Dataset Information

Development and validation of a 1-year survival prognosis estimation model for Amyotrophic Lateral Sclerosis using manifold learning algorithm UMAP.

ABSTRACT: Amyotrophic Lateral Sclerosis (ALS) is an inexorably progressive neurodegenerative condition with no effective disease modifying therapies. The development and validation of reliable prognostic models is a recognised research priority. We present a prognostic model for survival in ALS where result uncertainty is taken into account. Patient data were reduced and projected onto a 2D space using Uniform Manifold Approximation and Projection (UMAP), a novel non-linear dimension reduction technique. Information from 5,220 patients was included as development data originating from past clinical trials, and real-world population data as validation data. Predictors included age, gender, region of onset, symptom duration, weight at baseline, functional impairment, and estimated rate of functional loss. UMAP projection of patients shows an informative 2D data distribution. As limited data availability precluded complex model designs, the projection was divided into three zones with relevant survival rates. These rates were defined using confidence bounds: high, intermediate, and low 1-year survival rates at respectively [Formula: see text] ([Formula: see text]), [Formula: see text] ([Formula: see text]) and [Formula: see text] ([Formula: see text]). Predicted 1-year survival was estimated using zone membership. This approach requires a limited set of features, is easily updated, improves with additional patient data, and accounts for results uncertainty.

SUBMITTER: Grollemund V

PROVIDER: S-EPMC7414917 | biostudies-literature | 2020 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Development and validation of a 1-year survival prognosis estimation model for Amyotrophic Lateral Sclerosis using manifold learning algorithm UMAP.

Grollemund Vincent V Chat Gaétan Le GL Secchi-Buhour Marie-Sonia MS Delbot François F Pradat-Peyre Jean-François JF Bede Peter P Pradat Pierre-François PF

Scientific reports 20200807 1

Amyotrophic Lateral Sclerosis (ALS) is an inexorably progressive neurodegenerative condition with no effective disease modifying therapies. The development and validation of reliable prognostic models is a recognised research priority. We present a prognostic model for survival in ALS where result uncertainty is taken into account. Patient data were reduced and projected onto a 2D space using Uniform Manifold Approximation and Projection (UMAP), a novel non-linear dimension reduction technique. ...[more]

PMID: 32770027

Similar Datasets

Project description:BackgroundPersonalized ENCALS survival prediction model reliably estimates the personalized prognosis of patients with amyotrophic lateral sclerosis. Concerns were raised on discussing personalized prognosis without causing anxiety and destroying hope. Tailoring communication to patient readiness and patient needs mediates the impact of prognostic disclosure. We developed a communication guide to support physicians in discussing personalized prognosis tailored to individual needs and preferences of people with ALS and their families.MethodsA multidisciplinary working group of neurologists, rehabilitation physicians, and healthcare researchers A) identified relevant topics for guidance, B) conducted a systematic review on needs of patients regarding prognostic discussion in life-limiting disease, C) drafted recommendations based on evidence and expert opinion, and refined and finalized these recommendations in consensus rounds, based on feedback of an expert advisory panel (patients, family member, ethicist, and spiritual counsellor).ResultsA) Topics identified for guidance were 1) filling in the ENCALS survival model, and interpreting outcomes and uncertainty, and 2) tailoring discussion to individual needs and preferences of patients (information needs, role and needs of family, severe cognitive impairment or frontotemporal dementia, and non-western patients). B) 17 studies were included in the systematic review. C) Consensus procedures on drafted recommendations focused on selection of outcomes, uncertainty about estimated survival, culturally sensitive communication, and lack of decisional capacity. Recommendations for discussing the prognosis include the following: discuss prognosis based on the prognostic groups and their median survival, or, if more precise information is desired, on the interquartile range of the survival probability. Investigate needs and preferences of the patients and their families for prognostic disclosure, regardless of cultural background. If the patient does not want to know their prognosis, with patient permission discuss the prognosis with their family. If the patient is judged to lack decisional capacity, ask the family if they want to discuss the prognosis. Tailor prognostic disclosure step by step, discuss it in terms of time range, and emphasize uncertainty of individual survival time.ConclusionThis communication guide supports physicians in tailoring discussion of personalized prognosis to the individual needs and preferences of people with ALS and their families.

Dataset Information

Development and validation of a 1-year survival prognosis estimation model for Amyotrophic Lateral Sclerosis using manifold learning algorithm UMAP.

Publications

Development and validation of a 1-year survival prognosis estimation model for Amyotrophic Lateral Sclerosis using manifold learning algorithm UMAP.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets