The Bayesian Approach to Decision Making and Analysis in Nutrition Research and Practice

Enhancing artificial intelligence-doctor collaboration for computer-aided diagnosis in colonoscopy through improved digital literacy

Establishing appropriate trust and maintaining a balanced reliance on digital resources are vital for accurate optical diagnoses and effective integration of computer-aided diagnosis (CADx) in colonoscopy. Active learning using diverse polyp image datasets can help in developing precise CADx systems. Enhancing doctors' digital literacy and interpreting their results is crucial. Explainable artificial intelligence (AI) addresses opacity, and textual descriptions, along with AI-generated content, deepen the interpretability of AI-based findings by doctors. AI conveying uncertainties and decision confidence aids doctors' acceptance of results. Optimal AI-doctor collaboration requires improving algorithm performance, transparency, addressing uncertainties, and enhancing doctors' optical diagnostic skills.

Bayesian Interpretation of Essential Tremor Plus

Essential tremor (ET) plus is a new tremor classification that was introduced in 2018 by a task force of the International Parkinson and Movement Disorder Society. Patients with ET plus meet the criteria for ET but have one or more additional systemic or neurologic signs of uncertain significance or relevance to tremor (“soft signs”). Soft signs are not sufficient to diagnose another tremor syndrome or movement disorder, and soft signs in ET plus are known to have poor interrater reliability and low diagnostic sensitivity and specificity. Therefore, the clinical significance of ET plus must be interpreted probabilistically when judging whether a patient is more likely to have ET or a combined tremor syndrome, such as dystonic tremor. Such a probabilistic interpretation is possible with Bayesian analysis. This review presents a Bayesian analysis of ET plus in patients suspected of having ET versus a dystonic tremor syndrome, which is the most common differential diagnosis in patients referred for ET. Bayesian analysis of soft signs provides an estimate of the probability that a patient with possible ET is more likely to have an alternative diagnosis. ET plus is a distinct tremor classification and should not be viewed as a subtype of ET. ET plus covers a more-comprehensive phenotyping of people with possible ET, and the clinical interpretation of ET plus is enhanced with Bayesian analysis of associated soft signs.

Pointers and Pitfalls in Interpreting Nutrition and Dietetics Research: The Importance of Statistical and Clinical Significance

This monograph focuses on understanding statistical and clinical significance and is one of a research and statistics series published by the statistical team of the Journal of the Academy of Nutrition and Dietetics. The content covers the research questions, the definition of clinical significance, hypothesis testing, p-values, effect sizes, sample sizes, confidence intervals, power analyses, minimal clinically important differences, and validity. This monograph concludes with a summary of the importance of clinical and statistical results, for nutrition professionals to consider when assessing statistical and clinical significance. The assessment will help readers make subjective clinical judgements in the application of research findings based on their experience.

Commentary: on the effects of health expenditure on infant mortality in sub-Saharan Africa: evidence from panel data analysis

BACKGROUND

This commentary assesses critically the published article in the Health Economics Review. 2020; 10 (1), 1-9. It explains the effects of health expenditure on infant mortality in sub-Saharan Africa using a panel data analysis (i.e. random effects) over the year 2000-2015 extracted from the World Bank Development Indicators. The paper is well written and deserve careful attention.

MAIN TEXT

The main reasons for inaccurate estimates observed in this paper are due to endogeneity issue with random effects panel estimators. It occurs when two or more variables simultaneously affect/cause each other. In this paper, the presence of endogeneity bias (i.e. education, health, health care expenditures and real GDP per capita variables) and its omitted variable bias leads to inaccurate estimates and conclusion. Random effects model require strict exogeneity of regressors. Moreover, frequentist/classic estimation (i.e. random effects) relies on sampling size and likelihood of the data in a specified model without considering other kinds of uncertainty.

CONCLUSION

This comment argues future studies on health expenditures versus health outcomes (i.e. infant, under-five and neonates mortality) to use either dynamic panel (i.e. system Generalized Method of Moments, GMM) to control endogeneity issues among health (infant or neonates mortality), GDP per capita, education and health expenditures variables or adopting Bayesian framework to adjust uncertainty (i.e. confounding, measurement errors and endogeneity of variables) within a range of probability distribution.

Recapitulating the Bayesian framework for neurosurgical outpatient care and a cost-benefit analysis of telemedicine for socioeconomically disadvantaged patients in the Philippines during the pandemic

OBJECTIVE

In the Philippines during recent months, a neurosurgical center that caters primarily to socioeconomically disadvantaged patients has encountered unprecedented changes in practice patterns brought about by the COVID-19 pandemic. In particular, the usual task of outpatient care has shifted to the telemedicine format, bringing along all of its attendant advantages and gargantuan challenges. The authors sought to determine the responsiveness of this telemedicine setup to the needs of their disadvantaged patients and explored the application of Bayesian inference to enhance the use of teleconsultation in daily clinical decision-making.

METHODS

The authors used the following methods to assess the telemedicine setup used in a low-resource setting during the pandemic: 1) a cross-sectional survey of patients who participated in a medical consultation via telemedicine during the 16-week period from March 16, 2020, to July 15, 2020; 2) a cost-benefit analysis of the use of telemedicine by patients; and 3) a case illustration of a Bayesian approach application unique to the teleconsultation scenario.

RESULTS

Of the 272 patient beneficiaries of telemedicine in a 16-week period, 57 responded to the survey. The survey responses regarding neurosurgical outpatient care through telemedicine yielded high ratings of utility for the patients and their caregivers. According to 64% of respondents, the affordability of the telemedicine setup also prevented them from borrowing money from others, among other adverse life events prevented. There were realized financial gains on the part of the patients in terms of cost savings and protection from further impoverishment. The benefit-cost ratio was 3.51 for the patients, signifying that the benefits outweighed the costs. An actual teleconsultation case vignette was reported that is meant to be instructive and contributory to the preparedness of the neurosurgeon on the provider end of the service delivery.

CONCLUSIONS

Telemedicine holds promise as a viable and safe method for health service delivery during the pandemic. In the setting of a health system that is continually challenged by shortages of resources, this study shows that an effective telemedicine setup can come with high benefit-cost ratios and quality of care, along with the assurance of patient satisfaction. The potential for high-quality care can be enhanced by the inclusion of the Bayesian framework to the basic toolkit of remote clinical assessment. When confronted with choices in terms of differential diagnosis and tests, the rigor of a simple application of the Bayesian framework can minimize costs arising from uncertainties.