P1218Deep learning survival analysis enhances the value of hybrid PET/CT for long-term cardiovascular event prediction

2019 ◽  
Vol 40 (Supplement_1) ◽  
Author(s):  
L E Juarez-Orozco ◽  
J W Benjamins ◽  
T Maaniitty ◽  
A Saraste ◽  
P Van Der Harst ◽  
...  
Keyword(s):  
Myocardial Infarction ◽  
Survival Analysis ◽  
Deep Learning ◽  
Ct Angiography ◽  
Time To Event ◽  
Clinical Variables ◽  
Pet Ct ◽  
Early Revascularization

Abstract Background Deep Learning (DL) is revolutionizing cardiovascular medicine through complex data-pattern recognition. In spite of its success in the diagnosis of coronary artery disease (CAD), DL implementation for prognostic evaluation of cardiovascular events is still limited. Traditional survival models (e.g.Cox) notably incorporate the effect of time-to-event but are unable to exploit complex non-liner dependencies between large numbers of predictors. On the other hand, DL hasn't systematically incorporated time-to-event for prognostic evaluations. Long-term registries of hybrid PET/CT imaging represent a suitable substrate for DL-based survival analysis due the large amount of time-dependent structured variables that they convey. Therefore, we sought to evaluate the feasibility and performance of DL Survival Analysis in predicting the occurrence of myocardial infarction (MI) and death in a long-term registry of cardiac hybrid PET/CT. Methods Data from our PET/CT registry of symptomatic patients with intermediate CAD risk who underwent sequential CT angiography and 15O-water PET for suspected ischemia, was analyzed. The sample has been followed for a 6-year average for MI or death. Ten clinical variables were extracted from electronic records including cardiovascular risk factors, dyspnea and early revascularization. CT angiography images were evaluated segmentally for: presence of plaque, % of luminal stenosis and calcification (58 variables). Absolute stress PET myocardial perfusion data was evaluated globally and regionally across vascular territories (4 variables). Cox-Nnet (a deep survival neural network) was implemented in a 5-fold cross-validated 80:20 split for training and testing. Resulting DL-hazard ratios were operationalized and compared to the observed events developed during follow-up. The performance of Cox-Nnet evaluating structured CT, PET/CT, and PET/CT+clinical variables was compared to expert interpretation (operationalized as: normal coronaries, non-obstructive CAD, obstructive CAD) and to Calcium Score (CaSc), through the concordance (c)-index. Results There were 426 men and 525 women with a mean age of 61±9 years-old. Twenty-four MI and 49 deaths occurred during follow-up (1 month–9.6 years), while 11.5% patients underwent early revascularization. Cox-Nnet evaluation of PET/CT data (c-index=0.75) outperformed categorical expert interpretation (c-index=0.54) and CaSc (c-index=0.65), while hybrid PET/CT and PET/CT+clinical (c-index=0.75) variables demonstrated incremental performance overall independent from early revascularization. Conclusion Deep Learning Survival Analysis is feasible in the evaluation of cardiovascular prognostic data. It might enhance the value of cardiac hybrid PET/CT imaging data for predicting the long-term development of myocardial infarction and death. Further research into the implementation of Deep Learning for prognostic analyses in CAD is warranted.

scholarly journals Later is not necessarily better: limitations of survival analysis in studies of long-term drug treatment of psychiatric conditions

2021 ◽  
pp. bmjebm-2021-111743
Author(s):  
Joanna Moncrieff ◽  
Janus Christian Jakobsen ◽  
Max Bachmann
Keyword(s):  
Survival Analysis ◽  
Statistical Tests ◽  
Cumulative Risk ◽  
Previous Treatment ◽  
Time To Event ◽  
Actual Outcome ◽  
Psychiatric Conditions ◽  
Withdrawal Effects

Survival analysis is routinely used to assess differences between groups in relapse prevention and treatment discontinuation studies involving people with long-term psychiatric conditions. The actual outcome in survival analysis is ‘time to event’, yet, in the mental health field, there has been little consideration of whether a temporary delay to relapse is clinically relevant in a condition that can last for decades. Moreover, in psychiatric drug trials, a pattern of elevated early relapses following randomisation to placebo or no treatment is common. This may be the result of the withdrawal of previous treatment leading to physiological withdrawal effects, which may be mistaken for relapse, or genuine relapse precipitated by the process of withdrawal. Such withdrawal effects typically produce converging survival curves eventually. They inevitably lead to differences in time to relapse, even when there is little or no difference in the cumulative risk of relapse at final follow-up. Therefore, statistical tests based on survival analyses can be misleading because they obscure these withdrawal effects. We illustrate these difficulties in a trial of antipsychotic reduction versus maintenance, and a trial of prophylactic esketamine in people with treatment-resistant depression. Both illustrate withdrawal-related effects that underline the importance of long-term follow-up and question the use of tests based on time to event. Further discussion of the most relevant outcome and appropriate approach to analysis, and research on patient and carer preferences is important to inform the design of future trials and interpretation of existing ones.

