Publications
573 results found
Davids J, Lam K, Nimer A, et al., 2022, AIM in Medical Education, Artificial Intelligence in Medicine, Pages: 319-340, ISBN: 9783030645724
Artificial intelligence (AI) is making a global impact on various professions ranging from commerce to healthcare. This section looks at how it is beginning and will continue to impact other areas such as medical education. The multifaceted yet socrato-didactic methods of education need to evolve to cater for the twenty-firstcentury medical educator and trainee. Advances in machine learning and artificial intelligence are paving the way to new discoveries in medical education delivery. Methods This chapter begins by introducing the broad concepts of AI that are relevant to medical education and then addresses some of the emerging technologies employed to directly cater for aspects of medical education methodology and innovations to streamline education delivery, education assessments, and education policy. It then builds on this to further explore the nature of new artificial intelligence concepts for medical education delivery, educational assessments, and clinical education research discovery in a PRISMAguided systematic review and meta-analysis. Results Results from the meta-analysis showed improvement from using either AI alone or with conventional education methods compared to conventional methods alone. A significant pooled weighted mean difference ES estimate of ES 4.789; CI 1.9-7.67; p 1/4 0.001, I2 1/4 93% suggests a 479% learner improvement across domains of accuracy, sensitivity to performing educational tasks, and specificity. Significant amount of bias between studies was identified and a model to reduce bias is proposed. Conclusion AI in medical education shows considerable promise in domains of improving learners’ outcomes; this chapter rounds off its discussion with the role of AI in simulation methodologies and performance assessments for medical education, highlighting areas where it could augment how we deliver training.
Lidströmer N, Ashrafian H, 2022, Preface, Artificial Intelligence in Medicine, Pages: xiii-xviii
Davids J, Bharambe V, Ashrafian H, 2022, AIM in Clinical Neurophysiology and Electroencephalography (EEG), Artificial Intelligence in Medicine, Pages: 1753-1765, ISBN: 9783030645724
Artificial intelligence and its facets of machine and deep learning have permeated into the fabric of our society with widespread adoption. However, the medical community is only recently beginning to embrace its potential for applications in various subspecialties. Clinical neurophysiology, neurology, neurosurgery, and the rest of the neurosciences are seeing considerable impacts in how AI is being utilized across these specialties. EEG analysis using deep learning in the field of neuro-pathophysiology is also gaining rapid traction with a myriad of emerging applications suggesting promise. However, although deep learning has shown considerable potential, the lack of transparency about how models make decisions and the barriers to entry curtail acceptability among clinicians. Some have argued that the stakes for erroneous judgments in the diagnostic pathway remain too high to be completely reliant on AI, while others have embraced its potential and are delivering services using AI. This chapter discusses the role of AI in clinical neurophysiology with an extended focus on epilepsy and EEG analysis. We also highlight some of the areas where AI and its applications have been adopted for characterization of other neurophysiological diagnostic modalities, for instance, in migraine, and end with a discussion of model explainability.
Lidströmer N, Davids J, Sood HS, et al., 2022, AIM in Primary Healthcare, Artificial Intelligence in Medicine, Pages: 711-741, ISBN: 9783030645724
Primary healthcare is a highly interesting generalist field in medicine. Over the coming years, this field will continue to profoundly benefit from AI in medicine, which will result in positive changes in the everyday lives of patients. Medical specialist knowledge will reach out to primary healthcare settings, profoundly altering the whole referral system and its indications. Specialist domains will be distributed widely and remotely, as scientific advances will reach primary care patients and doctors more frequently, rapidly, and accurately, thus tilting the dependency balance in the patientdoctor relationship. Personalized and precision healthcare will reach out to every clinic and patient, and nowhere will it be as obvious as in the primary healthcare setting. AI in primary care will also speed up disease theranostics, which will impact management decisions. Decision support will be abundant for the GP and the patient. Patient power will likely see an increase as patients become more active, well-informed, and independent in information discovery and learning about their own disease, a trend that has already occurred in most developed economies. This trend will likely continue in emerging economies through AI-powered mHealth platforms thanks to the rise in smart phone technologies. Many areas within primary care are entering a revolution: Pharmacogenomics will profoundly change the way we prescribe medications. All types of pattern recognition in image-based specialties will essentially strengthen their presence in the primary care clinic: radiology ranging from flat X-rays to ultrasonography, dermatology, pathology, and parts of ophthalmology and scopic inspections, where other image pattern recognitions can be further expanded. Moreover, interpersonal psychotherapy, follow-ups, and compliance will be armored with surveillance, coaching, and instructing components. Verily, in primary healthcare, the whole medical AI symphony will reach its soaring tutti and eve
Tukra S, Lidströmer N, Ashrafian H, et al., 2022, AI in Surgical Robotics, Artificial Intelligence in Medicine, Pages: 835-854, ISBN: 9783030645724
The future of surgery is tightly knit with the evolution of artificial intelligence (AI) and its thorough involvement in surgical robotics. Robotics long ago became an integral part of the manufacturing industry. The area of healthcare though adds several more layers of complication. In this chapter we elaborate a broad range of issues to be dealt with when a robotic system enters the surgical theater and interacts with human surgeons - from overcoming the limitations of minimally invasive surgery to the enhancement of performance in open surgery. We present the latest from the fields of cognitive surgical robots, focusing on proprioception, intraoperative decision-making, and, ultimately, autonomy. More specifically, we discuss how AI has advanced the research field of surgical tool tracking, haptic feedback and tissue interaction sensing, advanced intraoperative visualization, robot-assisted task execution, and finally land in the crucial development of context-aware decision support.
