Artificial intelligence-based analysis of payment system data can predict one-year mortality of hospitalized patients with heart failure

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
T Tohyama ◽  
K Funakoshi ◽  
H Kaku ◽  
N Enzan ◽  
M Ikeda ◽  
...  
Keyword(s):  
Heart Failure ◽  
Length Of Hospital Stay ◽  
Ensemble Classifier ◽  
Payment System ◽  
Training Set ◽  
C Statistic ◽  
System Data ◽  
Validation Set ◽  
One Year ◽  
The One

Abstract Background Individual risk stratification is fundamental in the care of heart failure (HF) patients. However, the prediction performance of risk scores, such as MAGGIC and SHFM, is not adequate and, more importantly, they need additional predictors including various biomarkers, imaging data, and environmental factors. Data from a case-mix payment system including diagnosis and procedures with outcomes can be used to develop the risk prediction models, allowing the use of big data for a more accurate prediction of mortality. Purpose This study aimed to develop artificial intelligence (AI) models for predicting 1-year mortality in patients hospitalized due to HF. Methods We analyzed the data from 10175 patients enrolled in the Japanese Registry Of Acute Decompensated Heart Failure (JROADHF). Candidate variables included the data obtained from a payment system introduced by the Japanese government, the Diagnosis Procedure Combination (DPC), which included each patient profile (age, sex, height, weight), principal diagnosis for hospitalization, comorbidities, procedures, length of hospital stay, and discharge status. They did not include clinical data available from patients such as vital status, laboratory data including bio-makers, electrocardiographic and echocardiographic data. The collected data were divided into the training set and the validation set (80%: 20%). With the training set, 5 AI models (logistic regression, random forest, support vector machine, neural network, and ensemble classifier) learned the one-year mortality results. AI models were evaluated by using the validation set with ROC analysis. The training and validation steps were repeated 10 times with different seed values to calculate the C-statistic of each model. We also identified the predictors for one-year prognosis acquired from the AI models. Results At 1-year of follow-up, a total of 1727 patients had died (17%). Among the machine learning models, the ensemble classifier showed the highest C-statistic of 0.76 (95% confidence interval: 0.75 to 0.77) for predicting mortality. Top predictors acquired from the random forest classifier was ADL (Barthel Index) at discharge, age, body mass index, and length of hospital stay. Conclusion By using AI-based analysis of a national case-mix payment system data, the present risk stratification model could predict the one-year mortality of hospitalized HF patients without any quantitative laboratory and physiological data. Furthermore, the present results could emphasize the advantage of this approach using the claim-based data that are routinely collected in a usual daily practice with no need to collect any additional information. Funding Acknowledgement Type of funding source: Public grant(s) – National budget only. Main funding source(s): Japan Agency for Medical Research and Development

scholarly journals CARDIOSYNCHRONOUS ELECTROMYOSTIMULATION IN PATIENTS WITH ACUTE HEART FAILURE

2013 ◽  
Vol 12 (6) ◽  
pp. 15-20
Author(s):  
G. G. Ivanov ◽  
M. Yu. Orkvasov ◽  
G. Khalabi
Keyword(s):  
Heart Failure ◽  
Conservative Treatment ◽  
Acute Heart Failure ◽  
Clinical Symptoms ◽  
Impedance Measurement ◽  
Pharmacological Therapy ◽  
Group I ◽  
Group Ii ◽  
One Year ◽  
The One

Aim. To study the effectiveness of the external cardiosynchronous electromyostimulation (ECSEMS) in patients with different variants of acute heart failure (AHF).Material and methods. The study included 62 AHF patients: Group I — those receiving only standard pharmacological therapy; and Group II — those in whom standard pharmacological therapy was ineffective after 12 hours, and who were also administered ECSEMS sessions for the next 7 days. The examination included multi-frequency bio-impedance measurement and dispersion mapping.Results. Clinical symptoms were less severe in Group I. In 64% of the Group II patients, the combination treatment was associated with a positive dynamics of the water balance parameters. The 7-day ECSEMS, as a part of the complex management of AHF patients, significantly reduced the one-month lethality, although did not change the one-year survival.Conclusion. The ECSEMS method could be used in order to increase the effectiveness of the conservative treatment of AHF patients. 

