How competitors become collaborators—Bridging the gap(s) between machine learning algorithms and clinicians

Grote, Thomas; Berens, Philipp

doi:10.1111/bioe.12957

Cited by 25 publications

(54 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…

researchers in health economics and epidemiology increasingly leverage ML algorithms with the aim of identifying and even addressing health inequalities (Obermeyer et al, 2019;Chang et al, 2021). This paper articulates an account about how to manage the promise and perils of fair ML in health contexts by drawing on the insight that these systems are best seen as collaborative tools rather than straight decision-making tools.While others have discussed this possibility, the collaboration between humans and algorithms has mostly been understood as a form of epistemic peer (dis)agreement (Bjerring and Busch, 2020;Grote & Berens 2020;Grote & Berens, 2021). Contrary to such a view, we argue that utilizing ML algorithms for the purposes of mitigating health disparities requires us to explore alternative models of collaboration.

…”

mentioning

confidence: 89%

“…While others have discussed this possibility, the collaboration between humans and algorithms has mostly been understood as a form of epistemic peer (dis)agreement (Bjerring and Busch, 2020;Grote & Berens 2020;Grote & Berens, 2021). Contrary to such a view, we argue that utilizing ML algorithms for the purposes of mitigating health disparities requires us to explore alternative models of collaboration.…”

mentioning

confidence: 89%

“…The peer model, if true, provides a plausible rationale for a method of model validation that has featured in several prominent papers about ML in healthcare. In particular, studies that use an antagonistic framing of algorithms competing versus clinical experts, with the former being at least as good or strictly better than the latter, presume that the role of ML algorithms is akin to that of a peer (Gulshan et al, 2016;Esteva et al, 2017;De Fauw et al, 2018; see also Bjerring and Busch, 2021 ;Grote & Berens 2020;Grote & Berens, 2021). While studies indicate, that the combination of a clinician and a ML algorithm bring about more accurate diagnoses as opposed to the clinician deciding in isolation (McKinney et al, 2020;Tschandl et al, 2020), the peer model is to some degree unattractive as it has been shown that clinicians are prone to over-rely on algorithmic advice, thus being led astray when the algorithm decides incorrectly (Tschandl et al, 2020;Gaube et al, 2021).…”

Section: The Auditing Modelmentioning

confidence: 99%

See 2 more Smart Citations

Enabling Fairness in Healthcare Through Machine Learning

Grote

Keeling

2022

Ethics Inf Technol

Self Cite

View full text Add to dashboard Cite

The use of machine learning systems for decision-support in healthcare may exacerbate health inequalities. However, recent work suggests that algorithms trained on sufficiently diverse datasets could in principle combat health inequalities. One concern about these algorithms is that their performance for patients in traditionally disadvantaged groups exceeds their performance for patients in traditionally advantaged groups. This renders the algorithmic decisions unfair relative to the standard fairness metrics in machine learning. In this paper, we defend the permissible use of affirmative algorithms; that is, algorithms trained on diverse datasets that perform better for traditionally disadvantaged groups. Whilst such algorithmic decisions may be unfair, the fairness of algorithmic decisions is not the appropriate locus of moral evaluation. What matters is the fairness of final decisions, such as diagnoses, resulting from collaboration between clinicians and algorithms. We argue that affirmative algorithms can permissibly be deployed provided the resultant final decisions are fair.

show abstract

“…

…”

mentioning

confidence: 89%

mentioning

confidence: 89%

Section: The Auditing Modelmentioning

confidence: 99%

See 1 more Smart Citation

Enabling Fairness in Healthcare Through Machine Learning

Grote

Keeling

2022

Ethics Inf Technol

Self Cite

View full text Add to dashboard Cite

show abstract

“…Ideally, such automated tools serve to support retinal specialists in their decision making. To this end, computational tools need to explain their decisions and communicate their uncertainty to the treating ophthalmologist [20, 21]. In collaboration, a retina specialist assisted by an artificial intelligence (AI) tool can outperform the model alone, e.g.…”

