Deep Learning for Predicting Urgent Hospitalizations in Elderly Population Using Healthcare Administrative Databases

Sciannameo, Veronica; Daniele, Jahier  Pagliari; Ferracin, Elisa; Ricotti, Andrea; Ricceri, Fulvio; Costa, G.; Berchialla, Paola

doi:10.2139/ssrn.4022016

Cited by 2 publications

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The training phase of the model collects data variables primarily based on publicly available health conditions datasets. These variables include data about blood pressure, pulse oximetry, the concentration of glucose in the blood, activity tracking, sleep tracking with the corresponding prediction class; in addition to patient feedback and evaluation data (Dinsmore et al, 2021 ); finally, data related to health trajectories from Healthcare Administrative Databases (HADs) such as diagnoses and medication prescriptions are also included (Veronica et al, 2022 ). The production phase of the model collects data coming from the proposed tool and its associated sensory fabrics, as described in Figures 2 , 4 to predict emergent health situations requiring interventions such as early hospital admission, diagnosis, clinical procedures, and medications, will be compared with deep learning (DL) and convolutional neural network (CNN) (Nguyen et al, 2016 ; Pham et al, 2016 ) vs. traditional machine learning algorithms, e.g., Bayesian probabilistic model, k nearest neighbors, logistic regression, support vector machines, and decision tree (Deparis et al, 2018 ; Hansen et al, 2018 ; Khalid et al, 2018 ; Noh et al, 2019 ; Ben-Assuli and Padman, 2020 ; Franz et al, 2020 ; Veronica et al, 2022 ).…”

Section: Increasing Ict Usage Trends In the Elderly Population Groupmentioning

confidence: 99%

Autonomous Tool for Monitoring Multi-Morbidity Health Conditions in UAE and India

Atalla

Amin

Kumar³

et al. 2022

Front. Artif. Intell.

View full text Add to dashboard Cite

Multi-morbidity is the presence of two or more long-term health conditions, including defined physical or mental health conditions, such as diabetes or schizophrenia. One of the regular and critical health cases is an elderly person with a multi-morbid health condition and special complications who lives alone. These patients are typically not familiar with advanced Information and Communications Technology (ICT), but they are comfortable using smart devices such as wearable watches and mobile phones. The use of ICT improves medical quality, promotes patient security and data security, lowers operational and administrative costs, and gives the people in charge to make informed decisions. Additionally, the use of ICT in healthcare practices greatly reduces human errors, enhances clinical outcomes, ramps up care coordination, boosts practice efficiencies, and helps in collecting data over time. The proposed research concept provides a natural technique to implement preventive health care innovative solutions since several health sensors are embedded in devices that autonomously monitor the patients' health conditions in real-time. This enhances the elder's limited ability to predict and respond to critical health situations. Autonomous monitoring can alert doctors and patients themselves of unexpected health conditions. Real-time monitoring, modeling, and predicting health conditions can trigger swift responses by doctors and health officials in case of emergencies. This study will use data science to stimulate discoveries and breakthroughs in the United Arab Emirates (UAE) and India, which will then be reproduced in other world areas to create major gains in health for people, communities, and populations.

show abstract

Section: Increasing Ict Usage Trends In the Elderly Population Groupmentioning

confidence: 99%

Autonomous Tool for Monitoring Multi-Morbidity Health Conditions in UAE and India

Atalla

Amin

Kumar³

et al. 2022

Front. Artif. Intell.

View full text Add to dashboard Cite

show abstract

Learning prevalent patterns of co-morbidities in multichronic patients using population-based healthcare data

Seghieri,

Tortù,

Tricò

et al. 2024

Sci Rep

View full text Add to dashboard Cite

The prevalence of longstanding chronic diseases has increased worldwide, along with the average age of the population. As a result, an increasing number of people is affected by two or more chronic conditions simultaneously, and healthcare systems are facing the challenge of treating multimorbid patients effectively. Current therapeutic strategies are suited to manage each chronic condition separately, without considering the whole clinical condition of the patient. This approach may lead to suboptimal clinical outcomes and system inefficiencies (e.g. redundant diagnostic tests and inadequate drug prescriptions). We develop a novel methodology based on the joint implementation of data reduction and clustering algorithms to identify patterns of chronic diseases that are likely to co-occur in multichronic patients. We analyse data from a large adult population of multichronic patients living in Tuscany (Italy) in 2019 which was stratified by sex and age classes. Results demonstrate that (i) cardio-metabolic, endocrine, and neuro-degenerative diseases represent a stable pattern of multimorbidity, and (ii) disease prevalence and clustering vary across ages and between women and men. Identifying the most common multichronic profiles can help tailor medical protocols to patients’ needs and reduce costs. Furthermore, analysing temporal patterns of disease can refine risk predictions for evolutive chronic conditions.

show abstract

Deep Learning for Predicting Urgent Hospitalizations in Elderly Population Using Healthcare Administrative Databases

Cited by 2 publications

References 13 publications

Autonomous Tool for Monitoring Multi-Morbidity Health Conditions in UAE and India

Autonomous Tool for Monitoring Multi-Morbidity Health Conditions in UAE and India

Learning prevalent patterns of co-morbidities in multichronic patients using population-based healthcare data

Contact Info

Product

Resources

About