Artificial intelligence and surgical innovation: lower limb arthroplasty

Artificial intelligence and surgical innovation: lower limb arthroplasty.
Br J Hosp Med (Lond). 2020 Oct 2;81(10):1-7. doi: 10.12968/hmed.2020.0309. Epub 2020 Oct 6.

• A review of the use of artificial intelligence and surgical innovation in lower limb arthroplasty, with a particular focus on robotic-assisted surgery in total knee arthroplasty.

Can Machine-learning Algorithms Predict Early Revision TKA in the Danish Knee Arthroplasty Registry?

Can Machine-learning Algorithms Predict Early Revision TKA in the Danish Knee Arthroplasty Registry?
Clin Orthop Relat Res. 2020;10.1097/CORR.0000000000001343. doi:10.1097/CORR.0000000000001343

• Although several well-known presurgical risk factors for revision were coupled with four different machine learning methods, the authors could not develop a clinically useful model capable of predicting early TKA revisions in the Danish Knee Arthroplasty Registry based on preoperative data.

Artificial intelligence for analysing CT brain scans

Artificial intelligence for analysing CT brain scans
NICE Medtech innovation briefing [MIB207] 17 March 2020

• Review of six AI software packages designed to automatically detect and notify healthcare professionals of abnormalities after analysis of brain CT scans. Includes costs.

International evaluation of an AI system for breast cancer screening

International evaluation of an AI system for breast cancer screening
Nature v577, p89–94 (1 January 2020)

• DeepMind and Google Health have developed a new AI system to help doctors detect breast cancer early. The researchers trained an algorithm on mammogram images from female patients in the US and UK, and it performed better than human radiologists.

Graft Rejection Prediction Following Kidney Transplantation Using Machine Learning Techniques: A Systematic Review and Meta-Analysis

Graft Rejection Prediction Following Kidney Transplantation Using Machine Learning Techniques: A Systematic Review and Meta-Analysis
MEDINFO 2019: Health and Wellbeing e-Networks for All, Studies in Health Technology and Informatics Volume 264: p10 - 14. DOI 10.3233/SHTI190173

• Analysis of the literature around the role of machine learning (ML) in predicting graft rejection following kidney transplantation identified 14 studies and five different algorithms.

Abstract

Intensive Care Unit Telemedicine

Special issue on Intensive Care Unit Telemedicine,

Critical Care Clinics  July 2019

• Including:
• Telemedicine in Intensive Care Units: A Luxury or Necessity? [editorial]
• Intensive Care Unit Telemedicine in the Era of Big Data, Artificial Intelligence, and Computer Clinical Decision Support Systems. [Abstract]
• [Contact your local NHS library for a copy of articles from this journal]

Can Machine Learning Algorithms Predict Which Patients Will Achieve Minimally Clinically Important Differences From Total Joint Arthroplasty?

Can Machine Learning Algorithms Predict Which Patients Will Achieve Minimally Clinically Important Differences From Total Joint Arthroplasty?
Clin Orthop Relat Res. 2019 Jun;477(6):1267-1279.

• The three machine learning algorithms were tested using hospital registry data regarding total joint arthroplasty (TJA) patients.They were found to have the potential to improve clinical decision-making and patient care by helping to prioritize resources for postsurgical monitoring and informing presurgical discussions of likely outcomes of TJA.

See also

• Artificial Intelligence May Lead to Better Outcomes After Joint Surger, PRNewswire 16 May 2019

A new era: AI and machine learning in prostate cancer

A new era: artificial intelligence and machine learning in prostate cancer
Nature Reviews Urology 15 May 2019

• Machine learning methods are used to identify genes or groups of genes for which expression specificity to predict outcomes of prostate cancer is high and could be used for screening, developing diagnostic tools, determining optimal individualized treatment and producing targeted drug regimens.

Key points

The Topol Review - genomics, digital medicine, AI and robotics

The Topol Review

• An independent report on behalf of the Secretary of State for Health and Social Care, 11 February 2019

This report aims to examine

• how technological and other developments (including in genomics, artificial intelligence, digital medicine and robotics) are likely to change the roles and functions of clinical staff in all professions over the next two decades to ensure safer, more productive, more effective and more personal care for patients;

• what the implications of these changes are for the skills required by the professionals filling these roles, identifying professions or sub-specialisms where these may be particularly significant;

• the consequences for the selection, curricula, education, training, development and lifelong learning of current and future National Health Service staff.