Effect of home-based telecardiology on chronic heart failure: Costs and outcomes

2005 ◽  
Vol 11 (1_suppl) ◽  
pp. 16-18 ◽  
Author(s):  
S Scalvini ◽  
S Capomolla ◽  
E Zanelli ◽  
M Benigno ◽  
D Domenighini ◽  
...  
Keyword(s):  
Heart Failure ◽  
Chronic Heart Failure ◽  
Usual Care ◽  
Usual Care Group ◽  
Care Group ◽  
Home Based ◽  
Clinical Instability ◽  
One Year ◽  
The One ◽  
The Cost

Chronic heart failure (CHF) remains a common cause of disability. We have investigated the use of home-based telecardiology (HBT) in CHF patients. Four hundred and twenty-six patients were enrolled in the study: 230 in the HBT group and 196 in the usual-care group. HBT consisted of trans-telephonic follow-up and electrocardiogram (ECG) monitoring, followed by visits from the paramedical and medical team. A one-lead ECG recording was transmitted to a receiving station, where a nurse was available for reporting and interactive teleconsultation. The patient could call the centre when assistance was required (tele-assistance), while the team could call the patient for scheduled appointments (telemonitoring). The one-year clinical outcomes showed that there was a significant reduction in rehospitalizations in the HBT group compared with the usual-care group (24% versus 34%, respectively). There was an increase in quality of life in the HBT group (mean Minnesota Living Questionnaire scores 29 and 23.5, respectively). The total costs were lower in the HBT group (107,494 and 140,874, respectively). The results suggest that a telecardiology service can detect and prevent clinical instability, reduce rehospitalization and lower the cost of managing CHF patients.

Abstract P699: Trends in Ischemic Stroke Risk Factors and Outcomes in a Rural Population in the United States

Stroke ◽  
2021 ◽  
Vol 52 (Suppl_1) ◽  
Author(s):  
Durgesh Chaudhary ◽  
Ayesha Khan ◽  
Shima Shahjouei ◽  
Mudit Gupta ◽  
Clare Lambert ◽  
...  
Keyword(s):  
Risk Factors ◽  
Heart Failure ◽  
Atrial Fibrillation ◽  
Ischemic Stroke ◽  
Rural Population ◽  
The United States ◽  
Stroke Recurrence ◽  
Stroke Mortality ◽  
One Year ◽  
The One

Introduction: The stroke mortality rate has gradually declined due to improved interventions and controlled risk factors. We investigated the trends in stroke risk factors and outcomes among a rural population in the United States between 2004 and 2018. Methods: We built a comprehensive stroke database called “Geisinger NeuroScience Ischemic Stroke (GNSIS)” for this study. Clinical data were extracted from multiple sources, including electronic health records and quality data. Results: Our cohort comprised of 8,561 consecutive ischemic stroke patients (mean age: 70.1±13.9 years, men: 51.6%, 95.1% Caucasian). Hypertension was the most prevalent risk factor (75.2%). The rate of hypertension, diabetes, dyslipidemia, and history of stroke increased significantly over the fifteen years window. The one-year recurrence and mortality rates were 6.3% and 15.8%, respectively. Although the one-year stroke recurrence increased from 2004 to 2018 (Cochran-Armitage test Z = -3.66, p<0.001), the one-year stroke mortality rate decreased significantly (Cochran-Armitage test Z = 2.39, p=0.008). Age >65 years, atrial fibrillation or flutter, heart failure, and prior ischemic stroke were independently associated with one-year all-cause mortality in stratified Cox proportional hazards model. In the Fine-Gray competing risk model, diabetes mellitus and age <65 years was found to be associated with one-year ischemic stroke recurrence. In the logistic regression, chronic kidney disease (CKD), diabetes, and prior ischemic stroke were predictors of one-year recurrence while age >65 years, atrial fibrillation or flutter, CKD, heart failure, prior hemorrhagic and ischemic stroke, history of neoplasm, myocardial infarction, and rheumatic diseases were predictors of one-year mortality. Conclusion: Although stroke mortality has decreased, stroke recurrence and several vascular risk factors have significantly increased in our rural population between 2004-2018. Older age, atrial fibrillation or flutter, heart failure, and prior ischemic stroke were independently associated with one-year all-cause mortality while diabetes mellitus and age less than 65 years were predictors of ischemic stroke recurrence.

