Machine learning methods, applications and economic analysis to predict heart failure hospitalisation risk: a scoping review protocol.

INTRODUCTION: Machine learning (ML) has emerged as a powerful tool for uncovering patterns and generating new information. In cardiology, it has shown promising results in predictive outcomes risk assessment of heart failure (HF) patients, a chronic condition affecting over 64 million individuals globally.This scoping review aims to synthesise the evidence on ML methods, applications and economic analysis to predict the HF hospitalisation risk. METHODS AND ANALYSIS: This scoping review will use the approach described by Arksey and O'Malley. This protocol will use the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) Protocol, and the PRISMA extension for scoping reviews will be used to present the results. PubMed, Scopus and Web of Science are the databases that will be searched. Two reviewers will independently screen the full-text studies for inclusion and extract the data. All the studies focusing on ML models to predict the risk of hospitalisation from HF adult patients will be included. ETHICS AND DISSEMINATION: Ethical approval is not required for this review. The dissemination strategy includes peer-reviewed publications, conference presentations and dissemination to relevant stakeholders.

Application of the time-driven activity-based costing methodology to a complex patient case management program in Portugal.

BACKGROUND: The number of people with chronic diseases has increased globally, as has the number of chronic diseases per person. Faced with this reality, the term "complex patient" is current and actual. The healthcare costs associated with these patients are high and are expected to increase since most healthcare systems are not yet ready to provide integrated long-term care. In Portugal, several health institutions have made efforts to provide integrated care: case management models have been implemented to complex patients follow-up. However, studies related to cost of these programs are still limited. Therefore, a qualitative investigation was conducted, approaching the design criteria of a case study research, to design a case management program for complex patients and determine its direct costs, following the Time-Driven Activity-Based Costing methodology, in Local Health Unit setting. METHOD: The direct costs of providing care to a complex patient involved in a case management program were determined, using the Time-Driven Activity-Based Costing methodology. A map of the complex patient was drawn, considering a standard flow in the program. Times and costs were allocated to the activities on the map, following Portuguese and international practices of case management models. RESULTS: A total of 684,45€/year is spent for each new patient in the case management program, of which 452,65€ corresponds to cost of remuneration of professionals involved; and 663,85€/year, for each patient who is in the case management program (over 1 year), where 432,05€ corresponds to cost of the remuneration of the professionals involved. Follow-up is the most costly phase (80.82%) and where more time is spent (85.62%). CONCLUSION: The time spent by professionals and resources involved and the costs associated with each patient were obtained. The economic impact of the analysed activities was not studied, however, according to international authors, when well applied and selected, integrated care models lead to cost reduction and improved health outcomes.

Machine learning prediction of mortality in Acute Myocardial Infarction.

BACKGROUND: Acute Myocardial Infarction (AMI) is the leading cause of death in Portugal and globally. The present investigation created a model based on machine learning for predictive analysis of mortality in patients with AMI upon admission, using different variables to analyse their impact on predictive models. METHODS: Three experiments were built for mortality in AMI in a Portuguese hospital between 2013 and 2015 using various machine learning techniques. The three experiments differed in the number and type of variables used. We used a discharged patients' episodes database, including administrative data, laboratory data, and cardiac and physiologic test results, whose primary diagnosis was AMI. RESULTS: Results show that for Experiment 1, Stochastic Gradient Descent was more suitable than the other classification models, with a classification accuracy of 80%, a recall of 77%, and a discriminatory capacity with an AUC of 79%. Adding new variables to the models increased AUC in Experiment 2 to 81% for the Support Vector Machine method. In Experiment 3, we obtained an AUC, in Stochastic Gradient Descent, of 88% and a recall of 80%. These results were obtained when applying feature selection and the SMOTE technique to overcome imbalanced data. CONCLUSIONS: Our results show that the introduction of new variables, namely laboratory data, impacts the performance of the methods, reinforcing the premise that no single approach is adapted to all situations regarding AMI mortality prediction. Instead, they must be selected, considering the context and the information available. Integrating Artificial Intelligence (AI) and machine learning with clinical decision-making can transform care, making clinical practice more efficient, faster, personalised, and effective. AI emerges as an alternative to traditional models since it has the potential to explore large amounts of information automatically and systematically.

Decision-making support systems on extended hospital length of stay: Validation and recalibration of a model for patients with AMI.

Background: Cardiovascular diseases are still a significant cause of death and hospitalization. In 2019, circulatory diseases were responsible for 29.9% of deaths in Portugal. These diseases have a significant impact on the hospital length of stay. Length of stay predictive models is an efficient way to aid decision-making in health. This study aimed to validate a predictive model on the extended length of stay in patients with acute myocardial infarction at the time of admission. Methods: An analysis was conducted to test and recalibrate a previously developed model in the prediction of prolonged length of stay, for a new set of population. The study was conducted based on administrative and laboratory data of patients admitted for acute myocardial infarction events from a public hospital in Portugal from 2013 to 2015. Results: Comparable performance measures were observed upon the validation and recalibration of the predictive model of extended length of stay. Comorbidities such as shock, diabetes with complications, dysrhythmia, pulmonary edema, and respiratory infections were the common variables found between the previous model and the validated and recalibrated model for acute myocardial infarction. Conclusion: Predictive models for the extended length of stay can be applied in clinical practice since they are recalibrated and modeled to the relevant population characteristics.

Direct Costs of COVID-19 Inpatient Admissions in a Portuguese Tertiary Care University Centre.