Lidströmer N, Aresu F, Ashrafian H, 2022, Basic Concepts of Artificial Intelligence: Primed for Clinicians, Artificial Intelligence in Medicine, Pages: 3-20, ISBN: 9783030645724
With the urgent need for automatized algorithm applications to an ever-increasing amount of data and a further decrease of the chances of human errors on crucial tasks, artificial intelligence algorithms were introduced. An expansive demand of AI applications in varying fields led to the development of specifically designed ad hoc algorithms with the role of better estimating (by learning) solutions to the problems. The boost of AI in healthcare right now is a consequence of two things - the availability of big data and better processors, able to train and execute algorithmic tasks, i.e., implementations of these algorithms with neural networks. It will soon be vital for medical students to grasp the principles of AI. The purpose of this major reference textbook on AI in medicine, of which this chapter is the base level introduction, is to become the greatest standard reference work. No area of medicine, preclinical or clinical, will escape the profound effects of AI: the whole healthcare domain will be reshaped thoroughly.
Penney N, Yeung D, Garcia-Perez I, et al., 2021, Longitudinal Multi-omic Phenotyping Reveals Host-microbe Responses to Bariatric Surgery, Glycaemic Control and Obesity
<jats:title>Abstract</jats:title> <jats:p>Resolution of type-2 diabetes (T2D) is common following bariatric surgery, particularly Roux-en-Y gastric bypass (RYGB). However, the underlying mechanisms have not been fully elucidated. To address this we compared the integrated serum, urine and faecal metabolic profiles of obese participants with and without T2D (n=81, T2D=42) with participants who underwent RYGB or sleeve gastrectomy (pre and 3-months post-surgery; n=27), taking diet into account. We co-modelled these data with shotgun metagenomic profiles of the gut microbiota to provide a comprehensive atlas of host-gut microbe responses to bariatric surgery, weight-loss and glycaemic control at the systems level. Bariatric surgery reversed a number of disrupted pathways characteristic of T2D. The differential metabolite set representative of bariatric surgery overlapped with both diabetes (19.3% commonality) and BMI (18.6% commonality). However, the percentage overlap between diabetes and BMI was minimal (4.0% commonality), consistent with weight-independent mechanisms of T2D resolution. The gut microbiota was more strongly correlated to BMI than T2D, although we identified some pathways such as amino acid metabolism that correlated with changes to the gut microbiota and which influence glycaemic control. Improved understanding of GM-host co-metabolism may lead to novel therapies for weight-loss or diabetes.</jats:p>
Acharya A, Judah G, Ashrafian H, et al., 2021, Investigating the implementation of SMS and mobile messaging In Population Screening (The SIPS Study): Protocol for a Delphi Study, JMIR Research Protocols, Vol: 10, Pages: 1-8, ISSN: 1929-0748
BackgroundThe use of mobile messaging including Short Message Service (SMS) and Web-based messaging in healthcare has grown significantly. Using messaging to facilitate patient communication has been advocated in several circumstances including population screening. These programmes, however, pose unique challenges to mobile communication, as messaging is often sent from a central hub to a diverse population with differing needs. Despite this, there is a paucity of robust frameworks to guide implementation. ObjectiveThis protocol describes the methods that will be used to develop a guide for the principles of use of mobile messaging for population screening programmes in England.Methods This modified Delphi study will be conducted in two parts: evidence synthesis and consensus generation. The former will incorporate a literature review of publications from 1st January 2000 to the present. This will elicit key themes to inform an online scoping questionnaire posed to a group of experts from academia, clinical medicine, industry and public health. Thematic analysis of free-text responses by two independent authors will elicit items to be used in the consensus generation. Patient and Public Involvement groups will be convened to ensure that a comprehensive item list is generated, which represents the public’s perspective. Each item will then be anonymously voted upon by experts as to its importance and feasibility of implementation in screening, during three rounds of a Delphi process. Consensus will be defined a priori at 70%, with items considered important and feasible eligible for inclusion into the final recommendation. A list of desirable items (important, but not currently feasible) will be developed to guide future work. ResultsThe Institutional Review Board at Imperial College London has granted ethical approval (20IC6088). Results are expected to involve a list of recommendations to screening services with findings made available to screening services