scholarly journals The Role of Hydraulic Silicate Cements on Long-Term Properties and Biocompatibility of Partial Pulpotomy in Permanent Teeth

Materials ◽  
2021 ◽  
Vol 14 (2) ◽  
pp. 305
Author(s):  
Chung-Min Kang ◽  
Saemi Seong ◽  
Je Seon Song ◽  
Yooseok Shin
Keyword(s):  
Regression Analysis ◽  
Cox Regression ◽  
Antimicrobial Properties ◽  
Permanent Teeth ◽  
Success Rates ◽  
Pulp Tissue ◽  
Cox Regression Analysis ◽  
Clinical Variables

The use of hydraulic silicate cements (HSCs) for vital pulp therapy has been found to release calcium and hydroxyl ions promoting pulp tissue healing and mineralized tissue formation. The present study investigated whether HSCs such as mineral trioxide aggregate (MTA) affect their biological and antimicrobial properties when used as long-term pulp protection materials. The effect of variables on treatment outcomes of three HSCs (ProRoot MTA, OrthoMTA, and RetroMTA) was evaluated clinically and radiographically over a 48–78 month follow-up period. Survival analysis was performed using Kaplan–Meier survival curves. Fisher’s exact test and Cox regression analysis were used to determine hazard ratios of clinical variables. The overall success rate of MTA partial pulpotomy was 89.3%; Cumulative success rates of the three HSCs were not statistically different when analyzed by Cox proportional hazard regression analysis. None of the investigated clinical variables affected success rates significantly. These HSCs showed favorable biocompatibility and antimicrobial properties in partial pulpotomy of permanent teeth in long-term follow-up, with no statistical differences between clinical factors.

scholarly journals Comparison of Short- and Long-Term Prognosis between ST-Elevation and Non-ST-Elevation Myocardial Infarction

2021 ◽  
Vol 10 (2) ◽  
pp. 180
Author(s):  
Frédéric Bouisset ◽  
Jean-Bernard Ruidavets ◽  
Jean Dallongeville ◽  
Marie Moitry ◽  
Michele Montaye ◽  
...  
Keyword(s):  
Myocardial Infarction ◽  
Mortality Rate ◽  
Confounding Factors ◽  
Coronary Syndrome ◽  
Short And Long Term ◽  
St Elevation ◽  
Probability Of Death ◽  
Long Term Prognosis

Background: Available data comparing long-term prognosis according to the type of acute coronary syndrome (ACS) are scarce, contradictory, and outdated. Our aim was to compare short- and long-term mortality in ST-elevated (STEMI) and non-ST-elevated myocardial infarction (non-STEMI) ACS patients. Methods: Patients presenting with an inaugural ACS during the year 2006 and living in one of the three areas in France covered by the Monitoring of Trends and Determinants in Cardiovascular Disease (MONICA) registry were included. Results: A total of 1822 patients with a first ACS—1121 (61.5%) STEMI and 701 (38.5%) non-STEMI—were included in the study. At the 28-day follow-up, the mortality rates were 6.7% and 4.7% (p = 0.09) for STEMI and non-STEMI patients, respectively, and after adjustment of potential confounding factors, the 28-day probability of death was significantly lower for non-STEMI ACS patients (Odds Ratio = 0.58 (0.36–0.94), p = 0.03). At the 10-year follow-up, the death rates were 19.6% and 22.8% (p = 0.11) for STEMI and non-STEMI patients, respectively, and after adjustment of potential confounding factors, the 10-year probability of death did not significantly differ between non-STEMI and STEMI events (OR = 1.07 (0.83–1.38), p = 0.59). Over the first year, the mortality rate was 7.2%; it then decreased and stabilized at 1.7% per year between the 2nd and 10th year following ACS. Conclusion: STEMI patients have a worse vital prognosis than non-STEMI patients within 28 days following ACS. However, at the 10-year follow-up, STEMI and non-STEMI patients have a similar vital prognosis. From the 2nd year onwards following the occurrence of a first ACS, the patients become stable coronary artery disease patients with an annual mortality rate in the 2% range, regardless of the type of ACS they initially present with.

