A Machine Learning-based Estimated Survival Model

Malignant tumors are the leading cause of death in elderly patients, and palliative care can improve the quality of life for elderly advanced cancer patients. One of the main reasons why these patients are not included in palliative care is the lack of accurate estimation of their survival period by patients, family members, and doctors. Both doctors and patients tend to be overly optimistic about the survival period of elderly advanced cancer patients, leading to overtreatment. Therefore, assessing the risk of death for these patients and further establishing a survival period estimation model can improve the accuracy of doctors' clinical predictions of patient survival, facilitate early referral to palliative care, and promote rationalization of medical decision-making.

Active, Not Recruiting

This study is active but is not currently recruiting participants.

Notify Me

Key information

Conditions

Advanced Solid Tumor

Age range

60 year and older

Sex eligibility

All sexes

Study type

Observational

Primary location

Siyao Zhao

Chengdu, Sichuan, 610041, China

About this study

By searching the literature, conducting systematic reviews, and meta-analyses, we aim to uncover the prognostic factors related to death in elderly advanced cancer patients.
Based on evidence-based data and considering the clinical conditions of elderly advanced cancer patients in China, we will establish relevant entries for a risk assessment scale for death in elderly advanced cancer patients. By using the Delphi expert consultation evaluation method, we will finalize the assessment scale framework, laying the theoretical foundation for the establishment and validation of a death risk prediction model for elderly advanced cancer patients in China.
Develop a survival estimation model for elderly advanced cancer patients; through metabolomics studies and other research methods, we will investigate metabolic biomarkers related to predicting the survival period of elderly advanced cancer patients.

Who can participate

Healthy volunteers accepted: No

Only the study team can determine whether someone qualifies for participation.

Inclusion criteria

Inclusion criteria for late-stage malignant tumor patients: Must meet Condition 1) and also meet either Condition 2), 3), or 4):

Clinical diagnosis of advanced malignant tumor: TNM stage III or IV
"Surprise question": If this patient were to die within the next 6 months, it would not be surprising to you.
Karnofsky performance status (KPS) score ≤ 50
Palliative Performance Scale (PPS) ≤ 50%

Exclusion criteria

Patients who refuse to participate in the study;
Patients who, for various reasons, are unable to cooperate and complete the questionnaire survey;
Patients who, for various reasons, are unable to cooperate and complete the follow-up.

Treatment and study plan

Primary outcomes

A model

Time frame: 2026-12-31

Build a survival estimation model for elderly late-stage cancer patients.

Sponsors and collaborators

Lead sponsor

Zhao Siyao

Other

Registry information

Official study title

Construction and Validation of a Machine Learning-based Estimated Survival Model for Elderly Patients With Advanced Malignancy

Important dates

Study start: 2024
Primary completion: 2025
Study completion: 2026
First posted: May 29, 2024
Registry last updated: May 29, 2024

OpenTrials presents study information sourced from ClinicalTrials.gov. The official registry record should be consulted for the latest information.

View the official ClinicalTrials.gov record (opens in a new tab)

This listing is for discovery and informational purposes only. It is not medical advice, does not guarantee that a study is recruiting, and does not determine eligibility. Contact the study team and a qualified healthcare professional when considering participation.

Published trials that share one or more normalized conditions with this study.

Active, Not Recruiting