Dewa L, Lawrance E, Roberts L, et al., 2021, Quality social connection as an active ingredient in digital interventions for young people with depression and anxiety: systematic scoping review and meta-analysis, Journal of Medical Internet Research, Vol: 23, Pages: 1-22, ISSN: 1438-8871
BackgroundDisrupted social connections may negatively impact youth mental health. In contrast, sustained quality social connections (QSC) can improve mental health outcomes. However, few studies have examined how these quality connections impact depression and anxiety outcomes within digital interventions, and conceptualisation is limited.ObjectiveThe study aim was to conceptualise, appraise and synthesise evidence on quality social connection within digital interventions (D-QSC) and the impact on depression and anxiety outcomes for young people (14-24).MethodsA systematic scoping review and meta-analysis was conducted using the Johanna Briggs Institute methodological frameworks and guided by experts with lived experience. Reporting was guided by the Preferred Reporting Items for Systematic reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR). Medline, Embase, PsycInfo and Cumulative Index to Nursing and Allied Health Literature (CINAHL) databases were searched against a comprehensive combination of key concepts on 24th June 2020. Search concepts included young people, digital intervention, depression/anxiety, and social connection. Google was also searched. One reviewer independently screened abstracts/titles and full-text and 10% were screened by a second reviewer. A narrative synthesis was used to structure findings on indicators of D-QSC and mechanisms that facilitate the connection. Indicators of D-QSC from included studies were synthesised to produce a conceptual framework. Results5715 publications were identified and 42 were included. Of these, there were 23,319 participants. Indicators that D-QSC was present varied and included relatedness, having a sense of belonging and connecting to similar people. However, despite the variation, most of the indicators were associated with improved outcomes for depression and anxiety. Negative interactions, loneliness and feeling ignored indicated D-QSC was not present. In ten applicable studies, a meta-an
Aggarwal R, Visram S, Martin G, et al., 2021, Defining the enablers and barriers to the implementation of large-scale healthcare related mobile technology: a qualitative case study in a tertiary hospital setting, JMIR mHealth and uHealth, Vol: 10, Pages: 1-11, ISSN: 2291-5222
Background:The successful implementation of clinical smartphone applications in hospital settings requires close collaboration with industry partners. A large-scale hospital-wide implementation of a clinical mobile application for healthcare professionals developed in partnership with Google Health and academic partners was deployed on a Bring Your Own Device (BYOD) basis using mobile device management (MDM) at our UK academic hospital. As this was the first large-scale implementation of this type of innovation in the UK health system, important insights and lessons learned from the deployment may be useful to other organisations considering implementing similar technology in partnership with commercial companies.Objective:The aims of this study were to define the key enablers and barriers, and to propose a ‘roadmap’ for the implementation of a hospital-wide clinical mobile application developed in collaboration with an industry partner as a data processor and an academic partner for independent evaluation.Methods:Semi-structured interviews were conducted with high-level stakeholders from industry, academia and healthcare providers who had instrumental roles in the implementation of the application at our hospital. The interviews explored participant’s views on the enablers and barriers to the implementation process. Interviews were analysed using a broadly deductive approach to thematic analysis.Results:In total, 14 participants were interviewed. Key enablers identified were the establishment of a steering committee with high-level clinical involvement, well-defined roles and responsibilities between partners, effective communication strategies with end-users, safe information governance precautions and increased patient engagement and transparency. Barriers identified were the lack of dedicated resources for mobile change at our hospital, risk aversion, unclear strategy and regulation, and the implications of BYOD and MDM policies. The key lesson
