Prospects and Challenges for Clinical Decision Support in the Era of Big Data

Naqa, Issam El; Kosorok, Michael R.; Jin, Judy; Haken, R.K. Ten

doi:10.1200/cci.18.00002

Cited by 29 publications

(22 citation statements)

References 96 publications

(103 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Finally, in the emerging era of big data [54], large clinical databases are increasingly used to provide insights into decision-making; however, these databases typically do not encode the participants' or the physicians' emotions. This is an area where self-reported outcomes can potentially provide information on emotions, which would otherwise not be measurable.…”

Section: Discussionmentioning

confidence: 99%

Emotions as Social Information in Shared Decision-Making in Oncology

Treffers

Putora

2020

Oncology

View full text Add to dashboard Cite

Emotions play an important role in decision-making and they can impact individual as well as shared decisions. With increasing complexity of the decision, the potential for emotions to influence the outcome increases. Emotions are thus an influential factor in oncological decision-making which is a complex and high-stakes situation. As the shared decisionmaking process is at the center of patient-centric decisions, we model emotions as social information that inform the shared decision-making process. We present and explain a range of emotional concepts, together with a specific clinical example, that can impact the shared decision-making process. Our process model shows that emotions are experienced in various combinations before, during, and after a shared decision is made and how patients' and physicians' emotions interact and spill over during a shared decision situation. Overall, our process model and specific example show how emotions can impact shared decision-making in oncology in a multitude of ways. With this paper, we want to raise awareness of the role of emotions in the shared decision-making process, as emotions are often not explicitly recognized as decision criteria. Increased awareness of emotions may help their optimal utilization and reduce their influence as a bias in shared decision-making.

show abstract

Section: Discussionmentioning

confidence: 99%

Emotions as Social Information in Shared Decision-Making in Oncology

Treffers

Putora

2020

Oncology

View full text Add to dashboard Cite

show abstract

“…Therefore, more advanced data analytics will be deployed and the demand to integrate accuracy and interpretability will rise to cope with clinical practice needs in the field. 74 Although different techniques are associated with distinct inherent limitations for radiation outcomes prediction, which include the independence assumption for features in logistic regression, the robustness in decision trees, the need for feature discretization in Bayesian networks, or the network configuration dependency in DL, our review shows that combining predictions among a handful of good, but different, IP and NIP models may result in better ML approaches to achieve higher accuracy and interpretability for radiation outcomes prediction.…”

Section: Discussionmentioning

confidence: 99%

Balancing accuracy and interpretability of machine learning approaches for radiation treatment outcomes modeling

Luo

Tseng

Cui³

et al. 2019

BJR|Open

Self Cite

View full text Add to dashboard Cite

Radiation outcomes prediction (ROP) plays an important role in personalized prescription and adaptive radiotherapy. A clinical decision may not only depend on an accurate radiation outcomes’ prediction, but also needs to be made based on an informed understanding of the relationship among patients’ characteristics, radiation response and treatment plans. As more patients’ biophysical information become available, machine learning (ML) techniques will have a great potential for improving ROP. Creating explainable ML methods is an ultimate task for clinical practice but remains a challenging one. Towards complete explainability, the interpretability of ML approaches needs to be first explored. Hence, this review focuses on the application of ML techniques for clinical adoption in radiation oncology by balancing accuracy with interpretability of the predictive model of interest. An ML algorithm can be generally classified into an interpretable (IP) or non-interpretable (NIP) (“black box”) technique. While the former may provide a clearer explanation to aid clinical decision-making, its prediction performance is generally outperformed by the latter. Therefore, great efforts and resources have been dedicated towards balancing the accuracy and the interpretability of ML approaches in ROP, but more still needs to be done. In this review, current progress to increase the accuracy for IP ML approaches is introduced, and major trends to improve the interpretability and alleviate the “black box” stigma of ML in radiation outcomes modeling are summarized. Efforts to integrate IP and NIP ML approaches to produce predictive models with higher accuracy and interpretability for ROP are also discussed.

show abstract

“…Artificial intelligence and decision support systems are being increasingly used to facilitate medical decisionmaking [14][15][16]; these systems, however, are trained on data sets that omit insular criteria. These omissions may result in significant biases and discrepancies when the treatment recommendations are associated with existing data sources and collide with the real-world, that is institutional conditions like the unavailability of certain treatment modalities.…”

Section: Discussionmentioning

confidence: 99%

Insular Decision Criteria in Clinical Practice: Analysis of Decision-Making in Oncology

et al. 2020

View full text Add to dashboard Cite

Background: Medical decision-making is complex and involves a variety of decision criteria, many of which are universally recognised. However, decision-making analyses have demonstrated that certain decision criteria are not used uniformly among clinicians. Aim: We describe decision criteria, which for various contexts are only used by a minority of decision makers. For these, we introduce and define the term "insular criteria". Methods: 19 studies analysing clinical decision-making based on decision trees were included in our study. All studies were screened for decisionmaking criteria that were mentioned by less than three local decision makers in studies involving 8-26 participants. Results: 14 out of the 19 included studies reported insular criteria. We identified 42 individual insular criteria. They could be intuitively allocated to seven major groups, these were: comorbidities, treatment, patients' characteristics/preferences, caretaker, scores, laboratory and tumour properties/ staging. Conclusion: Insular criteria are commonly used in clinical decision-making, yet, the individual decision makers may not be aware of them. With this analysis, we demonstrate the existence of insular criteria and their variety. In daily practice and clinical studies, awareness of insular criteria is important.

show abstract

Prospects and Challenges for Clinical Decision Support in the Era of Big Data

Cited by 29 publications

References 96 publications

Emotions as Social Information in Shared Decision-Making in Oncology

Emotions as Social Information in Shared Decision-Making in Oncology

Balancing accuracy and interpretability of machine learning approaches for radiation treatment outcomes modeling

Insular Decision Criteria in Clinical Practice: Analysis of Decision-Making in Oncology

Contact Info

Product

Resources

About