Dataset Information

Creating Prognostic Systems for Well-Differentiated Thyroid Cancer Using Machine Learning.

ABSTRACT: Updates to staging models are needed to reflect a greater understanding of tumor behavior and clinical outcomes for well-differentiated thyroid carcinomas. We used a machine learning algorithm and disease-specific survival data of differentiated thyroid carcinoma from the Surveillance, Epidemiology, and End Results Program of the National Cancer Institute to integrate clinical factors to improve prognostic accuracy. The concordance statistic (C-index) was used to cut dendrograms resulting from the learning process to generate prognostic groups. We created one computational prognostic model (7 prognostic groups with C-index = 0.8583) based on tumor size (T), regional lymph nodes (N), status of distant metastasis (M), and age to mirror the contemporary American Joint Committee on Cancer (AJCC) staging system (C-index = 0.8387). We showed that adding histologic type (papillary and follicular) improved the survival prediction of the model. We also showed that 55 is the best cutoff of age in the model, consistent with the changes from the most recent 8th edition staging manual from AJCC. The demonstrated approach has the potential to create prognostic systems permitting data driven and real time analysis that can aid decision-making in patient management and prognostication.

SUBMITTER: Yang CQ

PROVIDER: S-EPMC6517862 | biostudies-literature | 2019

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Creating Prognostic Systems for Well-Differentiated Thyroid Cancer Using Machine Learning.

Yang Charles Q CQ Gardiner Lauren L Wang Huan H Hueman Matthew T MT Chen Dechang D

Frontiers in endocrinology 20190508

Updates to staging models are needed to reflect a greater understanding of tumor behavior and clinical outcomes for well-differentiated thyroid carcinomas. We used a machine learning algorithm and disease-specific survival data of differentiated thyroid carcinoma from the Surveillance, Epidemiology, and End Results Program of the National Cancer Institute to integrate clinical factors to improve prognostic accuracy. The concordance statistic (C-index) was used to cut dendrograms resulting from t ...[more]

PMID: 31139148

Similar Datasets

Project description:BackgroundSurgical extent in the management of well-differentiated thyroid cancer (DTC) remains a recurrent subject of debate. This is especially relevant in low-risk DTC of 1-4 cm, which represent the majority of new thyroid cancer diagnoses. With trends towards treatment de-escalation and recent guidelines from the American Thyroid Association and British Thyroid Association endorsing hemithyroidectomy (HT) alone for low-risk DTC of 1-4 cm, we sought to systematically appraise the literature to examine recurrence rate outcomes after HT in this low-risk group.SummarySearching PubMed, Cochrane Library, and Ovid MEDLINE, we conducted a systematic review to assess the survival and recurrence rate data presented in all published studies that had a cohort of patients treated with HT for the treatment of DTC. Pooled 10-year survival and recurrence rates, odds ratios, and 95% confidence intervals were calculated for meta-analysis. We identified 31 studies (with a total of 228,746 patients (HT: 36,129, total thyroidectomy, TT: 192,617), which had published recurrence and/or survival data for patients having had HT for DTC. We discovered a pooled recurrence rate of 9.0% for HT, which is significantly higher than in previously published reports. Further, this rate is maintained when examining patients within low-risk cohorts established with recognised risk classifications. We also discovered that of those patients who develop recurrent disease, 48% recur outside the central neck.Key messagesOur study provides a comprehensive systematic review of evidence aimed primarily at defining the recurrence rate in DTC after HT, and more specifically within the low-risk subgroup. We describe pooled recurrence and 10-year survival rates from a larger, broader, and more contemporary patient population than has been previously reported. Our findings indicate that there is a small but significantly higher recurrence rate after HT than TT, but the evidence base is heterogenous and subject to confounding factors and would ultimately benefit from prospective randomised trials to overcome these deficiencies.

Dataset Information

Creating Prognostic Systems for Well-Differentiated Thyroid Cancer Using Machine Learning.

Publications

Creating Prognostic Systems for Well-Differentiated Thyroid Cancer Using Machine Learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets