Prognosis Of Failure Research Articles

Increasing the class of foundational medication for heart failure is associated with improved prognosis in hospitalized patients with heart failure with reduced or mildly reduced ejection fraction

Abstract Aim To clarify the association between changes in the number of foundational medications for heart failure (FMHF) during hospitalization for worsening heart failure and post-discharge prognosis. Methods and results We retrospectively analyzed a combined dataset of three large-scale registries of hospitalized patients with heart failure in Japan (NARA-HF, WET-HF, and REALITY-AHF) and included patients already diagnosed with heart failure with reduced or mildly reduced left ventricular ejection fraction (HFr/mrEF) before admission. Patients were stratified by changes in the number of prescribed FMHF classes, namely angiotensin-converting enzyme inhibitors or angiotensin receptor blockers, beta blockers, and mineralocorticoid receptor blockers, from admission to discharge. The primary endpoint was defined as the combined endpoint of heart failure rehospitalization and all-cause death within 1-year of discharge. The cohort consisted of 1,113 patients, and 482 combined endpoints were observed. In total, 413 (37.1%) patients were on increased FMHF (increased group), 607 (54.5%) remained unchanged (unchanged group), and 93 (8.4%) had a decreased number of FMHF (decreased group) at discharge compared to the time of admission. In multivariable analysis, the increased group was associated with a significantly lower incidence of the primary endpoint compared with the unchanged group (hazard ratio 0.56, 95% confidence interval 0.45–0.60; P<0.001) and decreased group (hazard ratio 0.58, 95% confidence interval 0.40–0.84; P=0.004). Conclusion Increasing the number of FMHF cases during heart failure hospitalization is associated with a better prognosis in patients with HFr/mrEF. Funding Acknowledgement Type of funding sources: Foundation. Main funding source(s): REALITY registry was funded by the Cardiovascular Research Fund of Japan.WET-HF registry was supported by a Grant-in-Aid for Young Scientists (Y.S. JSPS KAKENHI, 18K15860).

SMALL VESSELS, BIG PROBLEMS: MICROSCOPIC POLYANGIITIS PRESENTING AS DIFFUSE ALVEOLAR HEMORRHAGE

SMALL VESSELS, BIG PROBLEMS: MICROSCOPIC POLYANGIITIS PRESENTING AS DIFFUSE ALVEOLAR HEMORRHAGE

Machine Learning Technics for Remaining useful Life Prediction using Diagnosis Data: a Case Study of a Jaw Crusher

Predictive maintenance currently involves digital transformation with all the technologies developed to serve the latter. This maintenance strategy is believed to be an efficient solution to end late/early intervention issues. It is for this reason that machine health state monitoring by Remaining Useful Life prognosis is very crucial. However, in the literature, most studies focus on failure diagnosis more than the system's Remaining Useful Life. In addition, to prepare models to serve the prognosis, the use of actual machinery data is critical to assure the later scalability of the application. The literature about predictive maintenance has often evaluated data-driven approaches with machine learning techniques processing simulated Data rather than real ones. To tackle this problem, the authors propose a continuity of previous work treating a jaw crusher default diagnosis in the context of the ore mining industry. The RUL of the crusher components is estimated upon completion of the fault diagnosis data. Smart sensors Data have been preprocessed to serve the evaluation of four regression machine learning models: Bayesian Linear Regression, Poisson Regression, Neural Network Regression, and Random Forest. Poisson regression and Neural Network required data normalization in this case study to improve their performance. Linear regression methods proved their inability to forecast the machine degradation state, while the bagging ensemble method, Random Forest, was able to track the actual values. This paper aims to enhance the Prognosis and Health Management of the machine while contributing to the literature enhancement on failure prognosis using real industrial data. Keywords— Data-driven approach, Industry 4.0, Machine learning, Predictive Maintenance, RUL prognosis, Smart sensors.

Stochastic Failure Prognosis of Discrete Event Systems

This article studies the prognosis of failure, i.e., its prediction prior to its occurrence, in stochastic discrete event systems. Prior work has focused on the definition and offline verification of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$m$</tex-math></inline-formula> -steps stochastic-prognosability, or <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$S_m$</tex-math></inline-formula> -prognosability, which allows the prediction of a fault at least <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$m$</tex-math></inline-formula> -steps in advance. This article complements the existing work by proposing an algorithm for the computation of online failure prognoser. The proposed algorithm reduces the condition for issuing an affirmative prognostic decision to verification condition of a safety property of a Markov chain. We discuss how such a verification condition can be computed using a finitely terminating algorithm.

Decentralized Failure Prognosis of Stochastic Discrete-Event Systems and a Test Algorithm

Recently, the study of fault diagnosis and prognosis of discrete-event systems (DESs) has received considerable attention. This article aims to investigate the decentralized fault prognosis of stochastic DESs (SDESs). The notion of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$m$ </tex-math></inline-formula> -step stochastic-coprognosability, called <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$S_{m} $ </tex-math></inline-formula> -coprognosability, is formalized to capture the capability of stochastic systems to predict a fault at least <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$m$ </tex-math></inline-formula> steps in advance under the decentralized framework. The verifier is constructed from the stochastic decentralized system, in which <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$n$ </tex-math></inline-formula> local prognosers are deployed to send the local prognostic decisions to a coordinator for calculating the final prognostic decision. In particular, a necessary and sufficient condition of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$S_{m}$ </tex-math></inline-formula> -coprognosability of stochastic systems is derived, and an algorithm for testing <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$S_{m} $ </tex-math></inline-formula> -coprognosability is given, which is polynomial to the number of states and events but exponential to the number of local sites. Furthermore, the maximum number of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$m$ </tex-math></inline-formula> for making the given SDES to be <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$S_{m} $ </tex-math></inline-formula> -coprognosable is discussed. Note to Practitioners—This article extends the fault prognosis methods of SDESs from centralized framework to decentralized framework, such that for many technologically complex systems whose information collection is scattered in physically separated different sites, every local site makes decision based on information collected by own sensors, without communicating with other local sites, which is more appropriate than the centralized method.

In-hospital mortality rate and predictors of 30-day readmission in patients with iron deficiency anemia and diastolic heart failure: A cross-sectional study

Introduction: There is currently strong evidence of the adverse effects of anemia on the prognosis of heart failure with reduced ejection fraction. Unfortunately, the data on the effects of anemia on a large sample of patients with diastolic heart failure (DHF) is lacking. In this study, we aimed to evaluate the effect of iron deficiency anemia on DHF readmission rates and its corresponding causes and burdens on the healthcare system. Methods: We utilized 2018 Nationwide readmission data and included patients aged ≥18 years with ICD-10 CM code indicating acute or acute chronic diastolic heart failure and iron deficiency anemia was included in the study. The primary outcome is 30-day readmission rates. Secondary outcomes were mortality rates, common causes of readmission, and healthcare utilization. Independent predictors for readmission were identified using cox regression analysis. Results: The total number of admissions in our study was 795,777. The mean age was 74.4 years (SD=13.7), and 63.54% were females. The 30-day readmission rate in patients with diastolic heart failure and iron deficiency anemia was 18.32 % vs. 16.01% in patients without anemia. The mortality rate at index admission and readmission was 3.62 % (2601) and 5.82 % (737), respectively. The most common cause of readmission was hypertensive heart and kidney disease with heart failure (17.74%). The independent predictors of readmission were age&lt;85 years, household income &lt;59000$/per year, Medicare and Medicaid insurance, higher Elixhauser comorbidities score, longer Length of stay during the index admission, discharge to a nursing home, hospital located in a large metropolitan area. The financial burden on healthcare for all the readmission was $837 million for 2018. Conclusion: The 30-day readmission rate in patients with diastolic heart failure and iron deficiency anemia is 18.32% in the year 2018. The mortality rate increased from 3.62 % to 5.82 % with readmission. The financial burden for readmission during that year was $837 million. Future studies are warranted to treat iron deficiency anemia to prevent readmissions in diastolic heart failure.

Trimethyllysine, a trimethylamine N-oxide precursor, predicts the presence, severity, and prognosis of heart failure

Background and aimsIntestinal flora metabolites are associated with cardiovascular (CV) diseases including heart failure (HF). The carnitine precursor trimethyllysine (TML), which participates in the generation of the atherogenic-related metabolite trimethylamine N-oxide (TMAO), was found to be related to poor prognosis in patients with CV diseases. The aim of the present study was to examine the relationship between TML and stable chronic HF.Methods and resultsIn total, 956 subjects including 471 stable chronic HF and 485 non-HF patients were enrolled in the present cohort study and subjects with stable HF were followed up for 2.0 ± 1.1 years. Serum levels of TML and TMAO were measured by liquid chromatography mass spectrometry in tandem. TML levels were significantly elevated in patients with HF compared with non-HF patients and were positively correlated with N-terminal pro-brain natriuretic peptide (NTproBNP) levels (r = 0.448, P < 0.001). TML was associated with the presence of HF after adjusting for age, sex, complications, traditional clinical factors, and TMAO (tertile 3 (T3), adjusted odds ratio (OR) 1.93, 95% confidence interval (CI) 1.19–3.13, and P = 0.007). In patients with HF, increased TML levels were associated with a composite endpoint of CV death and HF hospitalization during follow-up (T3, adjusted hazard ratio (HR) 1.93, 95% CI 1.27–2.93, and P = 0.002). Increased TML levels indicated a higher risk of CV death, re-hospitalization, and all-cause mortality.ConclusionSerum TML levels were associated with the presence and severity of HF in all subjects. High levels of TML can indicate complications and poor prognosis in HF patients.

Molecular imaging of fibroblast activity in pressure overload heart failure using [68Ga]Ga-FAPI-04 PET/CT.

We aimed to evaluate whether [68Ga]Ga-FAPI-04 PET/CT could characterize the early stages of cardiac fibrosis in pressure overload heart failure. Sprague-Dawley rats underwent abdominal aortic constriction (AAC) (n = 12) and sham surgery (n = 10). All rats were scanned with [68Ga]Ga-FAPI-04 PET/CT at 2, 4, and 8weeks after surgery. The expression of fibroblast activation protein (FAP) in the myocardium was detected by immunohistochemistry. [68Ga]Ga-FAPI-04 PET signal and FAP expression were compared between two groups. Compared with the sham group, the AAC group presented with decreased ejection fraction (EF) and fractional shortening (FS) and increased left ventricular internal dimensions in diastole (LVIDd) and systole (LVIDs) at 4 and 8weeks (all p < 0.01). The AAC group showed higher [68Ga]Ga-FAPI-04 accumulation in the heart than the sham group at 2, 4, and 8weeks, and FAPI increased significantly from 2 to 8weeks (all p < 0.001). Immunohistochemistry confirmed the higher density of the FAP+ area in the AAC group. The intensity of the [68Ga]Ga-FAPI-04 correlated with the density of the FAP+ area (p < 0.001). The expression of the [68Ga]Ga-FAPI-04 at 4weeks correlated with the deterioration of cardiac function at 8weeks (EF: R = - 0.87; FS: R = - 0.72; LVIDd: R = 0.77; LVIDs: R = 0.79; all p < 0.001). The AAC group also showed an increased [68Ga]Ga-FAPI-04 signal in the liver, peaking at 4weeks and then declining. Cardiac and liver PET signals correlated at 4weeks in the AAC group (R = 0.69, p = 0.0010), suggesting an early fibrotic link between organs. A combination of the [68Ga]Ga-FAPI-04 intensity in the heart and liver at 4weeks better predicted the deterioration of cardiac function at 8weeks. The activated fibroblasts in the heart and liver after pressure overload can be monitored by [68Ga]Ga-FAPI-04 PET/CT, which reveals an early fibrotic link in cardio-liver interactions and could better predict nonischemic heart failure prognosis.

Critical care hepatology: definitions, incidence, prognosis and role of liver failure in critically ill patients.

Organ dysfunction or overt failure is a commonplace event in the critically ill affecting up to 70% of patients during their stay in the ICU. The outcome depends on the resolution of impaired organ function, while a domino-like deterioration of organs other than the primarily affected ones paves the way for increased mortality. “Acute Liver Failure” was defined in the 1970s as a rare and potentially reversible severe liver injury in the absence of prior liver disease with hepatic encephalopathy occurring within 8 weeks. Dysfunction of the liver in general reflects a critical event in “Multiple Organ Dysfunction Syndrome” due to immunologic, regulatory and metabolic functions of liver parenchymal and non-parenchymal cells. Dysregulation of the inflammatory response, persistent microcirculatory (hypoxic) impairment or drug-induced liver injury are leading problems that result in “secondary liver failure,” i.e., acquired liver injury without underlying liver disease or deterioration of preexisting (chronic) liver disease (“Acute-on-Chronic Liver Failure”). Conventional laboratory markers, such as transaminases or bilirubin, are limited to provide insight into the complex facets of metabolic and immunologic liver dysfunction. Furthermore, inhomogeneous definitions of these entities lead to widely ranging estimates of incidence. In the present work, we review the different definitions to improve the understanding of liver dysfunction as a perpetrator (and therapeutic target) of multiple organ dysfunction syndrome in critical care.Graphic

A Trade-Off Analysis between Sensor Quality and Data Intervals for Prognostics Performance.

In safety-critical systems such as industrial plants or aircraft, failure occurs inevitably during operation, and it is important to prevent it in order to maintain high availability. To reduce this risk, a lot of efforts are directed from developing sensing technologies to failure prognosis algorithms to enable predictive maintenance. The success of effective and reliable predictive maintenance not only relies on robust prognosis algorithms but also on the selection of sensors or data acquisition strategy. However, there are not many in-depth studies on a trade-off between sensor quality and data storage in the view of prognosis performance. The information about (1) how often data should be measured and (2) how good sensor quality should be for reliable failure prediction can be highly impactful for practitioners. In this paper, the authors evaluate the efficacy of the two factors in terms of remaining useful life (RUL) prediction accuracy and its uncertainty. In addition, since knowing true degradation information is almost impossible in practice, the authors validated the use of the prognosis metric without requiring the true degradation information. A numerical case study is conducted to identify the relationship between sensor quality and data storage. Then, real bearing run-to-failure (RTF) datasets acquired from accelerometer (contact type) and microphone (non-contact type) sensors are evaluated based on the prognosis performance metric and compared in terms of the sensors’ cost-effectiveness for predictive maintenance.

The Acute-Phase Ambulation Program Improves Clinical Outcome for Acute Heart Failure.

It remains unclear whether the acute-phase ambulation program (AAP) improves the prognosis of heart failure (HF) patients. We examined the association between the initiation of AAP and the prognosis of patients with worsening HF. We enrolled 560 consecutive patients admitted due to worsening HF from March 2019 to April 2021. Our hospital introduced AAP in May 2020, but we did not perform AAP until April 2020. We retrospectively compared cardiac events within 180 days after discharge between patients admitted before April 2020 (conventional group) and after May 2020 (AAP group). Primary endpoints were all-cause mortality and readmission for worsening HF. The Kaplan–Meier survival curves showed a significantly lower event rate in the AAP group in HF readmission or the primary endpoint (p = 0.020 and p = 0.014). The occurrence of the primary endpoint was associated with age, history of HF, systolic blood pressure, medications including renin–angiotensin system inhibitors or angiotensin receptor blocker, hemoglobin, NT-proBNP, and AAP participation. After adjusting for these parameters and sex, participation in AAP was an independent factor associated with a reduced risk of primary endpoint occurrence (hazard ratio of 0.62 (0.41–0.95), p = 0.028). The AAP for patients with acute HF might lead to improved short-term prognosis and should be considered for implementation.

Rare clinical phenotype of filaminopathy presenting as restrictive cardiomyopathy and myopathy in childhood

BackgroundFLNC is one of the few genes associated with all types of cardiomyopathies, but it also underlies neuromuscular phenotype. The combination of concomitant neuromuscular and cardiac involvement is not often observed in filaminopathies and the impact of this on the disease prognosis has hitherto not been analyzed.ResultsHere we provide a detailed clinical, genetic, and structural prediction analysis of distinct FLNC-associated phenotypes based on twelve pediatric cases. They include early-onset restrictive cardiomyopathy (RCM) in association with congenital myopathy. In all patients the initial diagnosis was established during the first year of life and in five out of twelve (41.7%) patients the first symptoms were observed at birth. RCM was present in all patients, often in combination with septal defects. No ventricular arrhythmias were noted in any of the patients presented here. Myopathy was confirmed by neurological examination, electromyography, and morphological studies. Arthrogryposes was diagnosed in six patients and remained clinically meaningful with increasing age in three of them. One patient underwent successful heart transplantation at the age of 18 years and two patients are currently included in the waiting list for heart transplantation. Two died due to congestive heart failure. One patient had ICD instally as primary prevention of SCD. In ten out of twelve patients the disease was associated with missense variants and only in two cases loss of function variants were detected. In half of the described cases, an amino acid substitution A1186V, altering the structure of IgFLNc10, was found.ConclusionsThe present description of twelve cases of early-onset restrictive cardiomyopathy with congenital myopathy and FLNC mutation, underlines a distinct unique phenotype that can be suggested as a separate clinical form of filaminopathies. Amino acid substitution A1186V, which was observed in half of the cases, defines a mutational hotspot for the reported combination of myopathy and cardiomyopathy. Several independent molecular mechanisms of FLNC mutations linked to filamin structure and function can explain the broad spectrum of FLNC-associated phenotypes. Early disease presentation and unfavorable prognosis of heart failure demanding heart transplantation make awareness of this clinical form of filaminopathy of great clinical importance.

Clinical study on the treatment of primary trigeminal neuralgia by robot-assisted percutaneous balloon compression.

C-arm-guided percutaneous puncture balloon compression alone has risk factors of puncture failure, complications, and poor prognosis. Robot-assisted PBC can effectively increase the one-time puncture success rate and improve the safety of the procedure. However, evidence on the superiority of robot-assisted PBC over C-arm-guided PBC alone remains relatively limited. Retrospective analysis The clinical data of 60 patients with trigeminal neuralgia aged 60 years or older in the Department of Neurosurgery of the Fourth Hospital of Harbin Medical University from January 2021 to October 2021. There were 29 males and 31 females, and the patients' ages ranged from 60 to 79 years, with an average of 71.63 ± 5.12 years. Two groups were divided according to the surgical method, the C-arm guidance-only group (30 cases, n = 30) and the robot-assisted group (30 cases, n = 30). The success rate of first puncture, total operation time, number of "pear-shaped" balloons, number of C-arm x-ray scans, and immediate postoperative relief rate were recorded in both groups, and follow-up was performed to evaluate the postoperative results and complications. The overall evaluation of postoperative results and complications was performed. Intraoperative balloon compression was successfully completed in all 60 patients, and the first puncture success rate was higher in the robot-assisted group than in the simple C-arm group, with a significant difference between the two groups (P < 0.001). In terms of intraoperative balloon morphology, the number of "pear-shaped" balloons was higher in the PBC than in the C-arm-only PBC group, with a significant difference between the two groups (P < 0.005). The degree of immediate postoperative remission in the robotic group was 0 VAS score, which was not statistically significant in both groups (P > 0.05). By the final follow-up, the mean VAS score of the robot-assisted group was lower than that of the simple C-arm group, and both were statistically significant (P < 0.05); complications of masticatory muscle weakness or abnormal facial sensation occurred in both groups after surgery, but the number of cases in the robot-assisted group was less than that of the simple C-arm group. Robot-assisted PBC is better than PBC with a C-arm x-ray machine in terms of first puncture success rate, number of intraoperative balloon "pear-shaped" cases, number of C-arm x-ray scans and short-term efficacy.

The effect of serum IL-2 levels on the prognosis of primary biliary cholangitis-related liver failure and the preliminary exploration of its mechanism.

BackgroundIn primary biliary cholangitis (PBC), the levels of serum IL-2 were involved in liver inflammation and immune changes. This study aimed to investigate the prognostic significance of serum IL-2 combined with total bilirubin (TBIL) in liver failure and cytokine changes during the disease.MethodsA total of 160 PBC patients treated with UDCA were included. Parameters at admission were collected, and the COX regression model was used to predict independent risk factors associated with PBC disease progression. We identified the optimal cut-off values and prognosis effects of serum IL-2 and TBIL based on the time-dependent receiver operating characteristic (ROC) curve. We also analyzed the incidence of liver failure with Kaplan-Meier survival analysis. In addition, the changes of cytokines (mainly IL-2) in liver tissues and blood samples from 11 patients with end-stage PBC liver failure and five healthy controls were examined.ResultsAge, IL-2, ALB, γ-GT, ALP, TBIL, Hb, TBA, WBC, and PLT, as well as anti-Sp100, were found to be independent risk factors in PBC patients with liver failure. Patients with decreased serum IL-2 levels and increased TBIL levels have a significantly higher incidence of liver failure and a worse prognosis. Patients with advanced PBC liver failure after liver transplantation exhibited a significant decrease in levels of serum IL-2 and a relatively immunosuppressed status.ConclusionsThe combination of serum IL-2 and TBIL can be a predictor of the progression of liver failure in patients with primary biliary cholangitis, and it is likely to be related to the expression of GM-CSF and G-CSF.

Worst pattern of invasion in oral squamous cell carcinoma is an independent prognostic factor.

IntroductionBiologic aggressiveness of OSCC (Oral Cavity Squamous Cell Carcinoma), has intrigued research in various prognosticating histopathological markers over past few decades. DOI (Depth of Invasion) is one such histopathological factor which affects outcomes and was included in the AJCC 8th edition TNM staging. Pattern of Invasion (POI) has been widely reported as an adverse prognostic factor associated with higher locoregional failure and poor prognosis. However, these factors are not utilized for treatment decision making and for outcome assessment.Materials and methodsThis is a retrospective analysis of 320 patients with OSCC who underwent treatment, from October 2018–February 2020. Clinic demographic details were extracted from electronic medical records. Univariate and multivariate analysis was done for the parameters. WPOI (Worst Pattern of Invasion) was correlated with all histopathological prognostic factors. Survival analysis was done using Kaplan Meier for WPOI type's I–V. DFS (Disease free Survival) was evaluated for different grades of WPOI.ResultsWe analyzed the results comparing, early and advanced T (Tumor) stages, cohesive WPOI I-III, non-cohesive WPOI IV-V. Univariate analysis showed a significant association of T-stage (p = 0.001), N (Nodal) -stage (p = 0.002), DOI (p = 0.008), PNI (Peri-neural invasion) (0.001) and Tumor differentiation Grade (p = 0.001). On multivariate analysis, non-cohesive WPOI (IV & V) showed significant association with grade, PNI, DOI (0.002, 0.033 & 0.033 respectively). Non-cohesive WPOI had significantly higher locoregional failures and short DFS.ConclusionPresence of invasive WPOI is associated with advanced T stage, poor differentiation, PNI, greater depth of invasion, and higher chances of nodal metastasis. WPOI is associated with poor DFS, treatment intensification in early stage disease with WPOI type IV & V may improve survival.

