Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Jan 12;14(1):1181.
doi: 10.1038/s41598-024-51268-4.

Entropy removal of medical diagnostics

Shuhan He #  1 , Paul Chong #  2 , Byung-Jun Yoon  3   4 , Pei-Hung Chung  3 , David Chen  5 , Sammer Marzouk  6 , Kameron C Black  7 , Wilson Sharp  2 , Pedram Safari  8 , Joshua N Goldstein  9 , Ali S Raja  9 , Jarone Lee  9
Affiliations

Entropy removal of medical diagnostics

Shuhan He et al. Sci Rep. .

Abstract

Shannon entropy is a core concept in machine learning and information theory, particularly in decision tree modeling. To date, no studies have extensively and quantitatively applied Shannon entropy in a systematic way to quantify the entropy of clinical situations using diagnostic variables (true and false positives and negatives, respectively). Decision tree representations of medical decision-making tools can be generated using diagnostic variables found in literature and entropy removal can be calculated for these tools. This concept of clinical entropy removal has significant potential for further use to bring forth healthcare innovation, such as quantifying the impact of clinical guidelines and value of care and applications to Emergency Medicine scenarios where diagnostic accuracy in a limited time window is paramount. This analysis was done for 623 diagnostic tools and provided unique insights into their utility. For studies that provided detailed data on medical decision-making algorithms, bootstrapped datasets were generated from source data to perform comprehensive machine learning analysis on these algorithms and their constituent steps, which revealed a novel and thorough evaluation of medical diagnostic algorithms.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

Figure 1
Figure 1
Decision tree representation of 2 × 2 diagnostic table. Diagnostic variables (TP/FP/FN/TN) are utilized to represent a 2 × 2 table and its corresponding medical decision-making tool as a decision tree for entropy analysis.
Figure 2
Figure 2
Scatterplot of removed entropy and tool sensitivity and specificity. 623 medical decision-making tools were analyzed. (A) Sensitivity exhibits a 0.46 Pearson correlation and 0.55 Spearman correlation with entropy removal (p < .001). (B) Specificity exhibits a 0.61 Pearson correlation and 0.74 Spearman correlation with entropy removal (p < .001).
Figure 3
Figure 3
Scatterplot of removed entropy and tool positive predictive value and negative predictive value. 623 medical decision-making tools were analyzed. (A) Positive predictive value exhibits a 0.60 Pearson correlation and 0.71 Spearman correlation with entropy removal (p < .001). (B) Negative predictive value exhibits a 0.41 Pearson correlation and 0.46 Spearman correlation with entropy removal (p < .001).
See this image and copyright information in PMC

References

    1. Guyatt G, et al. Evidence-based medicine: A new approach to teaching the practice of medicine. JAMA. 1992;268:2420–2425. doi: 10.1001/jama.1992.03490170092032. - DOI - PubMed
    1. Kohn KT, Corrigan JM, Donaldson MS. To Err Is Human: Building a Safer Health System. National Academy Press; 1999. - PubMed
    1. “AHRQ National Scorecard on Hospital-Acquired Conditions Updated Baseline Rates and Preliminary Results 2014–2017” (Agency for Healthcare Research and Quality, 2019).
    1. Newman TB, Kohn MA. Evidence-Based Diagnosis: An Introduction to Clinical Epidemiology. Cambridge University Press; 2020.
    1. Bartol T. Thoughtful use of diagnostic testing: Making practical sense of sensitivity, specificity, and predictive value. Nurse Practit. 2015;40:10–12. - PubMed