scholarly journals BLOOD PRESSURE TRENDS PRECEDING DEMENTIA: A STUDY OF HEART FAILURE PATIENTS

2019 ◽  
Vol 3 (Supplement_1) ◽  
pp. S959-S959
Author(s):  
Connor Wilson ◽  
Amanda Pangle ◽  
Jeanne Wei ◽  
Gohar Azhar
Keyword(s):  
Heart Failure ◽  
Blood Pressure ◽  
Systolic Pressure ◽  
Dementia Diagnosis ◽  
Retrospective Case ◽  
Significant Difference ◽  
Diagnosis Of Dementia ◽  
Blood Pressures ◽  
One Year ◽  
The One

Abstract Blood pressure and perfusion of the brain are central components of neurological health that are often influenced by heart failure. This retrospective case-control study analyzed blood pressure changes preceding the diagnosis of dementia in patients over the age of 60. Blood pressures were obtained from the date of dementia diagnosis, and then one year and five years before diagnosis. Study “controls” were age-matched patients without dementia, using the mean age of dementia diagnosis as the first data point. Over the five-year period preceding diagnosis, 67.2% with dementia showed decreasing systolic pressure compared to 46.6% of patients without dementia. Similarly, 62.7% with dementia showed a decreasing systolic pressure over the one-year period, compared to 50.0% of those without dementia. Additionally, there was a significant difference (p &lt; 0.001) in the dementia rates between African American and Caucasian subgroups (55.0% African Americans vs. 31.0% Caucasians). Patients with dementia were more likely to have decreasing blood pressure trends than age-matched patients without dementia and appeared to have significantly lower blood pressures one year before the diagnosis. It is crucial that providers are cognizant of these trends and risk factors for dementia as they manage blood pressures in geriatric patients.

Effectiveness of telemonitoring-enhanced support over structured telephone support in reducing heart failure-related healthcare utilization in a multi-ethnic Asian setting

2019 ◽  
Vol 26 (6) ◽  
pp. 332-340
Author(s):  
Wai Leng Chow ◽  
Chaw Yu K Aung ◽  
Shao Chuen Tong ◽  
Geraldine SL Goh ◽  
Sheldon Lee ◽  
...  
Keyword(s):  
Heart Failure ◽  
Healthcare Utilization ◽  
Patient Activation ◽  
Cost Of Care ◽  
Self Management ◽  
Telephone Support ◽  
Total Cost ◽  
Bed Days ◽  
One Year ◽  
The One

Aims Our study aimed to compare the effectiveness of telemonitoring over structured telephone support in reducing heart failure-related healthcare utilization. Methods This was a non-randomised controlled study comparing 150 recently discharged heart failure patients enrolled into telemonitoring and 55 patients who only received structured telephone support after rejecting telemonitoring. Patient activation, knowledge and self-management levels were measured at baseline and the one year upon programme completion using the Patient Activation Measure, the Dutch Heart Failure Knowledge Scale and the Self-Care of Heart Failure Index respectively. Differences in heart failure-related and all-cause hospitalization rates, total bed days and mortality rates at 180 days and at one year, knowledge and self-management scores and total cost of care between groups at one year were analysed. Results Average age of telemonitoring was 57.9 years and 63.9 years for structured telephone support. Significant difference in adjusted 180-day all-cause bed days (telemonitoring: five days versus structured telephone support: 9.8 days), heart failure-related bed days (telemonitoring: 1.2 days versus structured telephone support: six days) and adjusted one-year heart failure-related bed days (telemonitoring: 2.2 days versus structured telephone support: 6.6 days) were observed. Telemonitoring was associated with reduced all-cause one-year mortality (hazard ratio 0.32, p = 0.02). Estimated mean maintenance and confidence scores were significantly higher in the telemonitoring group at one year. No differences in all-cause and HF-related readmission rates and knowledge levels were observed. The one-year total cost of care was predicted to be Singapore dollars (SG$) 2774.4 lower ( p = 0.07) in telemonitoring. Conclusion In conclusion, telemonitoring was associated with lower all-cause and heart failure-related total bed days at 180 days, lower heart failure-related total bed days and total cost of care at one year as compared with structured telephone support.