Weibull recurrent neural networks for failure prognosis using histogram data

Weibull time-to-event recurrent neural networks (WTTE-RNN) is a simple and versatile prognosis algorithm that works by optimising a Weibull survival function using a recurrent neural network. It offers the combined benefits of the sequential nature of the recurrent neural network, and the ability of the Weibull loss function to incorporate censored data. The goal of this paper is to present the first industrial use case of WTTE-RNN for prognosis. Prognosis of turbocharger conditions in a fleet of heavy-duty trucks is presented here, where the condition data used in the case study were recorded as a time series of sparsely sampled histograms. The experiments include comparison of the prediction models trained using data from the entire fleet of trucks vs data from clustered sub-fleets, where it is concluded that clustering is only beneficial as long as the training dataset is large enough for the model to not overfit. Moreover, the censored data from assets that did not fail are also shown to be incorporated while optimising the Weibull loss function and improve prediction performance. Overall, this paper concludes that WTTE-RNN-based failure predictions enable predictive maintenance policies, which are enhanced by identifying the sub-fleets of similar trucks.

Predicting prognosis of heart failure using common malnutrition assessment tools: A systematic review and meta-analysis.

COUNT score, PNI score, and GNRI scores are associated with cardiovascular events. This review identifies the most accurate malnutrition assessment tools based on these scores in predicting mortality and readmission outcomes in HF patients. PubMed via MEDLINE, EMBASE were searched to identify studies assessing malnutrition using CONUT, PNI and GNRI. A meta-analysis was carried out to pool the hazard ratios on mortality and readmission rates. The methodological quality was assessed using the Newcastle-Ottawa Scale. The mortality in HF patients with malnutrition assessed by CONUT showed pooled HR of 1.23. HF patients with all severe, moderate, and mild risk of malnutrition showed mortality with HR 3.56, 2.71 and 1.57 respectively. For malnutrition assessed with GNRI, HF patients with all severe, moderate, and mild risk of malnutrition showed mortality with HR 4.17, 2.73 and 1.73 respectively. No significance difference in association of CONUT score with pooled HR of readmission rate was observed HR 0.99. With PNI, HF patients with all severe and moderate risk of malnutrition showed mortality with HR 2.14 and HR 1.68 respectively, although they failed to achieve significance. CONUT and GNRI are the superior prognostic indicator than PNI in prediction of mortality associated with risk of malnutrition.

332.4: Microvascular Injury With Macrophage, Neutrophil, And Hla-dr Positive Inflammatory Infiltrate, either in dsa Positive or Negative abmr, Determines the Prognosis in Renal Allografts

Introduction: Antibody-mediated rejection (ABMR) has well-defined histomorphological lesions, like linear C4d staining or microvascular inflammation [(g + ptc) ≥ 2] in peritubular capillaries (PTCs). Although these histologic features of ABMR (ABMRh) are usually compatible with donor-specific antibodies (DSA), it is demonstrated that recipients can develop ABMRh in the absence of DSAs. Indeed, DSA can not be found in 40-60% of patients with marked microvascular inflammation (MVI). We aimed to investigate the relationship between PTC macrophage (M), neutrophil, and HLA-DR positive cell infiltration with variable clinical presentations of ABMR. Methods: A total of 125 patients with acute ABMR were categorized into four groups; Group 1: DSA (+) ABMR, Group 2: DSA (-) ABMR, Group 3: DSA (+) mixed rejection (ABMR+vascular rejection), and Group 4: DSA (-) mixed rejection. The degree of the glomerular and PTC macrophage (CD68+), neutrophil, and HLA-DR positive cells was graded. The loss of HLA-DR expression in PTC endothelium was accepted as PTC destruction. The follow-up biopsies were evaluated for the development of diffuse interstitial fibrosis (IF) and transplant glomerulopathy (TG). Results: The type of ABMR showed a significant correlation with PTC C4d expression, the presence of TMA, PTC destruction, microvascular (PTC and glomerular) macrophage, neutrophil, and DR+ cell infiltration (p<0.01 for all). Group 3 showed the highest microvascular inflammation, PTC destruction, C4d expression, and TMA. Groups 4, 1, and 2 followed Group 3, respectively, and Group 2 showed the best outcome. Also, patients in Group 3 developed the highest and earliest IF and TG development during follow-up (p<0.01). Similarly, Groups 4, 1, and 2 followed Group 3 regarding the development of IF and TG development. PTC C4d staining intensity significantly correlated with PTC destruction and DSA positivity (p<0.001). Overall 5-year graft survival was 86%, 51%, 45%, and 26% for Groups 2, 1, 4, and 3, respectively (p<0.001). Overall 5-year graft survival was 87%, 54%, and 20% for patients with grades 1, 2, and 3 PTC destruction, respectively (p<0.001). Additionally, overall 5-year survival was 100%, 81%, and 21% for grades 1, 2, and 3 C4d depositions in PTCs, respectively (P<0.001). Conclusion: ABMRh comprising characteristic histologic findings without detectable DSA represent a distinct phenotype with superior renal allograft survival than ABMRh with positive DSA. Additionally, PTC C4d deposition and the resulting PTC destruction were shown to significantly indicate graft failure and poor prognosis independent of the DSA positivity. Therefore, we concluded that ABMR should be divided into different subgroups for treatment, considering the presence of DSA and vascular rejection.