Section: Introductionmentioning

confidence: 99%

“…18 To this end, computational tools need to explain their decisions and communicate their uncertainty to the treating ophthalmologist. 19,20 Here, we develop a convolutional deep learning model based on the concept of multi-task learning. 21,22 Multi-task learning is a generalization of the widely used single-task learning, where models are trained for multiple input-output mappings simultaneously (Fig.…”

Section: Introductionmentioning

confidence: 99%

Multi-task learning for activity detection in neovascular age-related macular degeneration

Ayhan

Faber

Kuehlewein

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Objective: Modeling of the ophthalmologist's decision-making process for activity detection in neovascular age-related macular degeneration with a multi-task convolutional deep neuronal network which takes intra- and subretinal fluid into account. Design: A cohort study to evaluate the multi-task deep learning model for activity detection. Participants: n = 70 patients (46 female, 24 male) attended the University Eye Hospital Tuebingen between 21.2.2018 and 27.6.2018. 3762 optical coherence tomography B-scans (right eye: 2011, left eye: 1751) were acquired from them with Heidelberg Spectralis, Heidelberg, Germany. Methods: B-scans were graded by a retina specialist and an ophthalmology resident, and then used to develop a multi-task deep learning model to concurrently predict disease activity in neovascular age-related macular degeneration along with the presence of sub- and intraretinal fluid. Main outcome measures: Performance metrics compared to single-task networks, visualization of the representation driving the DNN-based decisions using t-distributed stochastic neighbor embedding and analysis of the model's decisions via clinically validated saliency mapping techniques. Results: The multi-task model surpassed single-task networks in accuracy for activity detection. Visualizations via t-distributed stochastic neighbor embedding and saliency maps highlighted that the network's decisions for activity of neovascular age-related macular degeneration were based on the presence of sub- and intraretinal fluids, the optical coherence tomography characteristics used for treatment decision in clinical routine. Conclusion: Multi-task learning increases the performance of neuronal networks for predicting disease activity, while providing clinicians with an easily accessible decision control, which resembles human reasoning.

show abstract

Non-empirical methods for ethics research on digital technologies in medicine, health care and public health: a systematic journal review

Ursin,

Müller,

Funer

et al. 2024

Med Health Care and Philos

View full text Add to dashboard Cite

Bioethics has developed approaches to address ethical issues in health care, similar to how technology ethics provides guidelines for ethical research on artificial intelligence, big data, and robotic applications. As these digital technologies are increasingly used in medicine, health care and public health, thus, it is plausible that the approaches of technology ethics have influenced bioethical research. Similar to the “empirical turn” in bioethics, which led to intense debates about appropriate moral theories, ethical frameworks and meta-ethics due to the increased use of empirical methodologies from social sciences, the proliferation of health-related subtypes of technology ethics might have a comparable impact on current bioethical research. This systematic journal review analyses the reporting of ethical frameworks and non-empirical methods in argument-based research articles on digital technologies in medicine, health care and public health that have been published in high-impact bioethics journals. We focus on articles reporting non-empirical research in original contributions. Our aim is to describe currently used methods for the ethical analysis of ethical issues regarding the application of digital technologies in medicine, health care and public health. We confine our analysis to non-empirical methods because empirical methods have been well-researched elsewhere. Finally, we discuss our findings against the background of established methods for health technology assessment, the lack of a typology for non-empirical methods as well as conceptual and methodical change in bioethics. Our descriptive results may serve as a starting point for reflecting on whether current ethical frameworks and non-empirical methods are appropriate to research ethical issues deriving from the application of digital technologies in medicine, health care and public health.

show abstract

How competitors become collaborators—Bridging the gap(s) between machine learning algorithms and clinicians

Cited by 25 publications

References 0 publications

Enabling Fairness in Healthcare Through Machine Learning

Enabling Fairness in Healthcare Through Machine Learning

Multi-task learning for activity detection in neovascular age-related macular degeneration

Non-empirical methods for ethics research on digital technologies in medicine, health care and public health: a systematic journal review

Contact Info

Product

Resources

About