Yeung KTD, Penney N, Harling L, et al., 2021, Response to comment on "'Does sleeve gastrectomy expose the distal esophagus to severe reflux?' So what? Keep the big picture in perspective", Annals of Surgery, Vol: 274, Pages: e793-e794, ISSN: 0003-4932
Acharya A, Sounderajah V, Ashrafian H, et al., 2021, A systematic review of interventions to improve breast cancer screening health behaviours, Preventive Medicine, Vol: 153, ISSN: 0091-7435
Whilst breast cancer screening has been implemented in many countries, uptake is often suboptimal. Consequently, several interventions targeting non-attendance behaviour have been developed. This systematic review aims to appraise the successes of interventions, identifying and comparing the specific techniques they use to modify health behaviours. A literature search (PROSPERO CRD42020212090) between January 2005 and December 2020 using PubMed, Medline, PsycInfo, EMBASE and Google Scholar was conducted. Studies which investigated patient-facing interventions to increase attendance at breast cancer screening appointments were included. Details regarding the intervention delivery, theoretical background, and contents were extracted, as was quantitative data on the impact on attendance rates, compared to control measures. Interventions were also coded using the Behavioural Change Techniques (BCT) Taxonomy. In total fifty-four studies, detailing eighty interventions, met the inclusion criteria. Only 50% of interventions reported a significant impact on screening attendance. Thirty-two different BCTs were used, with 'prompts/cues' the most commonly incorporated (77.5%), however techniques from the group 'covert learning' had the greatest pooled effect size 0.12 (95% CI 0.05-0.19, P < 0·01, I2 = 91.5%). 'Problem solving' was used in the highest proportion of interventions that significantly increased screening attendance (69.0%). 70% of the interventions were developed using behavioural theories. These results show interventions aimed at increasing screening uptake are often unsuccessful. Commonly used approaches which focus upon explaining the consequences of not attending mammograms were often ineffective. Problem solving, however, has shown promise. These techniques should be investigated further, as should emerging technologies which can enable interventions to be feasibly translated at a population-level.
Ravindran S, Bassett P, Shaw T, et al., 2021, Improving safety and reducing error in endoscopy (ISREE): a survey of UK services, FRONTLINE GASTROENTEROLOGY, Vol: 12, Pages: 593-600, ISSN: 2041-4137
- Author Web Link
- Cite
- Citations: 3
Ashrafian H, 2021, Venus and Mars: chest wall deformity and thoracic disease, LANCET RESPIRATORY MEDICINE, Vol: 9, Pages: 1363-1364, ISSN: 2213-2600
Ravindran S, Matharoo M, Shaw T, et al., 2021, 'Case of the month': a novel way to learn from endoscopy-related patient safety incidents, FRONTLINE GASTROENTEROLOGY, Vol: 12, Pages: 636-643, ISSN: 2041-4137
Ravindran S, Healey C, Coleman M, et al., 2021, DEVELOPMENT OF THE TEAM-ENTS (TEAMWORK IN ENDOSCOPY ASSESSMENT MODULE FOR ENDOSCOPIC NON-TECHNICAL SKILLS) FRAMEWORK, Annual Meeting of the British-Society-of-Gastroenterology (BSG), Publisher: BMJ PUBLISHING GROUP, Pages: A21-A21, ISSN: 0017-5749
Ravindran S, Healey C, Marshall S, et al., 2021, THE ENDOSCOPY SAFETY ATTITUDES QUESTIONNAIRE (ENDO-SAQ): RESULTS OF A PILOT STUDY, Publisher: BMJ PUBLISHING GROUP, Pages: A51-A51, ISSN: 0017-5749
Philpott-Morgan S, Thakrar DB, Symons J, et al., 2021, Characterising the nationwide burden and predictors of unkept outpatient appointments in the National Health Service in England: A cohort study using a machine learning approach, PLOS MEDICINE, Vol: 18, ISSN: 1549-1277
Sounderajah V, Ashrafian H, Rose S, et al., 2021, A quality assessment tool for artificial intelligence-centered diagnostic test accuracy studies: QUADAS-AI, NATURE MEDICINE, Vol: 27, Pages: 1663-1665, ISSN: 1078-8956
- Author Web Link
- Cite
- Citations: 35
Clarke J, Flott K, Crespo R, et al., 2021, Assessing the Safety of Home Oximetry for Covid-19: A multi-site retrospective observational study, BMJ Open, Vol: 11, Pages: 1-9, ISSN: 2044-6055
