Psychosocial profiles and their predictors in epilepsy using patient‐reported outcomes and machine learning

Epilepsia ◽  
2020 ◽  
Vol 61 (6) ◽  
pp. 1201-1210 ◽  
Author(s):  
Colin B. Josephson ◽  
Jordan D. T. Engbers ◽  
Meng Wang ◽  
Kevin Perera ◽  
Pamela Roach ◽  
...  
Keyword(s):  
Machine Learning ◽  
Patient Reported Outcomes ◽  
Patient Reported ◽  
Psychosocial Profiles

scholarly journals Electronic patient-reported outcomes and machine learning in predicting immune-related adverse events of immune checkpoint inhibitor therapies

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Sanna Iivanainen ◽  
Jussi Ekstrom ◽  
Henri Virtanen ◽  
Vesa V. Kataja ◽  
Jussi P. Koivunen
Keyword(s):  
Machine Learning ◽  
Early Detection ◽  
Adverse Events ◽  
Cancer Patients ◽  
Immune Checkpoint ◽  
Patient Reported Outcomes ◽  
Prediction Models ◽  
Accuracy Score ◽  
Patient Reported ◽  
Auc Value

Abstract Background Immune-checkpoint inhibitors (ICIs) have introduced novel immune-related adverse events (irAEs), arising from various organ systems without strong timely dependency on therapy dosing. Early detection of irAEs could result in improved toxicity profile and quality of life. Symptom data collected by electronic (e) patient-reported outcomes (PRO) could be used as an input for machine learning (ML) based prediction models for the early detection of irAEs. Methods The utilized dataset consisted of two data sources. The first dataset consisted of 820 completed symptom questionnaires from 34 ICI treated advanced cancer patients, including 18 monitored symptoms collected using the Kaiku Health digital platform. The second dataset included prospectively collected irAE data, Common Terminology Criteria for Adverse Events (CTCAE) class, and the severity of 26 irAEs. The ML models were built using extreme gradient boosting algorithms. The first model was trained to detect the presence and the second the onset of irAEs. Results The model trained to predict the presence of irAEs had an excellent performance based on four metrics: accuracy score 0.97, Area Under the Curve (AUC) value 0.99, F1-score 0.94 and Matthew’s correlation coefficient (MCC) 0.92. The prediction of the irAE onset was more difficult with accuracy score 0.96, AUC value 0.93, F1-score 0.66 and MCC 0.64 but the model performance was still at a good level. Conclusion The current study suggests that ML based prediction models, using ePRO data as an input, can predict the presence and onset of irAEs with a high accuracy, indicating that ePRO follow-up with ML algorithms could facilitate the detection of irAEs in ICI-treated cancer patients. The results should be validated with a larger dataset. Trial registration Clinical Trials Register (NCT3928938), registration date the 26th of April, 2019

Augmenting machine learning algorithms to predict mortality using patient-reported outcomes in oncology.

2021 ◽  
Vol 39 (15_suppl) ◽  
pp. 1510-1510
Author(s):  
Ravi Bharat Parikh ◽  
Jill Schnall ◽  
Manqing Liu ◽  
Peter Edward Gabriel ◽  
Corey Chivers ◽  
...  
Keyword(s):  
Quality Of Life ◽  
Machine Learning ◽  
Mortality Risk ◽  
Patient Reported Outcomes ◽  
Machine Learning Algorithms ◽  
Measurement Information ◽  
Patients With Cancer ◽  
Patient Reported ◽  
Mortality Table

1510 Background: Machine learning (ML) algorithms based on electronic health record (EHR) data have been shown to accurately predict mortality risk among patients with cancer, with areas under the curve (AUC) generally greater than 0.80. While patient-reported outcomes (PROs) may also predict mortality among patients with cancer, it is unclear whether routinely-collected PROs improve the predictive performance of EHR-based ML algorithms. Methods: This cohort study included 8600 patients with cancer who had an outpatient encounter at one of 18 medical oncology practices in a large academic health system between July 1st, 2019 and January 1st, 2020. 4692 (54.9%) patients completed assessments of symptoms, performance status, and quality of life from the PRO version of the Common Terminology Criteria for Adverse Events and the Patient-Reported Outcomes Measurement Information System Global v.1.2 scales. We hypothesized that ML models predicting 180-day all-cause mortality based on EHR + PRO data would improve AUC compared to ML models based on EHR data alone. We assessed univariate and adjusted associations between each PRO and 180-day mortality. To train the EHR-only model, we fit a Least Absolute Shrinkage and Selection Operator (LASSO) regression using 192 EHR demographic, comorbidity, and laboratory variables. To train the EHR + PRO model, we used a two-phase approach to fit a model using EHR data for all patients and PRO data for those who completed assessments. To test our hypothesis, we compared the bootstrapped AUC, area under the precision-recall curve (AUPRC), and sensitivity at a 20% risk threshold for both models. Results: 464 (5.4%) patients died within 180 days of the encounter. Decreased quality of life, functional status, and appetite were associated with greater 180-day mortality (Table). Compared to the EHR-only model, the EHR + PRO model significantly improved AUC (0.86 [95% CI 0.85-0.86] vs. 0.80 [95% CI 0.80-0.81]), AUPRC (0.40 [95% CI 0.37-0.42] vs. 0.30 [95% CI 0.28-0.32]), and sensitivity (0.45 [95% CI 0.42-0.48] vs. 0.33 [95% CI 0.30-0.35]). Conclusions: Routinely collected PROs augment EHR-based ML mortality risk algorithms. ML algorithms based on EHR and PRO data may facilitate earlier supportive care for patients with cancer. Association of PROs with 180-day mortality.[Table: see text]

