Machine learning with asymmetric abstention for biomedical decision-making

Gandouz, Mariem; Holzmann, Hajo; Heider, Dominik

doi:10.1186/s12911-021-01655-y

Cited by 7 publications

(3 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Care should be taken to use abstention, or the removal of instances in a principled and appropriate manner. When there is risk involved in making the wrong classification, abstention can be an important practice, as in medical contexts [ 46 , 47 ]. In other cases there may be a distinctive factor impacting the performance of the classifier on specific instances: for example, when simulated training data fails to capture dynamics in unusual genomic regions.…”

Section: Discussionmentioning

confidence: 99%

“…For example, in the context of genome scans for selection, such unexpected signatures can arise in regions of the genome with idiosyncratic recombination or mutation profiles that are not captured in simulated training data, such as the MHC [44,45]. Designing abstention into classifiers should be considered a best practice [46], especially for biomedical data [47]. Abstention in the context of discriminative classifiers can be addressed with the addition of an "abstention class" in training data [48] or an "abstention option" included in the loss function [49].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Enabling interpretable machine learning for biological data with reliability scores

2023

View full text Add to dashboard Cite

Machine learning tools have proven useful across biological disciplines, allowing researchers to draw conclusions from large datasets, and opening up new opportunities for interpreting complex and heterogeneous biological data. Alongside the rapid growth of machine learning, there have also been growing pains: some models that appear to perform well have later been revealed to rely on features of the data that are artifactual or biased; this feeds into the general criticism that machine learning models are designed to optimize model performance over the creation of new biological insights. A natural question arises: how do we develop machine learning models that are inherently interpretable or explainable? In this manuscript, we describe the SWIF(r) reliability score (SRS), a method building on the SWIF(r) generative framework that reflects the trustworthiness of the classification of a specific instance. The concept of the reliability score has the potential to generalize to other machine learning methods. We demonstrate the utility of the SRS when faced with common challenges in machine learning including: 1) an unknown class present in testing data that was not present in training data, 2) systemic mismatch between training and testing data, and 3) instances of testing data that have missing values for some attributes. We explore these applications of the SRS using a range of biological datasets, from agricultural data on seed morphology, to 22 quantitative traits in the UK Biobank, and population genetic simulations and 1000 Genomes Project data. With each of these examples, we demonstrate how the SRS can allow researchers to interrogate their data and training approach thoroughly, and to pair their domain-specific knowledge with powerful machine-learning frameworks. We also compare the SRS to related tools for outlier and novelty detection, and find that it has comparable performance, with the advantage of being able to operate when some data are missing. The SRS, and the broader discussion of interpretable scientific machine learning, will aid researchers in the biological machine learning space as they seek to harness the power of machine learning without sacrificing rigor and biological insight.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Enabling interpretable machine learning for biological data with reliability scores

2023

View full text Add to dashboard Cite

show abstract

“…Consequently, the usefulness of machine learning in medical image analysis is often not observed in omics analysis. New models and analysis platforms for these problems are being developed by our research group and others [ 100 , 102 , 187 – 190 ], and it is hoped that robust systems that can be applied clinically will be developed in the future.…”

Section: Current Challenges and Possible Future Ai-based Mtbsmentioning

confidence: 99%

Introducing AI to the molecular tumor board: one direction toward the establishment of precision medicine using large-scale cancer clinical and biological information

et al. 2022

View full text Add to dashboard Cite

Since U.S. President Barack Obama announced the Precision Medicine Initiative in his New Year’s State of the Union address in 2015, the establishment of a precision medicine system has been emphasized worldwide, particularly in the field of oncology. With the advent of next-generation sequencers specifically, genome analysis technology has made remarkable progress, and there are active efforts to apply genome information to diagnosis and treatment. Generally, in the process of feeding back the results of next-generation sequencing analysis to patients, a molecular tumor board (MTB), consisting of experts in clinical oncology, genetic medicine, etc., is established to discuss the results. On the other hand, an MTB currently involves a large amount of work, with humans searching through vast databases and literature, selecting the best drug candidates, and manually confirming the status of available clinical trials. In addition, as personalized medicine advances, the burden on MTB members is expected to increase in the future. Under these circumstances, introducing cutting-edge artificial intelligence (AI) technology and information and communication technology to MTBs while reducing the burden on MTB members and building a platform that enables more accurate and personalized medical care would be of great benefit to patients. In this review, we introduced the latest status of elemental technologies that have potential for AI utilization in MTB, and discussed issues that may arise in the future as we progress with AI implementation.

show abstract

Vision for Improving Pregnancy Health: Innovation and the Future of Pregnancy Research

et al. 2022

View full text Add to dashboard Cite

Understanding, predicting, and preventing pregnancy disorders have been a major research target. Nonetheless, the lack of progress is illustrated by research results related to preeclampsia and other hypertensive pregnancy disorders. These remain a major cause of maternal and infant mortality worldwide. There is a general consensus that the rate of progress toward understanding pregnancy disorders lags behind progress in other aspects of human health. In this presentation, we advance an explanation for this failure and suggest solutions. We propose that progress has been impeded by narrowly focused research training and limited imagination and innovation, resulting in the failure to think beyond conventional research approaches and analytical strategies. Investigations have been largely limited to hypothesis-generating approaches constrained by attempts to force poorly defined complex disorders into a single “unifying” hypothesis. Future progress could be accelerated by rethinking this approach. We advise taking advantage of innovative approaches that will generate new research strategies for investigating pregnancy abnormalities. Studies should begin before conception, assessing pregnancy longitudinally, before, during, and after pregnancy. Pregnancy disorders should be defined by pathophysiology rather than phenotype, and state of the art agnostic assessment of data should be adopted to generate new ideas. Taking advantage of new approaches mandates emphasizing innovation, inclusion of large datasets, and use of state of the art experimental and analytical techniques. A revolution in understanding pregnancy-associated disorders will depend on networks of scientists who are driven by an intense biological curiosity, a team spirit, and the tools to make new discoveries.

show abstract

Machine learning with asymmetric abstention for biomedical decision-making

Cited by 7 publications

References 36 publications

Enabling interpretable machine learning for biological data with reliability scores

Enabling interpretable machine learning for biological data with reliability scores

Introducing AI to the molecular tumor board: one direction toward the establishment of precision medicine using large-scale cancer clinical and biological information

Vision for Improving Pregnancy Health: Innovation and the Future of Pregnancy Research

Contact Info

Product

Resources

About