Long-term impact of new-onset atrial fibrillation complicating acute myocardial infarction on heart failure: insights from the NOAFCAMI-SH registry

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
S.L Xu ◽  
J Luo ◽  
H.Q Li ◽  
Z.Q Li ◽  
B.X Liu ◽  
...  
Keyword(s):  
Myocardial Infarction ◽  
Heart Failure ◽  
Atrial Fibrillation ◽  
Acute Myocardial Infarction ◽  
Natural Science ◽  
Funding Source ◽  
Onset Atrial Fibrillation ◽  
New Onset

Abstract Background New-onset atrial fibrillation (NOAF) complicating acute myocardial infarction (AMI) has been associated with poor survival, but the clinical implication of NOAF on subsequent heart failure (HF) is still not well studied. We aimed to investigate the relationship between NOAF following AMI and HF hospitalization. Methods This retrospective cohort study was conducted between February 2014 and March 2018, using data from the New-Onset Atrial Fibrillation Complicating Acute Myocardial Infarction in ShangHai registry, where all participants did not have a documented AF history. Patients with AMI who discharged alive and had complete echocardiography and follow-up data were analyzed. The primary outcome was HF hospitalization, which was defined as a minimum of an overnight hospital stay of a participant who presented with symptoms and signs of HF or received intravenous diuretics. Results A total of 2075 patients were included, of whom 228 developed NOAF during the index AMI hospitalization. During up to 5 years of follow-up (median: 2.7 years), 205 patients (9.9%) experienced HF hospitalization and 220 patients (10.6%) died. The incidence rate of HF hospitalization among patients with NOAF was 18.4% per year compared with 2.8% per year for those with sinus rhythm. After adjustment for confounders, NOAF was significantly associated with HF hospitalization (hazard ratio [HR]: 3.14, 95% confidence interval [CI]: 2.30–4.28; p<0.001). Consistent result was observed after accounting for the competing risk of all-cause death (subdistribution HR: 3.06, 95% CI: 2.18–4.30; p<0.001) or performing a propensity score adjusted multivariable model (HR: 3.28, 95% CI: 2.39–4.50; p<0.001). Furthermore, the risk of HF hospitalization was significantly higher in patients with persistent NOAF (HR: 5.81; 95% CI: 3.59–9.41) compared with that in those with transient NOAF (HR: 2.61; 95% CI: 1.84–3.70; p interaction = 0.008). Conclusion NOAF complicating AMI is strongly associated with an increased long-term risk of heart. Cumulative incidence of outcome Funding Acknowledgement Type of funding source: Public grant(s) – National budget only. Main funding source(s): 1. National Natural Science Foundation of China, 2. Natural Science Foundation of Shanghai

Long-term effects of an intensive prevention program (IPP) after acute myocardial infarction – the IPP Follow-up and Prevention Boost Trial

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
H Wienbergen ◽  
A Fach ◽  
S Meyer ◽  
J Schmucker ◽  
R Osteresch ◽  
...  
Keyword(s):  
Risk Factors ◽  
Myocardial Infarction ◽  
Risk Factor ◽  
Prevention Program ◽  
Study Endpoint ◽  
Funding Source ◽  
Risk Factor Control ◽  
One Year

Abstract Background The effects of an intensive prevention program (IPP) for 12 months following 3-week rehabilitation after myocardial infarction (MI) have been proven by the randomized IPP trial. The present study investigates if the effects of IPP persist one year after termination of the program and if a reintervention after >24 months (“prevention boost”) is effective. Methods In the IPP trial patients were recruited during hospitalization for acute MI and randomly assigned to IPP versus usual care (UC) one month after discharge (after 3-week rehabilitation). IPP was coordinated by non-physician prevention assistants and included intensive group education sessions, telephone calls, telemetric and clinical control of risk factors. Primary study endpoint was the IPP Prevention Score, a sum score evaluating six major risk factors. The score ranges from 0 to 15 points, with a score of 15 points indicating best risk factor control. In the present study the effects of IPP were investigated after 24 months – one year after termination of the program. Thereafter, patients of the IPP study arm with at least one insufficiently controlled risk factor were randomly assigned to a 2-months reintervention (“prevention boost”) vs. no reintervention. Results At long-term follow-up after 24 months, 129 patients of the IPP study arm were compared to 136 patients of the UC study arm. IPP was associated with a significantly better risk factor control compared to UC at 24 months (IPP Prevention Score 10.9±2.3 points in the IPP group vs. 9.4±2.3 points in the UC group, p<0.01). However, in the IPP group a decrease of risk factor control was observed at the 24-months visit compared to the 12-months visit at the end of the prevention program (IPP Prevention Score 10.9±2.3 points at 24 months vs. 11.6±2.2 points at 12 months, p<0.05, Figure 1). A 2-months reintervention (“prevention boost”) was effective to improve risk factor control during long-term course: IPP Prevention Score increased from 10.5±2.1 points to 10.7±1.9 points in the reintervention group, while it decreased from 10.5±2.1 points to 9.7±2.1 points in the group without reintervention (p<0.05 between the groups, Figure 1). Conclusions IPP was associated with a better risk factor control compared to UC during 24 months; however, a deterioration of risk factors after termination of IPP suggests that even a 12-months prevention program is not long enough. The effects of a short reintervention after >24 months (“prevention boost”) indicate the need for prevention concepts that are based on repetitive personal contacts during long-term course after coronary events. Figure 1 Funding Acknowledgement Type of funding source: Foundation. Main funding source(s): Stiftung Bremer Herzen (Bremen Heart Foundation)

Sign in / Sign up

Export Citation Format

Share Document