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

Abstract

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.

Implementation of a Hybrid Care Model for Telemedicine-based Cancer Pain Management at the Cancer Center of Naples, Italy: A Cohort Study

“…It is also suitable for data collection. Besides, patients expressed a high degree of satisfaction with the platform used (7).…”

“…), storage, and security. Thus, it is also a useful instrument for descriptive and predictive analyses (7). The booking system provides access to the hospital portal.…”

“…In In previous studies, we assessed the degree of patient satisfaction (6) and developed predictive machine-learning models to identify patients who could have benefited from more remote visits (7). In this study, we sought to report and describe the collected data of a single-center experience on telemedicine employed for the treatment of cancer pain during and after the Covid-19 era.…”

Trends in Research on Artificial Intelligence in Anesthesia: A VOSviewer -Based Bibliometric Analysis

“…Secondly, this analysis is limited to anesthesia. Thus, articles relating to the study of pain if not of anesthesia relevance (e.g., cancer pain) and articles on the intensive care unit (ICU) were deliberately excluded [27]. Even if the sample was consequently reduced, this strategy allows focusing attention on anesthesia topics.…”

Relationship between breakthrough cancer pain, background cancer pain and analgesic treatment – case series and review of the literature

“…Studies support the use of telemedicine or hybrid medical assessment (combination of visits with internet-based appointments), keeping in mind that in this case very slow titration rates must be suggested, as well as frequent assessment of patients’ pain intensity and characteristics, renal and hepatic function, and cognition. 56 – 59 …”