Background: The COVID-19 pandemic has posed greater financial pressure on health systems and institutions that had to respond to the specific needs of COVID-19 patients while ensuring the safety of the diagnosis and treatment of all patients and healthcare professionals. To assess the financial impact of COVID-19 patients admitted to hospitals, we have characterized the cost of COVID-19 admissions, using inpatient data from a Portuguese Tertiary Care University Centre. Methods: We analysed inpatient data from adult patients diagnosed with COVID-19 who were admitted between March 1, 2020 and May 31, 2020. Admissions were eligible if the ICD-10-CM principal diagnosis was coded U07.1. We excluded admissions from patients under 18 years old, admissions with incomplete records, admissions from patients who had been transferred to or from other hospitals or those whose inpatient stay was under 24 h. Pregnancy, childbirth, and puerperium admissions were also excluded, as well as admissions from patients who had undergone surgery. Results: We identified 223 admissions of patients diagnosed with COVID-19. Most were men (64.1%) and aged 45-64 years (30.5%). Around 13.0% of patients were admitted to intensive care units and 9.9% died in hospital. The average length of hospital stay was 12.7 days (SD = 10.2) and the average estimated cost per admission was EUR 8,177 (SD = 11,534), which represents more than triple the inpatient base price (EUR 2,386). Human resources accounted for the highest proportion of the total costs per admission (50.8%). About 92.4% of the admissions were assigned to Diagnosis Related Group (DRG) 723, whose inpatient price is lower than COVID-19 inpatient costs for all degrees of severity. Conclusion: COVID-19 admissions represent a substantial financial burden for the Portuguese NHS. For each COVID-19 hospitalized patient it would have been possible to treat three other hospitalized patients. Also, the price set for DRG 723 is not adjusted to the cost of COVID-19 patients. These findings highlight the need for additional financial resources for the health system and, in particular, for hospitals that have treated high volumes of hospitalized patients diagnosed with COVID-19.

Introdução: A pandemia por COVID-19 colocou uma maior pressão financeira sobre os sistemas e instituições de saúde que tiveram de responder às necessidades específicas dos doentes com COVID-19, garantindo a segurança do diagnóstico e tratamento de todos os doentes e profissionais de saúde. Para avaliar o impacto financeiro dos doentes com COVID-19 internados em hospitais, caracterizámos o custo dos internamentos com COVID-19, utilizando dados de um Centro Hospitalar Universitário Português. Métodos: Analisaram-se os dados de internamento dos doentes adultos diagnosticados com COVID- 19 admitidos entre 1 de março de 2020 e 31 de maio de 2020. Foram considerados elegíveis os episódios de internamento com diagnóstico principal U07.1 (ICD-10- CM). Excluíram-se os internamentos de doentes com menos de 18 anos, internamentos com registos incompletos, internamentos de doentes que foram transferidos de/ou para outros hospitais ou aqueles com internamento inferior a 24 horas. Também foram excluídos os internamentos por gravidez, parto e puerpério, bem como internamentos de doentes operados. Resultados: Identificaramse 223 internamentos de doentes diagnosticados com COVID-19. A maioria era do sexo masculino (64,1%) e com idade entre 45 e 64 anos (30,5%). Cerca de 13,0% dos doentes foram internados em unidades de cuidados intensivos e 9,9% morreram no hospital. A média do tempo de internamento foi 12,7 dias (DP = 10,2) e a média do custo estimado por admissão foi 8.177€ (DP = 11.534), o que representa mais do triplo do preço base de internamento (2.386€). Os recursos humanos representaram a maior proporção do total dos custos por admissão (50,8%). Cerca de 92,4% dos internamentos foram atribuídos ao Grupo de Diagnóstico Homogéneo (GDH) 723, cujo preço de internamento é inferior aos custos de internamento com COVID-19 para todos os graus de severidade. Conclusão: Os internamentos por COVID-19 representam um encargo financeiro substancial para o SNS português. Por cada doente internado com COVID-19, seria possível tratar outros três doentes internados. Além disso, o preço definido para o GDH 723 não está ajustado ao custo dos doentes com COVID-19. Estes resultados destacam a necessidade de recursos financeiros adicionais para o sistema de saúde e, em particular, para os hospitais que trataram um elevado número de doentes internados e diagnosticados com COVID-19.

The impact of diabetes on multiple avoidable admissions: a cross-sectional study.

BACKGROUND: Multiple admissions for ambulatory care sensitive conditions (ACSC) are responsible for an important proportion of health care expenditures. Diabetes is one of the conditions consensually classified as an ACSC being considered a major public health concern. The aim of this study was to analyse the impact of diabetes on the occurrence of multiple admissions for ACSC. METHODS: We analysed inpatient data of all public Portuguese NHS hospitals from 2013 to 2015 on multiple admissions for ACSC among adults aged 18 or older. Multiple ACSC users were identified if they had two or more admissions for any ACSC during the period of analysis. Two logistic regression models were computed. A baseline model where a logistic regression was performed to assess the association between multiple admissions and the presence of diabetes, adjusting for age and sex. A full model to test if diabetes had no constant association with multiple admissions by any ACSC across age groups. RESULTS: Among 301,334 ACSC admissions, 144,209 (47.9%) were classified as multiple admissions and from those, 59,436 had diabetes diagnosis, which corresponded to 23,692 patients. Patients with diabetes were 1.49 times (p < 0,001) more likely to be admitted multiple times for any ACSC than patients without diabetes. Younger adults with diabetes (18-39 years old) were more likely to become multiple users. CONCLUSION: Diabetes increases the risk of multiple admissions for ACSC, especially in younger adults. Diabetes presence is associated with a higher resource utilization, which highlights the need for the implementation of adequate management of chronic diseases policies.