Dataset Information

A decision tree to improve identification of pathogenic mutations in clinical practice.

ABSTRACT: BACKGROUND:A variant of unknown significance (VUS) is a variant form of a gene that has been identified through genetic testing, but whose significance to the organism function is not known. An actual challenge in precision medicine is to precisely identify which detected mutations from a sequencing process have a suitable role in the treatment or diagnosis of a disease. The average accuracy of pathogenicity predictors is 85%. However, there is a significant discordance about the identification of mutational impact and pathogenicity among them. Therefore, manual verification is necessary for confirming the real effect of a mutation in its casuistic. METHODS:In this work, we use variables categorization and selection for building a decision tree model, and later we measure and compare its accuracy with four known mutation predictors and seventeen supervised machine-learning (ML) algorithms. RESULTS:The results showed that the proposed tree reached the highest precision among all tested variables: 91% for True Neutrals, 8% for False Neutrals, 9% for False Pathogenic, and 92% for True Pathogenic. CONCLUSIONS:The decision tree exceptionally demonstrated high classification precision with cancer data, producing consistently relevant forecasts for the sample tests with an accuracy close to the best ones achieved from supervised ML algorithms. Besides, the decision tree algorithm is easier to apply in clinical practice by non-IT experts. From the cancer research community perspective, this approach can be successfully applied as an alternative for the determination of potential pathogenicity of VOUS.

SUBMITTER: do Nascimento PM

PROVIDER: S-EPMC7063785 | biostudies-literature | 2020 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A decision tree to improve identification of pathogenic mutations in clinical practice.

do Nascimento Priscilla Machado PM Medeiros Inácio Gomes IG Falcão Raul Maia RM Stransky Beatriz B de Souza Jorge Estefano Santana JES

BMC medical informatics and decision making 20200310 1

<h4>Background</h4>A variant of unknown significance (VUS) is a variant form of a gene that has been identified through genetic testing, but whose significance to the organism function is not known. An actual challenge in precision medicine is to precisely identify which detected mutations from a sequencing process have a suitable role in the treatment or diagnosis of a disease. The average accuracy of pathogenicity predictors is 85%. However, there is a significant discordance about the identif ...[more]

PMID: 32151256

Similar Datasets

Project description:ObjectiveTo assess what is known about the relationship between patient experience measures and incentives designed to improve care, and to identify how public policy and medical practices can promote patient-valued outcomes in health systems with strong financial incentives.Data sources/study settingExisting literature (gray and peer-reviewed) on measuring patient experience and patient-reported outcomes, identified from Medline and Cochrane databases; evaluations of pay-for-performance programs in the United States, Europe, and the Commonwealth countries.Study design/data collectionWe analyzed (1) studies of pay-for-performance, to identify those including metrics for patient experience, and (2) studies of patient experience and of patient-reported outcomes to identify evidence of influence on clinical practice, whether through public reporting or private reporting to clinicians.Principal findingsFirst, we identify four forms of "patient-reported information" (PRI), each with distinctive roles shaping clinical practice: (1) patient-reported outcomes measuring self-assessed physical and mental well-being, (2) surveys of patient experience with clinicians and staff, (3) narrative accounts describing encounters with clinicians in patients' own words, and (4) complaints/grievances signaling patients' distress when treatment or outcomes fall short of expectations. Because these forms vary in crucial ways, each must be distinctively measured, deployed, and linked with financial incentives. Second, although the literature linking incentives to patients experience is limited, implementing pay-for-performance systems appears to threaten certain patient-valued aspects of health care. But incentives can be made compatible with the outcomes patients value if: (a) a sufficient portion of incentives is tied to patient-reported outcomes and experiences, (b) incentivized forms of PRI are complemented by other forms of patient feedback, and (c) health care organizations assist clinicians to interpret and respond to PRI. Finally, we identify roles for the public and private sectors in financing PRI and orchestrating an appropriate balance among its four forms.ConclusionsUnless public policies are attentive to patients' perspectives, stronger financial incentives for clinicians can threaten aspects of care that patients most value. Certain policy parameters are already clear, but additional research is required to clarify how best to collect patient narratives in varied settings, how to report narratives to consumers in conjunction with quantified metrics, and how to promote a "culture of learning" at the practice level that incorporates patient feedback.

Dataset Information

A decision tree to improve identification of pathogenic mutations in clinical practice.

Publications

A decision tree to improve identification of pathogenic mutations in clinical practice.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets