes.

  3. Success Stories: Notable AI systems, such as IBM Watson, demonstrate high accuracy in clinical decision support, with 99% coherence with physician decisions in oncology.

Main Conclusions/Significance/Innovation ​

AI is not positioned to replace human physicians but is expected to assist in clinical decision-making, enhancing diagnostic accuracy and reducing errors. The integration of ML and NLP into healthcare has the potential to significantly improve patient outcomes, particularly in high-stakes areas like stroke management. The review emphasizes the need for continuous training of AI systems with real-world data to maintain and improve their effectiveness.

Research Limitations and Future Directions ​

  • Regulatory Hurdles: The implementation of AI in healthcare faces challenges due to the lack of regulatory standards for assessing AI system safety and efficacy.
  • Data Sharing Issues: Continuous data exchange is essential for AI systems to evolve, yet current healthcare environments often lack incentives for data sharing.
  • Future Research: The review suggests that future research should focus on overcoming these barriers, exploring the continuous integration of AI in real-life clinical settings, and addressing more complex clinical questions through AI applications.

In summary, the review provides a comprehensive overview of the transformative potential of AI in healthcare, particularly in the realm of stroke management, while also acknowledging the existing challenges and future research needs.

References ​

  1. Restoring cortical control of functional movement in a human with quadriplegia. - Chad E Bouton;Ammar Shaikhouni;Nicholas V Annetta;Marcia A Bockbrader;David A Friedenberg;Dylan M Nielson;Gaurav Sharma;Per B Sederberg;Bradley C Glenn;W Jerry Mysiw;Austin G Morgan;Milind Deogaonkar;Ali R Rezai - Nature (2016)
  2. Diagnostic errors in the intensive care unit: a systematic review of autopsy studies. - Bradford Winters;Jason Custer;Samuel M Galvagno;Elizabeth Colantuoni;Shruti G Kapoor;Heewon Lee;Victoria Goode;Karen Robinson;Atul Nakhasi;Peter Pronovost;David Newman-Toker - BMJ quality & safety (2012)
  3. The inevitable application of big data to health care. - Travis B Murdoch;Allan S Detsky - JAMA (2013)
  4. Outcomes and Complications After Endovascular Treatment of Brain Arteriovenous Malformations: A Prognostication Attempt Using Artificial Intelligence. - Hamed Asadi;Hong Kuan Kok;Seamus Looby;Paul Brennan;Alan O'Hare;John Thornton - World neurosurgery (2016)
  5. Integrated analysis of long non-coding RNA competing interactions reveals the potential role in progression of human gastric cancer. - Cheng-Yun Li;Ge-Yu Liang;Wen-Zhuo Yao;Jing Sui;Xian Shen;Yan-Qiu Zhang;Hui Peng;Wei-Wei Hong;Yan-Cheng Ye;Zhi-Yi Zhang;Wen-Hua Zhang;Li-Hong Yin;Yue-Pu Pu - International journal of oncology (2016)
  6. Voxel-based Gaussian naïve Bayes classification of ischemic stroke lesions in individual T1-weighted MRI scans. - Joseph C Griffis;Jane B Allendorfer;Jerzy P Szaflarski - Journal of neuroscience methods (2016)
  7. Radiomics: Images Are More than Pictures, They Are Data. - Robert J Gillies;Paul E Kinahan;Hedvig Hricak - Radiology (2016)
  8. Identifying Neuroimaging Markers of Motor Disability in Acute Stroke by Machine Learning Techniques. - A K Rehme;L J Volz;D-L Feis;I Bomilcar-Focke;T Liebig;S B Eickhoff;G R Fink;C Grefkes - Cerebral cortex (New York, N.Y. : 1991) (2015)
  9. Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs. - Varun Gulshan;Lily Peng;Marc Coram;Martin C Stumpe;Derek Wu;Arunachalam Narayanaswamy;Subhashini Venugopalan;Kasumi Widner;Tom Madams;Jorge Cuadros;Ramasamy Kim;Rajiv Raman;Philip C Nelson;Jessica L Mega;Dale R Webster - JAMA (2016)
  10. Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation. - Konstantinos Kamnitsas;Christian Ledig;Virginia F J Newcombe;Joanna P Simpson;Andrew D Kane;David K Menon;Daniel Rueckert;Ben Glocker - Medical image analysis (2017)

Literatures Citing This Work ​

  1. Recent Patient Health Monitoring Platforms Incorporating Internet of Things-Enabled Smart Devices. - Minhee Kang;Eunkyoung Park;Baek Hwan Cho;Kyu-Sung Lee - International neurourology journal (2018)
  2. Application of artificial intelligence in ophthalmology. - Xue-Li Du;Wen-Bo Li;Bo-Jie Hu - International journal of ophthalmology (2018)
  3. The Application of Medical Artificial Intelligence Technology in Rural Areas of Developing Countries. - Jonathan Guo;Bin Li - Health equity (2018)
  4. History and application of artificial neural networks in dentistry. - Wook Joo Park;Jun-Beom Park - European journal of dentistry (2018)
  5. Aging and drug discovery. - Daniela Bakula;Alexander M Aliper;Polina Mamoshina;Michael A Petr;Amanuel Teklu;Joseph A Baur;Judith Campisi;Collin Y Ewald;Anastasia Georgievskaya;Vadim N Gladyshev;Olga Kovalchuk;Dudley W Lamming;Martijn S Luijsterburg;Alejandro Martín-Montalvo;Stuart Maudsley;Garik V Mkrtchyan;Alexey Moskalev;S Jay Olshansky;Ivan V Ozerov;Alexander Pickett;Michael Ristow;Alex Zhavoronkov;Morten Scheibye-Knudsen - Aging (2018)
  6. Big Data Research in Chronic Kidney Disease. - Xiao-Xi Zeng;Jing Liu;Liang Ma;Ping Fu - Chinese medical journal (2018)
  7. Enhancing the prediction of acute kidney injury risk after percutaneous coronary intervention using machine learning techniques: A retrospective cohort study. - Chenxi Huang;Karthik Murugiah;Shiwani Mahajan;Shu-Xia Li;Sanket S Dhruva;Julian S Haimovich;Yongfei Wang;Wade L Schulz;Jeffrey M Testani;Francis P Wilson;Carlos I Mena;Frederick A Masoudi;John S Rumsfeld;John A Spertus;Bobak J Mortazavi;Harlan M Krumholz - PLoS medicine (2018)
  8. Artificial intelligence-enabled healthcare delivery. - Sandeep Reddy;John Fox;Maulik P Purohit - Journal of the Royal Society of Medicine (2019)
  9. Using machine learning to identify health outcomes from electronic health record data. - Jenna Wong;Mara Murray Horwitz;Li Zhou;Sengwee Toh - Current epidemiology reports (2018)
  10. Blood-Based Biomarkers for Predicting the Risk for Five-Year Incident Coronary Heart Disease in the Framingham Heart Study via Machine Learning. - Meeshanthini V Dogan;Steven R H Beach;Ronald L Simons;Amaury Lendasse;Brandan Penaluna;Robert A Philibert - Genes (2018)

... (954 more literatures)

© 2025 MaltSci - We reshape scientific research with AI technology