From clinical trials to diagnosis and surgery, artificial intelligence has the potential to transform medicine.
Nature Outlook |
There are now few areas of our lives that artificial intelligence (AI) does not touch. Not only is medicine no exception, but the potential for digital transformation of health care is especially striking.
Artificial intelligence could help clinicians to interpret scans and tissue samples.
Big data and artificial intelligence could help to accelerate clinical testing.
Without careful implementation, artificial intelligence could widen health-care inequality.
The treatment of many physical and mental-health conditions is going digital.
Autonomous systems are beginning to equal human specialists at precision surgical tasks.
Laboratory-automation start-ups are borrowing a page from the software industry.
The digitisation of medical records in the United States has brought benefits, but not everyone is content with how they have been implemented.
More from Nature Research
This Perspective describes the application of machine learning models in the design, synthesis and characterisation of molecules at different stages in the drug discovery and development process.
Why digitally powered real-world evidence is the fix needed for our broken clinical trials system.
Artificial intelligence outperforms traditional statistical models at predicting a range of clinical outcomes from a patient’s entire raw electronic health record (EHR). A team led by Alvin Rajkomar and Eyal Oren from Google in Mountain View, California, USA, developed a data processing pipeline for transforming EHR files into a standardized format. They then applied deep learning models to data from 216,221 adult patients hospitalized for at least 24 h each at two academic medical centers, and showed that their algorithm could accurately predict risk of mortality, hospital readmission, prolonged hospital stay and discharge diagnosis. In all cases, the method proved more accurate than previously published models. The authors provide a case study to serve as a proof-of-concept of how such an algorithm could be used in routine clinical practice in the future.
Artificial intelligence is beginning to be applied in the medical setting and has potential to improve workflows and errors, impacting patients and clinicians alike.
The authors of this Perspective critically evaluate various artificial intelligence (AI)-based computational approaches used for digital pathology and provide a broad framework to incorporate these tools into clinical oncology, discussing challenges such as the need for well-curated validation datasets, regulatory approval and fair reimbursement strategies.
Computer scientists must identify sources of bias, de-bias training data and develop artificial-intelligence algorithms that are robust to skews in the data, argue James Zou and Londa Schiebinger.
This Perspective examines key ethical challenges of ingestible electronic sensors, which are related to patients, physicians, and society more generally, and provides a comparative analysis of legal regulation of the sensors in the US and Europe.
The safety and security of medical devices driven by software, the software-development processes, and the need for data collection and privacy, all offer challenges and opportunities for device regulation and clinical care.
To bring the full potential of AI to the clinic, practical and regulatory changes need to be made in health systems globally.