Objectives To determine the safety and effectiveness of home oximetry monitoring pathways safe for Covid-19 patients in the English NHS.Design Retrospective, multi-site, observational study of home oximetry monitoring for patients with suspected or proven Covid-19 Setting This study analysed patient data from four Covid-19 home oximetry pilot sites in England across primary and secondary care settings.Participants A total of 1338 participants were enrolled in a home oximetry programme across four pilot sites. Participants were excluded if primary care data and oxygen saturations are rest at enrolment were not available. Data from 908 participants was included in the analysis. Interventions Home oximetry monitoring was provided to participants with a known or suspected diagnosis of Covid-19. Participants were enrolled following attendance to emergency departments, hospital admission or referral through primary care services. Results Of 908 patients enrolled into four different Covid-19 home oximetry programmes in England, 771 (84.9%) had oxygen saturations at rest of 95% or more, and 320 (35.2%) were under 65 years of age and without comorbidities. 52 (5.7%) presented to hospital and 28 (3.1%) died following enrolment, of which 14 (50%) had Covid-19 as a named cause of death. All-cause mortality was significantly higher in patients enrolled after admission to hospital (OR 8.70 [2.53-29.89]), compared to those enrolled in primary care. Patients enrolled after hospital discharge (OR 0.31 [0.15-0.68]) or emergency department presentation (OR 0.42 [0.20-0.89]) were significantly less likely to present to hospital than those enrolled in primary care. ConclusionsThis study find that home oximetry monitoring can be a safe pathway for Covid-19 patients; and indicates increases in risk to vulnerable groups and patients with oxygen saturations < 95% at enrolment, and in those enrolled on discharge from hospital. Findings from this evaluation have contributed to the national
Nazarian S, Lam K, Darzi A, et al., 2021, The diagnostic accuracy of smartwatches for the detection of cardiac arrhythmia: a systematic review and meta-analysis, Journal of Medical Internet Research, Vol: 23, ISSN: 1438-8871
Background:A significant morbidity, mortality and financial burden is associated with cardiac rhythm abnormalities. Atrial fibrillation (AF) is the most common type of cardiac arrhythmia. Conventional screening tools are often unsuccessful at detecting AF due to its episodic nature. Smartwatches have gained popularity in recent years as a health screening tool.Objective:The aim of our study was to systematically review and meta-analyse the diagnostic accuracy of smartwatches in the detection of cardiac arrhythmias.Methods:A comprehensive literature search was undertaken using the databases of EMBASE, Medline and the Cochrane Library. PRISMA guidance was followed. Studies reporting use of a smartwatch for detection of cardiac arrythmia were included. Independent proportion and their differences were calculated and pooled through DerSimonian and Laird random-effects modelling. Quality was assessed using the QUADAS-2 tool.Results:A total of 18 studies were analysed, measuring diagnostic accuracy in 424, 371 subjects in total. The overall sensitivity, specificity and accuracy of smartwatches to detect cardiac arrhythmias was 100% (95% CI 0.99-1.00), 95% (95% CI 0.93-0.97) and 97% (95% CI 0.96-0.99), respectively. The pooled PPV and NPV for detecting cardiac arrythmias was 85% 85% (95% CI 0.79-0.90) and 100% (95% CI 1.0-1.0), respectively.Conclusions:This review demonstrates the evolving field of digital disease screening and the increased role of machine learning in healthcare. The current diagnostic accuracy of smartwatch technology for detection of cardiac arrhythmias is high. Whilst the innovative drive of digital devices in healthcare screening will continue to gain momentum, the process of accurate evidence accrual and regulatory standards ready to accept their introduction is strongly needed. Clinical Trial: PROSPERO registration number: CRD42020213237
Acharya A, Judah G, Ashrafian H, et al., 2021, Investigating the Implementation of SMS and Mobile Messaging in Population Screening (the SIPS Study): Protocol for a Delphi Study (Preprint)
<sec> <title>BACKGROUND</title> <p>The use of mobile messaging, including SMS, and web-based messaging in health care has grown significantly. Using messaging to facilitate patient communication has been advocated in several circumstances, including population screening. These programs, however, pose unique challenges to mobile communication, as messaging is often sent from a central hub to a diverse population with differing needs. Despite this, there is a paucity of robust frameworks to guide implementation.</p> </sec> <sec> <title>OBJECTIVE</title> <p>The aim of this protocol is to describe the methods that will be used to develop a guide for the principles of use of mobile messaging for population screening programs in England.</p> </sec> <sec> <title>METHODS</title> <p>This modified Delphi study will be conducted in two parts: evidence synthesis and consensus generation. The former will include a review of literature published from January 1, 2000, to October 1, 2021. This will elicit key themes to inform an online scoping questionnaire posed to a group of experts from academia, clinical medicine, industry, and public health. Thematic analysis of free-text responses by two independent authors will elicit items to be used during consensus generation. Patient and Public Involvement and Engagement groups will be convened to ensure that a comprehensive item list is generated that represents the public’s perspective. Each item will then be anonymously voted on by experts as to its importance and feasibility of implementation in screening during three rounds of a Delphi process. Consensus will be defined a priori at 70%, with items considered important
