scholarly journals Deep-Learning Approach to Predict Survival Outcomes Using Wearable Actigraphy Device Among End-Stage Cancer Patients

2021 ◽  
Vol 9 ◽  
Author(s):  
Tien Yun Yang ◽  
Pin-Yu Kuo ◽  
Yaoru Huang ◽  
Hsiao-Wei Lin ◽  
Shwetambara Malwade ◽  
...  
Keyword(s):  
Deep Learning ◽  
Prediction Model ◽  
End Of Life ◽  
Cancer Patients ◽  
Performance Status ◽  
Hospital Death ◽  
Survival Prediction ◽  
Model Based ◽  
Prognostic Accuracy ◽  
End Stage

Survival prediction is highly valued in end-of-life care clinical practice, and patient performance status evaluation stands as a predominant component in survival prognostication. While current performance status evaluation tools are limited to their subjective nature, the advent of wearable technology enables continual recordings of patients' activity and has the potential to measure performance status objectively. We hypothesize that wristband actigraphy monitoring devices can predict in-hospital death of end-stage cancer patients during the time of their hospital admissions. The objective of this study was to train and validate a long short-term memory (LSTM) deep-learning prediction model based on activity data of wearable actigraphy devices. The study recruited 60 end-stage cancer patients in a hospice care unit, with 28 deaths and 32 discharged in stable condition at the end of their hospital stay. The standard Karnofsky Performance Status score had an overall prognostic accuracy of 0.83. The LSTM prediction model based on patients' continual actigraphy monitoring had an overall prognostic accuracy of 0.83. Furthermore, the model performance improved with longer input data length up to 48 h. In conclusion, our research suggests the potential feasibility of wristband actigraphy to predict end-of-life admission outcomes in palliative care for end-stage cancer patients.Clinical Trial Registration: The study protocol was registered on ClinicalTrials.gov (ID: NCT04883879).

scholarly journals Disparities in access to palliative care facilities for patients with and without cancer: A retrospective review

2021 ◽  
pp. 026921632110073
Author(s):  
Christine Lau ◽  
Christopher Meaney ◽  
Matthew Morgan ◽  
Rose Cook ◽  
Camilla Zimmermann ◽  
...  
Keyword(s):  
Palliative Care ◽  
End Of Life ◽  
Cancer Patients ◽  
Performance Status ◽  
Retrospective Chart Review ◽  
Care Needs ◽  
Care Facilities ◽  
Palliative Care Services ◽  
Low Performance ◽  
Electronic Referral

Background: To date, little is known about the characteristics of patients who are admitted to a palliative care bed for end-of-life care. Previous data suggest that there are disparities in access to palliative care services based on age, sex, diagnosis, and socioeconomic status, but it is unclear whether these differences impact access to a palliative care bed. Aim: To better identify patient factors associated with the likelihood/rate of admission to a palliative care bed. Design: A retrospective chart review of all initiated palliative care bed applications through an electronic referral program was conducted over a 24-month period. Setting/participants: Patients who apply and are admitted to a palliative care bed in a Canadian metropolitan city. Results: A total of 2743 patients made a total of 5202 bed applications to 9 hospice/palliative care units in 2015–2016. Referred and admitted cancer patients were younger, male, and more functional than compared to non-cancer patients (all p < 0.001). Referred and admitted patients without cancer were more advanced in their illness trajectory, with an anticipated prognosis <1 month and Palliative Performance Status of 10%–20% (all p < 0.001). On multivariate analysis, a diagnosis of cancer and a prognosis of <3 months were associated with increased likelihood and/or rate of admission to a bed, whereas the presence of care needs, a longer prognosis and a PPS of 30%–40% were associated with decreased rates and/or likelihood of admission. Conclusion: Patients without cancer have reduced access to palliative care facilities at end-of-life compared to patients with cancer; at the time of their application and admission, they are “sicker” with very low performance status and poorer prognoses. Further studies investigating disease-specific clinical variables and support requirements may provide more insights into these observed disparities.

scholarly journals Model-based optimization of subgroup weights for survival analysis

2019 ◽  
Vol 35 (14) ◽  
pp. i484-i491
Author(s):  
Jakob Richter ◽  
Katrin Madjar ◽  
Jörg Rahnenführer
Keyword(s):  
Survival Analysis ◽  
Prediction Model ◽  
Model Building ◽  
Prediction Models ◽  
Survival Prediction ◽  
Good Prediction ◽  
Similar Data ◽  
Weighted Likelihood ◽  
Model Based ◽  
Specific Subgroup

AbstractMotivationTo obtain a reliable prediction model for a specific cancer subgroup or cohort is often difficult due to limited sample size and, in survival analysis, due to potentially high censoring rates. Sometimes similar data from other patient subgroups are available, e.g. from other clinical centers. Simple pooling of all subgroups can decrease the variance of the predicted parameters of the prediction models, but also increase the bias due to heterogeneity between the cohorts. A promising compromise is to identify those subgroups with a similar relationship between covariates and target variable and then include only these for model building.ResultsWe propose a subgroup-based weighted likelihood approach for survival prediction with high-dimensional genetic covariates. When predicting survival for a specific subgroup, for every other subgroup an individual weight determines the strength with which its observations enter into model building. MBO (model-based optimization) can be used to quickly find a good prediction model in the presence of a large number of hyperparameters. We use MBO to identify the best model for survival prediction of a specific subgroup by optimizing the weights for additional subgroups for a Cox model. The approach is evaluated on a set of lung cancer cohorts with gene expression measurements. The resulting models have competitive prediction quality, and they reflect the similarity of the corresponding cancer subgroups, with both weights close to 0 and close to 1 and medium weights.Availability and implementationmlrMBO is implemented as an R-package and is freely available at http://github.com/mlr-org/mlrMBO.

Sign in / Sign up

Export Citation Format

Share Document