Extent of diagnostic agreement among medical referrals

Such, Monica Van; Lohr, Robert H.; Beckman, Thomas J.; Naessens, James M.

doi:10.1111/jep.12747

Cited by 61 publications

(36 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Risk categories are defined by the requirement that no more than 1% of positive cases be classified as low risk, and no more than 1% of negative cases be classified as high risk. recommendation for no further testing, while a positive call gives a recommendation for further testing by a more accurate (and costly) test (Simundic, 2017). This paper reported uncertainty at TRIPOD level 3 wherever possible.…”

Section: Machine Learning Algorithms For Crc Predictionmentioning

confidence: 84%

Robust Machine Learning for Colorectal Cancer Risk Prediction and Stratification

et al. 2020

View full text Add to dashboard Cite

While colorectal cancer (CRC) is third in prevalence and mortality among cancers in the United States, there is no effective method to screen the general public for CRC risk. In this study, to identify an effective mass screening method for CRC risk, we evaluated seven supervised machine learning algorithms: linear discriminant analysis, support vector machine, naive Bayes, decision tree, random forest, logistic regression, and artificial neural network. Models were trained and cross-tested with the National Health Interview Survey (NHIS) and the Prostate, Lung, Colorectal, Ovarian Cancer Screening (PLCO) datasets. Six imputation methods were used to handle missing data: mean, Gaussian, Lorentzian, one-hot encoding, Gaussian expectation-maximization, and listwise deletion. Among all of the model configurations and imputation method combinations, the artificial neural network with expectation-maximization imputation emerged as the best, having a concordance of 0.70 ± 0.02, sensitivity of 0.63 ± 0.06, and specificity of 0.82 ± 0.04. In stratifying CRC risk in the NHIS and PLCO datasets, only 2% of negative cases were misclassified as high risk and 6% of positive cases were misclassified as low risk. In modeling the CRC-free probability with Kaplan-Meier estimators, low-, medium-, and high CRC-risk groups have statistically-significant separation. Our results indicated that the trained artificial neural network can be used as an effective screening tool for early intervention and prevention of CRC in large populations.

show abstract

Section: Machine Learning Algorithms For Crc Predictionmentioning

confidence: 84%

Robust Machine Learning for Colorectal Cancer Risk Prediction and Stratification

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The most straightforward applications of our results are to begin employing continuous bounded response scales in safety-critical signal detection tasks and averaging individuals' estimates. For example, in-line with a recent report by Mayo clinic researchers underscoring the importance of second opinions in increasing the accuracy of medical diagnoses (Van Such, Lohr, Beckman, & Naessens, 2017), different radiologists can quickly scan through mammograms and continuous estimates from the individuals with the most decorrelated patterns can be combined offline. Importantly, our framework can be applied without requiring any communication between individuals and without requiring the delay between estimates that is necessary to obtain similar benefits from aggregating repeated estimates from the same individual (Corbett et al, 2011;Herzog & Hertwig, 2009;Vul & Pashler, 2008).…”

Section: Discussionmentioning

confidence: 95%

“It’s Not a Tumor”: A Framework for Capitalizing on Individual Diversity to Boost Target Detection

Corbett

Munneke

2018

Psychol Sci

View full text Add to dashboard Cite

Even experts routinely miss infrequent targets, such as weapons in baggage scans or tumors in mammograms, because the visual system is not equipped to notice the unusual. To date, limited progress has been made toward improving human factors that mediate such critical diagnostic tasks. Here, we present a novel framework for pairing individuals' estimates to increase target detection. Using a wisdom-of-crowds approach that capitalizes on the visual system's ability to efficiently combine information, we demonstrated how averaging two noninteracting individuals' continuous estimates of whether a briefly presented image contained a prespecified target can significantly boost detection across a range of tasks. Furthermore, we showed how pairing individuals' estimates to maximize decorrelated patterns of performance in one task can optimize performance on a separate task. These results make significant advances toward combating severe deficits in target detection using straightforward applications for maximizing performance within limited pools of observers.

show abstract

“…This may not be surprising, given recent data suggesting that final diagnoses differed from the referral diagnosis in 21% of subspecialist referrals; for most cases, diagnoses were unchanged or only more refined. 22 Given the mismatch between supply and demand for subspecialty services for low-income patients, 23,24 a collective intelligence approach could provide valuable diagnostic assistance for primary care clinicians in areas that struggle with human capital in health care and have higher rates of diagnostic error. 25 …”

Section: Discussionmentioning

confidence: 99%

Comparative Accuracy of Diagnosis by Collective Intelligence of Multiple Physicians vs Individual Physicians

et al. 2019

View full text Add to dashboard Cite

show abstract

Extent of diagnostic agreement among medical referrals

Cited by 61 publications

References 14 publications

Robust Machine Learning for Colorectal Cancer Risk Prediction and Stratification

Robust Machine Learning for Colorectal Cancer Risk Prediction and Stratification

“It’s Not a Tumor”: A Framework for Capitalizing on Individual Diversity to Boost Target Detection

Comparative Accuracy of Diagnosis by Collective Intelligence of Multiple Physicians vs Individual Physicians

Contact Info

Product

Resources

About