Acharya A, Lam K, Danielli S, et al., 2021, COVID-19 vaccinations among Black Asian and Minority Ethnic (BAME) groups: Learning the lessons from influenza, International Journal of Clinical Practice, Vol: 75, Pages: 1-3, ISSN: 1368-5031
BackgroundThe COVID-19 vaccination roll-out continues to grow at significant pace around the world. There is, however, growing concern regarding vaccine hesitancy amongst Black, Asian and Minority Ethnic (BAME) populations. Such inequalities have the potential for exposing, an already at-risk population, further. Whilst the COVID-19 vaccination programme is in its infancy, influenza programmes have been undertaken for over 50 years, and may provide invaluable insights. In this commentary, we aim to examine the lessons from influenza vaccinations, and how this can help reduce inequalities with COVID-19 vaccinations.Main TextSeveral factors have been associated with both seasonal and pandemic influenza vaccine hesitancy amongst BAME groups. One of the most prevalent barriers in both types of immunisation programmes is the mistrust of medical organisations. This is often a multi-faceted issue, with previous negative healthcare discrimination, and historical unethical practices contributing towards this scepticism. This mistrust, however, is predominantly aimed towards healthcare systems, as opposed to individual physicians. In fact, physician endorsement is often a strong driver to vaccination, with Black patients who receive this support 8 times more likely to receive seasonal influenza vaccination. On the other hand, with H1N1 pandemic influenza vaccination, social norms or community influence, was an important determinant. In both seasonal and pandemic immunisation programmes, a significant amount of concern regarding side-effects, including misinformation, was reported amongst BAME groups.ConclusionsThe use of community-based approaches, with local advocacy, has the potential to counteract misinformation, and concerns regarding side-effects. Moreover, using consistent physician endorsement not only in media campaigns but also through messaging would potentially help to address longstanding healthcare mistrust amongst minority ethnic groups. Close attention regardin
Che Bakri NA, Kwasnicki R, Dhillon K, et al., 2021, Objective assessment of post-operative morbidity following breast cancer treatments with wearable activity monitors, Annals of Surgical Oncology, Vol: 28, Pages: 5597-5606, ISSN: 1068-9265
BackgroundCurrent validated tools to measure upper limb dysfunction after breast cancer treatment, such as questionnaires, are prone to recall bias and do not enable comparisons between patients. This study aimed to test the feasibility of wearable activity monitors (WAMs) for achieving a continuous, objective assessment of functional recovery by measuring peri-operative physical activity (PA).MethodsA prospective, single-center, non-randomized, observational study was conducted. Patients undergoing breast and axillary surgery were invited to wear WAMs on both wrists in the peri-operative period and then complete upper limb function (DASH) and quality-of-life (EQ-5D-5L) questionnaires. Statistical analyses were performed to determine the construct validity and concurrent validity of WAMs.ResultsThe analysis included 39 patients with a mean age of 55 ± 13.2 years. Regain of function on the surgically treated side was observed to be an increase of arm activity as a percentage of preoperative levels, with the greatest increase observed between the postoperative days 1 and 2. The PA was significantly greater on the side not treated by surgery than on the surgically treated side after week 1 (mean PA, 75.8% vs. 62.3%; p < 0.0005) and week 2 (mean PA, 91.6% vs. 77.4%; p < 0.005). Subgroup analyses showed differences in recovery trends between different surgical procedures. Concurrent validity was demonstrated by a significant negative moderate correlation between the PA and DASH questionnaires (R = −0.506; p < 0.05).ConclusionThis study demonstrated the feasibility and validity of WAMs to objectively measure postoperative recovery of upper limb function after breast surgery, providing a starting point for personalized rehabilitation through early detection of upper limb physical morbidity.