Incremental Effects of Concurrent Pharmacotherapeutic Regimens for Heart Failure on Hospitalizations and Costs

2005 ◽  
Vol 39 (11) ◽  
pp. 1785-1791 ◽  
Author(s):  
Grant H Skrepnek ◽  
Jacob Abarca ◽  
Daniel C Malone ◽  
Edward P Armstrong ◽  
Farshad M Shirazi ◽  
...  
Keyword(s):  
Heart Failure ◽  
Inappropriate Medication ◽  
Care Organization ◽  
Regression Methods ◽  
Treatment Regimens ◽  
Patient Demographics ◽  
Inappropriate Medication Use ◽  
One Year ◽  
The One ◽  
Evidence Based Care

BACKGROUND Inappropriate medication use in patients with heart failure (HF) presents challenges in providing optimal, evidence-based care. OBJECTIVE To evaluate the incremental differences of concurrent and persistent use of angiotensin-converting enzyme (ACE) inhibitors, β-blockers, loop diuretics, and digoxin on the one-year, all-cause risk of hospitalization and total healthcare costs associated with treatment of HF in patients enrolled in a managed care organization within the US. METHODS A retrospective database analysis was conducted spanning from January 1, 1997, to December 31, 1999. Multivariate regression methods were used to examine the association between treatment regimens and hospitalizations or costs after controlling for patient demographics and risk factors. RESULTS Of the 1903 patients meeting inclusion criteria, 32.3% (n = 615) received none of the 4 HF agents studied and were associated with a 2.5 times greater risk (p ≤ 0.001) of hospitalization and 43.6% higher (p ≤ 0.001) total costs compared with all other patients with HF. Comparatively, 13.9% (n = 264) utilized the HF medications investigated for at least 6 months. Of those with persistent use of ≥3 agents, approximate decreases in hospitalizations were noted of 80% (p ≤ 0.001) and total costs of 70% (p ≤ 0.001) relative to patients receiving no HF therapy. CONCLUSIONS A substantial portion of patients with HF may be receiving suboptimal pharmacotherapeutic care in real-world practice settings, potentially incurring large increases in hospitalizations and total costs. Quality improvement initiatives should seek to identify and manage those not being treated according to guideline recommendations.

scholarly journals Evaluation of Rib Fractures due to Trauma

2021 ◽  
pp. 46-50
Author(s):  
Suphi Aydin ◽  
Ahmet Dumanli ◽  
Adem Gencer
Keyword(s):  
Gastrointestinal Bleeding ◽  
Hospital Stay ◽  
Traffic Accidents ◽  
Length Of Hospital Stay ◽  
Mortality Rates ◽  
Rib Fractures ◽  
The Mean ◽  
One Year ◽  
The One

Introduction and Aim: We aimed to evaluate the one-year mortality rates and the effect of comorbid diseases on mortality in patients with trauma and isolated rib fractures. Materials and Methods: Ninety patients who had trauma, isolated rib fracture between January 2016 and December 2016 and could be reached after one year after the trauma were included in the study. The files of the patients were scanned retrospectively. Age, gender, and length of hospital stay were recorded. After one-year follow-up, they were contacted by phone to evaluate the rates of additional disease and mortality. Results: 27 of the patients were female (30%), 63 of them were male (70%). Regarding the causes of injury, there were falls in 42 patients at most and in-vehicle traffic accidents in 35 patients. The mean age was 56.85 ± 16.33, the mean hospital stay was 4.04 ± 4.55 days. The most common comorbidities were diabetes mellitus in 13 patients and hypertension in 11 patients. The least detected additional diseases are; Ulcerative colitis, epilepsy, arrhythmia, gastroesophageal reflux, gastrointestinal bleeding, rheumatism, Alzheimer and Familial Mediterranean Fever in 1 patient each. One patient died who had gastrointestinal bleeding. Mortality rate was 1.11%. Conclusions: Post-traumatic rib fractures disrupt people's quality of life and cause morbidity and mortality. Although the risk of comorbid mortality increases, close follow-up is important in preventing or reducing mortality rates.

Sign in / Sign up

Export Citation Format

Share Document