Deep Learning Under Scrutiny: Performance Against Health Care Professionals in Detecting Diseases from Medical Imaging - Systematic Review and Meta-Analysis

Faes, Livia; Liu, Xiaoxuan; Kale, Aditya U; Bruynseels, Alice; Shamdas, Mohith; Moraes, Gabriella; Fu, Dun Jack; Wagner, Siegfried; Kern, Christoph; Ledsam, Joseph R.; Schmid, Martin; Topol, Eric J.; Balaskas, Konstantinos; Bachmann, Lucas M.; Keane, Pearse Andrew; Denniston, Alastair K.O.

doi:10.2139/ssrn.3384923

Cited by 11 publications

(8 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With nearly all studies providing detail on data sources, eligibility criteria and diagnosis classification, only a few studies reported study participant flow diagram, distribution of disease severity and distribution of alternative diagnosis. Our findings are in line with those of Faes et al recent systematic reviews 22 in which they found poor reporting and potential biases arising from study design in studies using ML Open access methods for classifying diseases from medical imaging. Similarly, in another systematic review, Christodoulou et al 23 found studies comparing the performance of logistic regression models with ML models for clinical prediction to have poor methodology and reporting quality.…”

Section: Discussionsupporting

confidence: 92%

Reporting quality of studies using machine learning models for medical diagnosis: a systematic review

Yusuf

Atal

et al. 2020

BMJ Open

View full text Add to dashboard Cite

AimsWe conducted a systematic review assessing the reporting quality of studies validating models based on machine learning (ML) for clinical diagnosis, with a specific focus on the reporting of information concerning the participants on which the diagnostic task was evaluated on.MethodMedline Core Clinical Journals were searched for studies published between July 2015 and July 2018. Two reviewers independently screened the retrieved articles, a third reviewer resolved any discrepancies. An extraction list was developed from the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis guideline. Two reviewers independently extracted the data from the eligible articles. Third and fourth reviewers checked, verified the extracted data as well as resolved any discrepancies between the reviewers.ResultsThe search results yielded 161 papers, of which 28 conformed to the eligibility criteria. Detail of data source was reported in 24 of the 28 papers. For all of the papers, the set of patients on which the ML-based diagnostic system was evaluated was partitioned from a larger dataset, and the method for deriving such set was always reported. Information on the diagnostic/non-diagnostic classification was reported well (23/28). The least reported items were the use of reporting guideline (0/28), distribution of disease severity (8/28 patient flow diagram (10/28) and distribution of alternative diagnosis (10/28). A large proportion of studies (23/28) had a delay between the conduct of the reference standard and ML tests, while one study did not and four studies were unclear. For 15 studies, it was unclear whether the evaluation group corresponded to the setting in which the ML test will be applied to.ConclusionAll studies in this review failed to use reporting guidelines, and a large proportion of them lacked adequate detail on participants, making it difficult to replicate, assess and interpret study findings.PROSPERO registration numberCRD42018099167.

show abstract

Section: Discussionsupporting

confidence: 92%

Reporting quality of studies using machine learning models for medical diagnosis: a systematic review

Yusuf

Atal

et al. 2020

BMJ Open

View full text Add to dashboard Cite

show abstract

“…To repeat, we should take preliminary reports on the reliability of AI systems in medicine with a grain of salt. As of yet, it is hard to reproduce the results of various machine learning studies, which makes it difficult to convince the medical community of their reliability and accuracy (Faes et al 2019;Olorisade et al 2017). As of yet, there are no standardized performance metrics for machine learning systems, which makes it hard to compare these systems with each other and with human practitioners ( Japkowicz & Shah 2011).…”

Section: Black-box Medicinementioning

confidence: 99%

“…If a general practitioner is unsure about how to interpret, say, a MR image, it seems perfectly reasonable to say that he should adopt the opinion that an expert in MRI interpretation would form after inspecting the image. In see Faes et al (2019). As a reviewer for this journal interestingly noted, this observation might point towards a correlation between the amount of information that a clinician has and the degree to which he or she is epistemically obliged to rely on AI systems in decision making.…”

Section: Black-box Medicinementioning

confidence: 99%

Artificial Intelligence and Patient-Centered Decision-Making

2020

View full text Add to dashboard Cite

Advanced AI systems are rapidly making their way into medical research and practice, and, arguably, it is only a matter of time before they will surpass human practitioners in terms of accuracy, reliability, and knowledge. If this is true, practitioners will have a prima facie epistemic and professional obligation to align their medical verdicts with those of advanced AI systems. However, in light of their complexity, these AI systems will often function as black boxes: the details of their contents, calculations, and procedures cannot be meaningfully understood by human practitioners. When AI systems reach this level of complexity, we can also speak of black-box medicine. In this paper, we want to argue that black-box medicine conflicts with core ideals of patient-centered medicine. In particular, we claim, black-box medicine is not conducive for supporting informed decision making based on shared information, shared deliberation, and shared mind between practitioner and patient.

show abstract

“…In some medical domains, the use of AI systems will replace a considerable part of the work of human experts [12]. However, performance comparisons between AI systems and human experts suffer from the difficulty in reproducing and comparing results due to the lack of a unified approach [11,13,14]. Yet, it is reasonable to assume that AI systems will increasingly gain in epistemic authority, even though the assistive role of AI is frequently emphasized [15].…”

Section: Ai-based Decision Support In Healthcarementioning

confidence: 99%

AI support for ethical decision-making around resuscitation: proceed with care

et al. 2021

View full text Add to dashboard Cite

Artificial intelligence (AI) systems are increasingly being used in healthcare, thanks to the high level of performance that these systems have proven to deliver. So far, clinical applications have focused on diagnosis and on prediction of outcomes. It is less clear in what way AI can or should support complex clinical decisions that crucially depend on patient preferences. In this paper, we focus on the ethical questions arising from the design, development and deployment of AI systems to support decision-making around cardiopulmonary resuscitation and the determination of a patient’s Do Not Attempt to Resuscitate status (also known as code status). The COVID-19 pandemic has made us keenly aware of the difficulties physicians encounter when they have to act quickly in stressful situations without knowing what their patient would have wanted. We discuss the results of an interview study conducted with healthcare professionals in a university hospital aimed at understanding the status quo of resuscitation decision processes while exploring a potential role for AI systems in decision-making around code status. Our data suggest that (1) current practices are fraught with challenges such as insufficient knowledge regarding patient preferences, time pressure and personal bias guiding care considerations and (2) there is considerable openness among clinicians to consider the use of AI-based decision support. We suggest a model for how AI can contribute to improve decision-making around resuscitation and propose a set of ethically relevant preconditions—conceptual, methodological and procedural—that need to be considered in further development and implementation efforts.

show abstract

Deep Learning Under Scrutiny: Performance Against Health Care Professionals in Detecting Diseases from Medical Imaging - Systematic Review and Meta-Analysis

Cited by 11 publications

References 0 publications

Reporting quality of studies using machine learning models for medical diagnosis: a systematic review

Reporting quality of studies using machine learning models for medical diagnosis: a systematic review

Artificial Intelligence and Patient-Centered Decision-Making

AI support for ethical decision-making around resuscitation: proceed with care

Contact Info

Product

Resources

About