Heart failure mortality prediction using PRISM score and development of a classification and regression tree model to refer patients for palliative care consultation

A deep learning system for heart failure mortality prediction

Heart failure (HF) is the final stage of the various heart diseases developing. The mortality rates of prognosis HF patients are highly variable, ranging from 5% to 75%. Evaluating the all-cause mortality of HF patients is an important means to avoid death and positively affect the health of patients. But in fact, machine learning models are difficult to gain good results on missing values, high dimensions, and imbalances HF data. Therefore, a deep learning system is proposed. In this system, we propose an indicator vector to indicate whether the value is true or be padded, which fast solves the missing values and helps expand data dimensions. Then, we use a convolutional neural network with different kernel sizes to obtain the features information. And a multi-head self-attention mechanism is applied to gain whole channel information, which is essential for the system to improve performance. Besides, the focal loss function is introduced to deal with the imbalanced problem better. The experimental data of the system are from the public database MIMIC-III, containing valid data for 10311 patients. The proposed system effectively and fast predicts four death types: death within 30 days, death within 180 days, death within 365 days and death after 365 days. Our study uses Deep SHAP to interpret the deep learning model and obtains the top 15 characteristics. These characteristics further confirm the effectiveness and rationality of the system and help provide a better medical service.

PRISM III Score Predicts Short-Term Outcome in Children with ARDS on Conventional and High-Frequency Oscillatory Ventilation

Therapeutic recommendations for pediatric acute respiratory distress syndrome (PARDS) include conventional (CMV) and rescue high-frequency oscillatory mode (HFOV) of mechanical ventilation (MV). The pediatric risk of mortality (PRISM) is a frequently used mortality score for critically ill patients. In search of methods to recognize those patients, we analyzed the PRISM III score as a potential predictor of the short-term outcome in MV subjects with PARDS. A retrospective five-year study of PARDS in children on MV was conducted in the Pediatric ICU. Seventy patients were divided into two groups (age group <1 year and age group 1−7 years). The PRISM III score was used to assess the 28-day outcome and possible development of complications. The most common causes of PARDS were pneumonia and sepsis. Male sex, malnourishment, sepsis, and shock were significant indicators of poor outcome. The PRISM III score values were significantly higher in those who died, as well as in subjects requiring HFOV. The score had a significant prognostic value for short-term mortality. There was no significant difference in outcome based on the comparison of two modes of ventilation. A significantly higher score was noted in subjects who developed sepsis and cardiovascular insufficiency. The PRISM III score is a fair outcome predictor during the 28-day follow-up in MV subjects with PARDS, regardless of the ventilation mode.

Palliative care referral criteria and outcomes in cancer and heart failure: a systematic review of literature

BACKGROUND

Cardiotoxicity resulting in heart failure (HF) is among the most dreaded complications of cancer therapy and can significantly impact morbidity and mortality. Leading professional societies in cardiology and oncology recommend improved access to hospice and palliative care (PC) for patients with cancer and advanced HF. However, there is a paucity of published literature on the use of PC in cardio-oncology, particularly in patients with HF and a concurrent diagnosis of cancer.

AIMS

To identify existing criteria for referral to and early integration of PC in the management of cases of patients with cancer and patients with HF, and to identify assessments of outcomes of PC intervention that overlap between patients with cancer and patients with HF.

DESIGN

Systematic literature review on PC in patients with HF and in patients with cancer.

DATA SOURCES

Databases including Ovid Medline, Ovid Embase, Cochrane Library, and Web of Science from January 2009 to September 2020.

RESULTS

Sixteen studies of PC in cancer and 14 studies of PC in HF were identified after screening of the 8647 retrieved citations. Cancer and HF share similarities in their patient-reported symptoms, quality of life, symptom burden, social support needs, readmission rates, and mortality.

CONCLUSION

The literature supports the integration of PC into oncology and cardiology practices, which has shown significant benefit to patients, caregivers, and the healthcare system alike. Incorporating PC in cardio-oncology, particularly in the management of HF in patients with cancer, as early as at diagnosis, will enable patients, family members, and healthcare professionals to make informed decisions about various treatments and end-of-life care and provide an opportunity for patients to participate in the decisions about how they will spend their final days.

An integrated review on machine learning approaches for heart disease prediction: Direction towards future research gaps

Objectives

To make a clear literature review on state-of-the-art heart disease prediction models.

Methods

It reviews 61 research papers and states the significant analysis. Initially, the analysis addresses the contributions of each literature works and observes the simulation environment. Here, different types of machine learning algorithms deployed in each contribution. In addition, the utilized dataset for existing heart disease prediction models was observed.

Results

The performance measures computed in entire papers like prediction accuracy, prediction error, specificity, sensitivity, f-measure, etc., are learned. Further, the best performance is also checked to confirm the effectiveness of entire contributions.

Conclusions

The comprehensive research challenges and the gap are portrayed based on the development of intelligent methods concerning the unresolved challenges in heart disease prediction using data mining techniques.