Li E, Clarke J, Neves AL, et al., 2021, Electronic health records, interoperability, and patient safety in health systems of high-income countries: a systematic review protocol, BMJ Open, Vol: 11, ISSN: 2044-6055
Introduction The availability and routine use of electronic health records (EHRs) have become commonplace in healthcare systems of many high-income countries. While there is an ever-growing body ofliterature pertaining to EHR use, evidence surrounding the importance of EHR interoperability and its impact on patient safety remains less clear. There is therefore a need and opportunity to evaluate the evidence available regarding this relationship so as to better inform health informatics development and policies in the years to come. This systematic review aims to evaluate the impact of EHR interoperability on patient safety in health systems of high-income countries. Methods and analysis A systematic literature review will be conducted via a computerised search through four databases: PubMed, Embase, HMIC, and PsycInfo for relevant articles published between 2010 and 2020. Outcomes of interest will include: impact on patient safety, and the broader effects on health systems. Quality of the randomised quantitative studies will be assessed using Cochrane Risk of Bias Tool. Non-randomised papers will be evaluated with the Risk of Bias In Non Randomised Studies - of Interventions (ROBINS-I) tool. Drummond’s Checklist will be utilised for publications pertaining to economic evaluation. The National Institute for Health and Care Excellence (NICE) quality appraisal checklist will be used to assess qualitative studies. A narrative synthesis will be conducted for included studies, and the body of evidence will be summarised in a summary of findings table. Ethics and dissemination This review will summarise published studies with non-identifiable data and thus does not require ethical approval. Findings will be disseminated through preprints, open access peer reviewed publication, and conference presentations
Nazarian S, Glover B, Ashrafian H, et al., 2021, Diagnostic Accuracy of Artificial Intelligence and Computer-Aided Diagnosis for the Detection and Characterization of Colorectal Polyps: Systematic Review and Meta-analysis, JOURNAL OF MEDICAL INTERNET RESEARCH, Vol: 23, ISSN: 1438-8871
- Author Web Link
- Cite
- Citations: 22
Nazarian S, Glover B, Ashrafian H, et al., 2021, The diagnostic accuracy of artificial intelligence and computer-aided diagnosis for the detection and characterisation of colorectal polyps: A systematic review and meta-analysis., Journal of Medical Internet Research, Vol: 23, Pages: 1-18, ISSN: 1438-8871
AimsColonoscopy reduces the incidence of colorectal cancer by allowing detection and resection of neoplastic polyps. Evidence shows that many small polyps are missed on a single colonoscopy. There has been a successful adoption of AI technologies to tackle the issues around missed polyps and as a tool to increase adenoma detection rate (ADR). The aim of this review was to examine the diagnostic accuracy of AI-based technologies in assessing colorectal polyps.MethodA comprehensive literature search was undertaken using the databases of EMBASE, Medline and the Cochrane Library. PRISMA guidelines were followed. Studies reporting use of computer-aided diagnosis for polyp detection or characterisation during colonoscopy were included. Independent proportion and their differences were calculated and pooled through DerSimonian and Laird random-effects modelling. ResultsA total of 48 studies were included. The meta-analysis showed a significant increase in pooled PDR in patients with the use of AI for polyp detection during colonoscopy compared with patients who had standard colonoscopy (OR 1.75; 95% CI 1.56-1.96; p= 0.0005). When comparing patients undergoing colonoscopy with the use of AI to those without, there was also a significant increase in ADR (OR 1.53; 95% CI 1.32-1.77; p= 0005). ConclusionWith the aid of machine learning, there is potential to improve ADR and consequently reduce the incidence of CRC. The current generation of AI-based systems demonstrate impressive accuracy for the detection and characterisation of colorectal polyps. However, this is an evolving field and before its adoption into a clinical setting, AI systems must prove worthy to patients and clinicians.