Towards data-driven decision-making for breast cancer patients undergoing mastectomy and reconstruction: Prediction of individual patient-reported outcomes at two-year follow-up using machine learning.

2020 ◽  
Vol 38 (15_suppl) ◽  
pp. 520-520 ◽  
Author(s):  
André Pfob ◽  
Babak Mehrara ◽  
Jonas Nelson ◽  
Edwin G. Wilkins ◽  
Andrea Pusic ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Machine Learning ◽  
Decision Making ◽  
Patient Reported Outcomes ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Data Driven ◽  
Group Level ◽  
Patient Reported

520 Background: Post-surgical satisfaction with breasts is a key outcome for women undergoing cancer-related mastectomy and reconstruction. Current decision making relies on group-level evidence, which may not offer optimal choice of treatment for individuals. We developed and validated machine learning algorithms to predict individual post-surgical breast-satisfaction. We aim to facilitate individualized data-driven decision making in breast cancer. Methods: We collected clinical, perioperative, and patient-reported data from 3058 women who underwent breast reconstruction due to breast cancer across 11 sites in North America. We trained and evaluated four algorithms (regularized regression, Support Vector Machine, Neural Network, Regression Tree) to predict significant changes in satisfaction with breasts at 2-year follow up using the validated BREAST-Q measure. Accuracy and area under the receiver operating characteristics curve (AUC) were used to determine algorithm performance in the test sample. Results: Machine learning algorithms were able to accurately predict changes in women’s satisfaction with breasts (see table). Baseline satisfaction with breasts was the most informative predictor of outcome, followed by radiation during or after reconstruction, nipple-sparing and mixed mastectomy, implant-based reconstruction, chemotherapy, unilateral mastectomy, lower psychological well-being, and obesity. Conclusions: We reveal the crucial role of patient-reported outcomes in determining post-operative outcomes and that Machine Learning algorithms are suitable to identify individuals who might benefit from alternative treatment decisions than suggested by group-level evidence. We provide a web-based tool for individuals considering mastectomy and reconstruction. importdemo.com . Clinical trial information: NCT01723423 . [Table: see text]

scholarly journals Comparison of Conventional Statistical Methods with Machine Learning in Medicine: Diagnosis, Drug Development, and Treatment

Medicina ◽  
2020 ◽  
Vol 56 (9) ◽  
pp. 455
Author(s):  
Hema Sekhar Reddy Rajula ◽  
Giuseppe Verlato ◽  
Mirko Manchia ◽  
Nadia Antonucci ◽  
Vassilios Fanos
Keyword(s):  
Machine Learning ◽  
Drug Development ◽  
Statistical Methods ◽  
Patient Reported Outcomes ◽  
A Priori ◽  
Response To Treatment ◽  
Patient Reported ◽  
Need To Evaluate ◽  
Diagnosis And Classification ◽  
Treatment Integration

Futurists have anticipated that novel autonomous technologies, embedded with machine learning (ML), will substantially influence healthcare. ML is focused on making predictions as accurate as possible, while traditional statistical models are aimed at inferring relationships between variables. The benefits of ML comprise flexibility and scalability compared with conventional statistical approaches, which makes it deployable for several tasks, such as diagnosis and classification, and survival predictions. However, much of ML-based analysis remains scattered, lacking a cohesive structure. There is a need to evaluate and compare the performance of well-developed conventional statistical methods and ML on patient outcomes, such as survival, response to treatment, and patient-reported outcomes (PROs). In this article, we compare the usefulness and limitations of traditional statistical methods and ML, when applied to the medical field. Traditional statistical methods seem to be more useful when the number of cases largely exceeds the number of variables under study and a priori knowledge on the topic under study is substantial such as in public health. ML could be more suited in highly innovative fields with a huge bulk of data, such as omics, radiodiagnostics, drug development, and personalized treatment. Integration of the two approaches should be preferred over a unidirectional choice of either approach.

Sign in / Sign up

Export Citation Format

Share Document