Different Machine Learning Approaches for Implementing Telehealth-Based Cancer Pain Management Strategies

Background: The most effective strategy for managing cancer pain remotely should be better defined. There is a need to identify those patients who require increased attention and calibrated follow-up programs. Methods: Machine learning (ML) models were developed using the data prospectively obtained...

Descripción completa

Detalles Bibliográficos
Autores principales: Cascella, Marco, Coluccia, Sergio, Monaco, Federica, Schiavo, Daniela, Nocerino, Davide, Grizzuti, Mariacinzia, Romano, Maria Cristina, Cuomo, Arturo
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9502863/
https://www.ncbi.nlm.nih.gov/pubmed/36143132
http://dx.doi.org/10.3390/jcm11185484
_version_ 1784795809855832064
author Cascella, Marco
Coluccia, Sergio
Monaco, Federica
Schiavo, Daniela
Nocerino, Davide
Grizzuti, Mariacinzia
Romano, Maria Cristina
Cuomo, Arturo
author_facet Cascella, Marco
Coluccia, Sergio
Monaco, Federica
Schiavo, Daniela
Nocerino, Davide
Grizzuti, Mariacinzia
Romano, Maria Cristina
Cuomo, Arturo
author_sort Cascella, Marco
collection PubMed
description Background: The most effective strategy for managing cancer pain remotely should be better defined. There is a need to identify those patients who require increased attention and calibrated follow-up programs. Methods: Machine learning (ML) models were developed using the data prospectively obtained from a single-center program of telemedicine-based cancer pain management. These models included random forest (RF), gradient boosting machine (GBM), artificial neural network (ANN), and the LASSO–RIDGE algorithm. Thirteen demographic, social, clinical, and therapeutic variables were adopted to define the conditions that can affect the number of teleconsultations. After ML validation, the risk analysis for more than one remote consultation was assessed in target individuals. Results: The data from 158 patients were collected. In the training set, the accuracy was about 95% and 98% for ANN and RF, respectively. Nevertheless, the best accuracy on the test set was obtained with RF (70%). The ML-based simulations showed that young age (<55 years), lung cancer, and occurrence of breakthrough cancer pain help to predict the number of remote consultations. Elderly patients (>75 years) with bone metastases may require more telemedicine-based clinical evaluations. Conclusion: ML-based analyses may enable clinicians to identify the best model for predicting the need for more remote consultations. It could be useful for calibrating care interventions and resource allocation.
format Online
Article
Text
id pubmed-9502863
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-95028632022-09-24 Different Machine Learning Approaches for Implementing Telehealth-Based Cancer Pain Management Strategies Cascella, Marco Coluccia, Sergio Monaco, Federica Schiavo, Daniela Nocerino, Davide Grizzuti, Mariacinzia Romano, Maria Cristina Cuomo, Arturo J Clin Med Article Background: The most effective strategy for managing cancer pain remotely should be better defined. There is a need to identify those patients who require increased attention and calibrated follow-up programs. Methods: Machine learning (ML) models were developed using the data prospectively obtained from a single-center program of telemedicine-based cancer pain management. These models included random forest (RF), gradient boosting machine (GBM), artificial neural network (ANN), and the LASSO–RIDGE algorithm. Thirteen demographic, social, clinical, and therapeutic variables were adopted to define the conditions that can affect the number of teleconsultations. After ML validation, the risk analysis for more than one remote consultation was assessed in target individuals. Results: The data from 158 patients were collected. In the training set, the accuracy was about 95% and 98% for ANN and RF, respectively. Nevertheless, the best accuracy on the test set was obtained with RF (70%). The ML-based simulations showed that young age (<55 years), lung cancer, and occurrence of breakthrough cancer pain help to predict the number of remote consultations. Elderly patients (>75 years) with bone metastases may require more telemedicine-based clinical evaluations. Conclusion: ML-based analyses may enable clinicians to identify the best model for predicting the need for more remote consultations. It could be useful for calibrating care interventions and resource allocation. MDPI 2022-09-19 /pmc/articles/PMC9502863/ /pubmed/36143132 http://dx.doi.org/10.3390/jcm11185484 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Cascella, Marco
Coluccia, Sergio
Monaco, Federica
Schiavo, Daniela
Nocerino, Davide
Grizzuti, Mariacinzia
Romano, Maria Cristina
Cuomo, Arturo
Different Machine Learning Approaches for Implementing Telehealth-Based Cancer Pain Management Strategies
title Different Machine Learning Approaches for Implementing Telehealth-Based Cancer Pain Management Strategies
title_full Different Machine Learning Approaches for Implementing Telehealth-Based Cancer Pain Management Strategies
title_fullStr Different Machine Learning Approaches for Implementing Telehealth-Based Cancer Pain Management Strategies
title_full_unstemmed Different Machine Learning Approaches for Implementing Telehealth-Based Cancer Pain Management Strategies
title_short Different Machine Learning Approaches for Implementing Telehealth-Based Cancer Pain Management Strategies
title_sort different machine learning approaches for implementing telehealth-based cancer pain management strategies
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9502863/
https://www.ncbi.nlm.nih.gov/pubmed/36143132
http://dx.doi.org/10.3390/jcm11185484
work_keys_str_mv AT cascellamarco differentmachinelearningapproachesforimplementingtelehealthbasedcancerpainmanagementstrategies
AT colucciasergio differentmachinelearningapproachesforimplementingtelehealthbasedcancerpainmanagementstrategies
AT monacofederica differentmachinelearningapproachesforimplementingtelehealthbasedcancerpainmanagementstrategies
AT schiavodaniela differentmachinelearningapproachesforimplementingtelehealthbasedcancerpainmanagementstrategies
AT nocerinodavide differentmachinelearningapproachesforimplementingtelehealthbasedcancerpainmanagementstrategies
AT grizzutimariacinzia differentmachinelearningapproachesforimplementingtelehealthbasedcancerpainmanagementstrategies
AT romanomariacristina differentmachinelearningapproachesforimplementingtelehealthbasedcancerpainmanagementstrategies
AT cuomoarturo differentmachinelearningapproachesforimplementingtelehealthbasedcancerpainmanagementstrategies