Development of a Survival Prognostic Model for Non-small Cell Lung Cancer

Zhang, Yuehua; Lu, Yuquan; Lu, Hong; Zhou, Yue-Min

doi:10.3389/fonc.2020.00362

Cited by 17 publications

(13 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Due to the low 5-year survival rate of lung cancer patients, there is an urgent need for accurate survival analysis so that doctors can better diagnose and manage treatment for their patients. For this reason, survival analysis systems constructed with the Cox proportional hazards model (CPHM) as the backbone model have emerged [ 36 , 37 , 38 ]. In contrast, Huang et al [ 39 ] used the XGBoost machine learning algorithm to build a model to predict the 1-year survival rate of NSCLC with bone metastases.…”

Section: Related Workmentioning

confidence: 99%

A Convolutional Neural Network-Based Intelligent Medical System with Sensors for Assistive Diagnosis and Decision-Making in Non-Small Cell Lung Cancer

Zhan

Long

Gou

et al. 2021

Sensors

View full text Add to dashboard Cite

In many regions of the world, early diagnosis of non-small cell lung cancer (NSCLC) is a major challenge due to the large population and lack of medical resources, which is difficult toeffectively address via limited physician manpower alone. Therefore, we developed a convolutional neural network (CNN)-based assisted diagnosis and decision-making intelligent medical system with sensors. This system analyzes NSCLC patients’ medical records using sensors to assist staging a diagnosis and provides recommended treatment plans to physicians. To address the problem of unbalanced case samples across pathological stages, we used transfer learning and dynamic sampling techniques to reconstruct and iteratively train the model to improve the accuracy of the prediction system. In this paper, all data for training and testing the system were obtained from the medical records of 2,789,675 patients with NSCLC, which were recorded in three hospitals in China over a five-year period. When the number of case samples reached 8000, the system achieved an accuracy rate of 0.84, which is already close to that of the doctors (accuracy: 0.86). The experimental results proved that the system can quickly and accurately analyze patient data and provide decision information support for physicians.

show abstract

Section: Related Workmentioning

confidence: 99%

A Convolutional Neural Network-Based Intelligent Medical System with Sensors for Assistive Diagnosis and Decision-Making in Non-Small Cell Lung Cancer

Zhan

Long

Gou

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…A KPS score of 80–100 indicates having ability to perform normal activities and no special care needed. The cut‐off of 80 has been widely used in the literature to classify patients into good versus not so good groups (Singh et al., 2019; Zhang et al., 2020).…”

Section: The Studymentioning

confidence: 99%

Trajectory of smoking behaviour during the first 6 months after diagnosis of lung cancer: A study from Taiwan

Yang

Liu

Wang

et al. 2021

Journal of Advanced Nursing

View full text Add to dashboard Cite

Aims To identify different classes of change pattern/ trajectory of tobacco smoking behaviour after diagnosis of lung cancer using multi‐wave data and to explore factors associated with the class membership. Design This is a multi‐wave observational study. Methods Smoking behaviour data were collected at diagnosis and then every month for 6 months from 133 newly diagnosed people with lung cancer who had recently quit smoking or continued to smoke at diagnosis. These patients were recruited from three medical centres and data were collected from May 2014 to January 2017. Smoking behaviour was assessed based on patients’ self‐reports on whether they smoked during the last month (yes/no) for a total of seven times. Mixture latent Markov model and logistic regression were used to analyse data. Results Two latent classes of smoking trajectory were identified among recent quitters or current smokers of people with lung cancer, namely “perseverance for abstinence” and “indecisive for abstinence.” Patients who were younger age (OR = 0.95, p = 0.026), exposure to second‐hand smoke (OR = 3.35, p = 0.012) and lower self‐efficacy for not smoking (OR = 0.96, p = 0.011) were more likely to belong to the class of “indecisive for abstinence.” Conclusions Heterogeneous classes of smoking trajectory existed in newly diagnosed people with lung cancer. The risk factors associated with a less favourable smoking trajectory can be incorporated into tailored smoking‐cessation programs for patients newly diagnosed with lung cancer. Impact The dynamic trajectory of smoking behaviour had not been adequately explored among newly diagnosed people with lung cancer. Two classes of smoking trajectory and the predictors associated with the class membership were identified. These findings suggest that the diagnosis of cancer is a teachable moment for smoking cessation. Patients with younger age, lower self‐efficacy of not smoking and exposure to second‐hand smoke at home need special attention.

show abstract

“…In most studies, the proposed survival prediction models for patients with lung cancer are static prediction models [9][10][11]. Traditional static prediction models take available patient features at a fixed time, commonly the time of diagnosis or initiation of therapy.…”

Section: Introductionmentioning

confidence: 99%

Dynamic Prediction of Near-Term Overall Survival in Patients with Advanced NSCLC Based on Real-World Data

Wang

Kerrigan

Puri

et al. 2022

Cancers

View full text Add to dashboard Cite

Patients with terminal cancers commonly receive aggressive and sub-optimal treatment near the end of life, which may not be beneficial in terms of duration or quality of life. To improve end-of-life care, it is essential to develop methods that can accurately predict the short-term risk of death. However, most prediction models for patients with cancer are static in the sense that they only use patient features at a fixed time. We proposed a dynamic prediction model (DPM) that can incorporate time-dependent predictors. We apply this method to patients with advanced non-small-cell lung cancer from a real-world database. Inverse probability of censoring weighted AUC with bootstrap inference was used to compare predictions among models. We found that increasing ECOG performance status and decreasing albumin had negative prognostic associations with overall survival (OS). Moreover, the negative prognostic implications strengthened over the patient disease course. DPMs using both time-independent and time-dependent predictors substantially improved short-term prediction accuracy compared to Cox models using only predictors at a fixed time. The proposed model can be broadly applied for prediction based on longitudinal data, including an estimation of the dynamic effects of time-dependent features on OS and updating predictions at any follow-up time.

show abstract

Development of a Survival Prognostic Model for Non-small Cell Lung Cancer

Cited by 17 publications

References 33 publications

A Convolutional Neural Network-Based Intelligent Medical System with Sensors for Assistive Diagnosis and Decision-Making in Non-Small Cell Lung Cancer

A Convolutional Neural Network-Based Intelligent Medical System with Sensors for Assistive Diagnosis and Decision-Making in Non-Small Cell Lung Cancer

Trajectory of smoking behaviour during the first 6 months after diagnosis of lung cancer: A study from Taiwan

Dynamic Prediction of Near-Term Overall Survival in Patients with Advanced NSCLC Based on Real-World Data

Contact Info

Product

Resources

About