Machine learning-based demand forecasting in cancer palliative care home hospitalization

Soltani, Marzieh; Farahmand, Mohammad; Pourghaderi, Ahmad Reza

doi:10.1016/j.jbi.2022.104075

Cited by 18 publications

(15 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another potential application of predictive modeling using ML and DL models is to predict the need for required SC and/or PC services. Soltani et al 10▪ used a DL model with input data from demographics and health profiles to predict SPC services required by cancer patients at home. Similarly, Murphree et al 11 used an ML model with input being demographics, comorbidities, prior care, etc., to forecast PC requirements for hospitalized patients.…”

Section: Discussionmentioning

confidence: 99%

Recent advances in artificial intelligence applications for supportive and palliative care in cancer patients

Reddy

Nafees

Raman

2023

Current Opinion in Supportive &Amp; Palliative Care

View full text Add to dashboard Cite

Purpose of review Artificial intelligence (AI) is a transformative technology that has the potential to improve and augment the clinical workflow in supportive and palliative care (SPC). The objective of this study was to provide an overview of the recent studies applying AI to SPC in cancer patients. Recent findings Between 2020 and 2022, 29 relevant studies were identified and categorized into two applications: predictive modeling and text screening. Predictive modeling uses machine learning and/or deep learning algorithms to make predictions regarding clinical outcomes. Most studies focused on predicting short-term mortality risk or survival within 6 months, while others used models to predict complications in patients receiving treatment and forecast the need for SPC services. Text screening typically uses natural language processing (NLP) to identify specific keywords, phrases, or documents from patient notes. Various applications of NLP were found, including the classification of symptom severity, identifying patients without documentation related to advance care planning, and monitoring online support group chat data. Summary This literature review indicates that AI tools can be used to support SPC clinicians in decision-making and reduce manual workload, leading to potentially improved care and outcomes for cancer patients. Emerging data from prospective studies supports the clinical benefit of these tools; however, more rigorous clinical validation is required before AI is routinely adopted in the SPC clinical workflow.

show abstract

Section: Discussionmentioning

confidence: 99%

Recent advances in artificial intelligence applications for supportive and palliative care in cancer patients

Reddy

Nafees

Raman

2023

Current Opinion in Supportive &Amp; Palliative Care

View full text Add to dashboard Cite

show abstract

“…Various prediction methodologies were applied by industries, such as the medical [26], resource [27][28][29][30], economic [31], and military industries [32], but there have been no studies of CNN deep learning network applications using image data.…”

Section: Previous Studies On Demand Forecastingmentioning

confidence: 99%

Tab2vox: CNN-Based Multivariate Multilevel Demand Forecasting Framework by Tabular-To-Voxel Image Conversion

2022

View full text Add to dashboard Cite

Since demand is influenced by a wide variety of causes, it is necessary to decompose the explanatory variables into different levels, extract their relationships effectively, and reflect them in the forecast. In particular, this contextual information can be very useful in demand forecasting with large demand volatility or intermittent demand patterns. Convolutional neural networks (CNNs) have been successfully used in many fields where important information in data is represented by images. CNNs are powerful because they accept samples as images and use adjacent voxel sets to integrate multi-dimensional important information and learn important features. On the other hand, although the demand-forecasting model has been improved, the input data is still limited in its tabular form and is not suitable for CNN modeling. In this study, we propose a Tab2vox neural architecture search (NAS) model as a method to convert a high-dimensional tabular sample into a well-formed 3D voxel image and use it in a 3D CNN network. For each image representation, the 3D CNN forecasting model proposed from the Tab2vox framework showed superior performance, compared to the existing time series and machine learning techniques using tabular data, and the latest image transformation studies.

show abstract

“…Finally, the implementation of the smart HaH management process for the disabled elderly is targeted and dynamic. The results of this study showed that the adoption of a wise management strategy involved the formation of a multidisciplinary team, clari of team members' responsibilities, comprehensive pre-admission assessment and dynamic level assessment throughout the process.Soltani et al [21] developed a management information system (MIS), which is based on a predictive model that allows for the prediction of individual i.e. and population demand for home inpatient services.…”

Section: Research Trends In the Smart Management Of Hah For The Disab...mentioning

confidence: 99%

Smart hospital at home management for disabled elderly:A scoping review

Zhang

Tian

2022

Preprint

View full text Add to dashboard Cite

Background Smart hospital at home(HaH) have become a potential solution to the medical service needs of patients at home, but little is known about their application effects in the disabled elderly. It is necessary to map HaH management models and describe their forms, content, strategies, and evaluation indicators. Methods A scoping review was conducted based on the framework from Arksey and O’Malley. PubMed，Web of Science，Wangfang，CNKI，VIP and OpenGrey were searched until June 30,2022. Mapping existing the smart HaH management for the disabled elderly, including form, content, strategy, and evaluation. Results There were a total of 8 included studies，which focused on the following issues: The forms of management covering: mobile medical and telemedicine;The content covering clinical consultation, establishment of patient health records, guidance on equipment use, and alarm management; Strategy covering the formation of multidisciplinary teams, clarification of team members' responsibilities, comprehensive assessment before bed admission, and dynamic grade assessment throughout the process; Evaluation covering patient health outcomes, smart medical dependence, patient satisfaction evaluation, management program compliance and feasibility; Conclusions Smart HaH management presents comprehensive, holistic, targeted, and dynamic, and is relatively consistent in terms of management form, content, and strategy characteristics, and has achieved positive application effects. However, there is still a lack of high-quality research data and standardized and unified management evaluation criteria, and there is an urgent need to conduct a multi-center, large-sample study of smart HaH management programs for the disabled elderly.

show abstract

Machine learning-based demand forecasting in cancer palliative care home hospitalization

Cited by 18 publications

References 40 publications

Recent advances in artificial intelligence applications for supportive and palliative care in cancer patients

Recent advances in artificial intelligence applications for supportive and palliative care in cancer patients

Tab2vox: CNN-Based Multivariate Multilevel Demand Forecasting Framework by Tabular-To-Voxel Image Conversion

Smart hospital at home management for disabled elderly:A scoping review

Contact Info

Product

Resources

About