Digital healthcare technologies, defined here as genomics, digital medicine, artificial intelligence (AI) and robotics.

The Review proposes three principles to support the deployment of digital healthcare technologies throughout the NHS:

1. Patients need to be included as partners and informed about health technologies, with a particular focus on vulnerable/marginalised groups to ensure equitable access.

2. The healthcare workforce needs expertise and guidance to evaluate new technologies, using processes grounded in real-world evidence.

3. The gift of time: wherever possible the adoption of new technologies should enable staff to gain more time to care, promoting deeper interaction with patients.

Digital technologies will have an impact on patients, carers and the wider community, health workforce, and health service leadership.

Recommendations

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

High-performance medicine: the convergence of human and artificial intelligence
Nature Medicine 25 p44–56, January 2019

• In this review article Eric J. Topol describes the impact Artificial Intelligence is having on medicine for physicians, health systems and patients.

Abstract

Cancer screening review

Cancer screening to be overhauled as part of NHS long term plan to improve care and save lives
NHS England 15 November 2018

• Professor Sir Mike Richards is to lead a major review of national cancer screening programmes.
• The review will look at how latest innovations can be utilised, including the potential use of artificial intelligence, integrating research and encourage more eligible people to be screened. It will also look to learn lessons from recent issues around breast and cervical screening.

Trustedoctor to facilitate virtual consultations for cancer patients

New Digital Health Tech Accelerator Opens Up NHS To Cancer Specialists
Forbes 18 September 2018

• Trustedoctor, one of the most recent additions to the NHS DigitalHealth accelerator program, a cloud-based, open platform that allows specialist physicians to quickly assess patients and consult with expert colleagues in a virtual setting. DigitalHealth.London will be supporting Trustedoctor in deploying a solution that could help alleviate the complexities that surround ongoing cancer care and support.
• According to Professor Karol Sikora, Professor of Oncology and Dean of Medicine at the University of Buckingham. “Trustedoctor’s technology could help to improve connectivity between patients, clinicians and NHS Trusts, speeding up diagnosis. It could also ensure the right expertise can be brought to the patient more speedily and effectively, even to those living at some distance from a cancer centre.”
• According to Paul Grundy, Consultant Neurosurgeon, Southampton Hospital, Chair of NHS England Clinical Reference Group for CNS Tumours and Secretary of the British Neuro-Oncology Society "Trustedoctor could be a great asset to the NHS by facilitating virtual consultations, allowing patients the benefits of being seen in the comfort and convenience of their own home and freeing up valuable clinic space in hospitals for those patients that do require an on-site appointment."

RCP position paper on Artificial intelligence (AI) in health

Artificial intelligence (AI) in health
Royal College of Physicians 3 September 2018

• The RCP has issued recommendations for the use of artificial intelligence (AI) to support doctors in providing patient care. The policy statement urges industry to address real-world challenges, doctors to appraise the technology and regulators to develop guidance and evaluation methods.

DeepMind AI system ‘able to identify eye diseases and make referrals’

Clinically applicable deep learning for diagnosis and referral in retinal disease
Nature Medicine (2018) 13 August 2018

• This research uses a novel deep learning architecture to a clinically heterogeneous set of three-dimensional optical coherence tomography scans from patients referred to a major eye hospital (Moorfields Hospital, London). 
• The research demonstrates performance in making a referral recommendation that reaches or exceeds that of experts on a range of sight-threatening retinal diseases after training on only 14,884 scans. 
• See commentary DeepMind AI system ‘able to identify eye diseases and make referrals’, Digital Health 14 August 2018.

Abstract

Artificial Intelligence in the NHS

Thinking on its own: AI in the NHS
Reform 11 January 2018

• This report illustrates the areas where artificial intelligence (AI) could help the NHS become more efficient and deliver better outcomes for patients. It also highlights the main barriers to the implementation of this technology and suggests some potential solutions. 
• Main issues discussed in the paper include early adopters, potential of AI in the NHS, improving buy-in, getting data right and the ethics of building AI.

AI early diagnosis could save heart and cancer patients

AI early diagnosis could save heart and cancer patients
BBC News 2 January 2018

• Researchers at John Radcliffe Hospital, Oxford have developed an artificial intelligence (AI) system that can diagnose scans for heart disease and lung cancer. The systems will save billions of pounds by enabling the diseases to be picked up much earlier. The heart disease technology will start to be available to NHS hospitals for free this summer.