Chan C, Sounderajah V, Daniels E, et al., 2021, The reliability and quality of YouTube videos as a source of public health information regarding COVID-19 vaccination: cross-sectional study, JMIR Public Health and Surveillance, Vol: 7, ISSN: 2369-2960
Background: Recent emergency authorization and rollout of COVID-19 vaccines by regulatory bodies has generated global attention. As the most popular video-sharing platform globally, YouTube is a potent medium for the dissemination of key public health information. Understanding the nature of available content regarding COVID-19 vaccination on this widely used platform is of substantial public health interest.Objective: This study aimed to evaluate the reliability and quality of information on COVID-19 vaccination in YouTube videos.Methods: In this cross-sectional study, the phrases “coronavirus vaccine” and “COVID-19 vaccine” were searched on the UK version of YouTube on December 10, 2020. The 200 most viewed videos of each search were extracted and screened for relevance and English language. Video content and characteristics were extracted and independently rated against Health on the Net Foundation Code of Conduct and DISCERN quality criteria for consumer health information by 2 authors.Results: Forty-eight videos, with a combined total view count of 30,100,561, were included in the analysis. Topics addressed comprised the following: vaccine science (n=18, 58%), vaccine trials (n=28, 58%), side effects (n=23, 48%), efficacy (n=17, 35%), and manufacturing (n=8, 17%). Ten (21%) videos encouraged continued public health measures. Only 2 (4.2%) videos made nonfactual claims. The content of 47 (98%) videos was scored to have low (n=27, 56%) or moderate (n=20, 42%) adherence to Health on the Net Foundation Code of Conduct principles. Median overall DISCERN score per channel type ranged from 40.3 (IQR 34.8-47.0) to 64.3 (IQR 58.5-66.3). Educational channels produced by both medical and nonmedical professionals achieved significantly higher DISCERN scores than those of other categories. The highest median DISCERN scores were achieved by educational videos produced by medical professionals (64.3, IQR 58.5-66.3) and the lowest median scores by indep
Aggarwal R, Farag S, Martin G, et al., 2021, Patient perceptions on data sharing and applying artificial intelligence to healthcare data: a cross sectional survey, Journal of Medical Internet Research, Vol: 23, Pages: 1-12, ISSN: 1438-8871
Background:Considerable research is being conducted as to how artificial intelligence (AI) can be effectively applied to healthcare. However, for it to be successful, large amounts of health data are required for the training and testing of algorithms. Data sharing for this purpose is controversial, therefore it is imperative to understand patient perceptions on this.Objective:To understand the perspectives and viewpoints of patients regarding the use of their health data in AI research.Methods:A cross-sectional survey with patients was conducted at a large multi-site teaching hospital in the United Kingdom. Data were collected on patient and public views about sharing health data for research and the use of AI on health data.Results:A total of 408 participants completed the survey. Respondents had low levels of prior knowledge of AI in general. Most were comfortable with sharing health data with the NHS (77·9%) or universities (65·7%), but far fewer with commercial organisations such as technology companies (26·4%). The majority endorsed AI research on healthcare data (76·8%) and healthcare imaging (76·4%) in a university setting, providing that concerns about privacy, re-identification of anonymised health care data and consent processes were addressed.Conclusions:There is significant variance in patient perceptions, levels of support, and understanding of health data research and AI. There is a need for greater public engagement and debate to ensure the acceptability of AI research and its successful integration into clinical practice in the future.
Kedrzycki MS, Leiloglou M, Ashrafian H, et al., 2021, Meta-analysis comparing fluorescence imaging with radioisotope and blue dye-guided sentinel node identification for breast cancer surgery., Annals of Surgical Oncology, Vol: 28, Pages: 3738-3748, ISSN: 1068-9265
INTRODUCTION: Conventional methods for axillary sentinel lymph node biopsy (SLNB) are fraught with complications such as allergic reactions, skin tattooing, radiation, and limitations on infrastructure. A novel technique has been developed for lymphatic mapping utilizing fluorescence imaging. This meta-analysis aims to compare the gold standard blue dye and radioisotope (BD-RI) technique with fluorescence-guided SLNB using indocyanine green (ICG). METHODS: This study was registered with PROSPERO (CRD42019129224). The MEDLINE, EMBASE, Scopus, and Web of Science databases were searched using the Medical Subject Heading (MESH) terms 'Surgery' AND 'Lymph node' AND 'Near infrared fluorescence' AND 'Indocyanine green'. Studies containing raw data on the sentinel node identification rate in breast cancer surgery were included. A heterogeneity test (using Cochran's Q) determined the use of fixed- or random-effects models for pooled odds ratios (OR). RESULTS: Overall, 1748 studies were screened, of which 10 met the inclusion criteria for meta-analysis. ICG was equivalent to radioisotope (RI) at sentinel node identification (OR 2.58, 95% confidence interval [CI] 0.35-19.08, p < 0.05) but superior to blue dye (BD) (OR 9.07, 95% CI 6.73-12.23, p < 0.05). Furthermore, ICG was superior to the gold standard BD-RI technique (OR 4.22, 95% CI 2.17-8.20, p < 0.001). CONCLUSION: Fluorescence imaging for axillary sentinel node identification with ICG is equivalent to the single technique using RI, and superior to the dual technique (RI-BD) and single technique with BD. Hospitals using RI and/or BD could consider changing their practice to ICG given the comparable efficacy and improved safety profile, as well as the lesser burden on hospital infrastructure.
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.