Validation of the MEDIA echo score for the prognosis of heart failure with preserved ejection fraction.

There is currently no widely used prognostic score in heart failure(HF) with preserved ejection fraction (HFpEF). The MEDIA echo score, including four variables (pulmonary arterial systolic pressure > 40mmHg, inferior vena cava collapsibility index < 50%, average E/e' > 9, and lateral mitral annular s' < 7cm/s), has been proposed as a useful risk stratification tool. This study aimed at further validating the MEDIA echo score in both hospitalised and ambulatory HFpEF patients. The MEDIA echo score ranges from 0 to 4 (each criterion scores 1 point). The associations between MEDIA echo score and cardiovascular outcomes were assessed in two independent HFpEF cohorts, namely patients hospitalised for worsening HFpEF (N = 242, mean age 78 ± 11), and stable ambulatory HFpEF patients (N = 76, mean age 65 ± 8). Using multivariable Cox models, in the worsening HFpEF cohort, patients with a MEDIA echo score of 3-4 displayed a significant increased risk of death (HR 2.10, 95%CI 1.02-4.33, P = 0.043, score 0-1 as reference). In the ambulatory HFpEF cohort, patients with a MEDIA echo score of 2 had a significantly higher risk of death or HF hospitalisation (HR 3.44, 95%CI 1.27-9.30, P = 0.015, score 0 as reference), driven by HF hospitalisation; in that cohort, adding the MEDIA echo score to the clinical model significantly improved reclassification for the combined endpoint (integrated discrimination improvement 6.2%, P = 0.006). The MEDIA echo score significantly predicted the outcome of HFpEF patients in both hospital and ambulatory settings; its use may help refine routine risk stratification on top of well-established prognosticators in stable HFpEF patients.

Practical management of frailty in older patients with heart failure: Statement from a panel of multidisciplinary experts on behalf the Heart Failure Working Group of the French Society of Cardiology and on behalf French Society of Geriatrics and Gerontology.

The heart failure (HF) prognosis in older patients remains poor with a high 5-years mortality rate more frequently attributed to noncardiovascular causes. The complex interplay between frailty and heart failure contribute to poor health outcomes of older adults with HF independently of ejection fraction. The aim of this position paper is to propose a practical management of frailty in older patients with heart failure. A panel of multidisciplinary experts on behalf the Heart Failure Working Group of the French Society of Cardiology and on behalf French Society of Geriatrics and Gerontology conducted a systematic literature search on the interlink between frailty and HF, met to propose an early frailty screening by non-geriatricians and to propose ways to implement management plan of frailty. Statements were agreed by expert consensus. Clinically relevant aspects of interlink between frailty and HF have been reported to identify the population eligible for screening and the most suitable screening test(s). The frailty screening program proposed focuses on frailty model defined by an accumulation of deficits including geriatric syndromes, comorbidities, for older patients with HF in different settings of care. The management plan of frailty includes optimization of HF pharmacological treatments and non-surgical device treatment as well as optimization of a global patient-centred biopsychosocial blended collaborative care pathway. The current manuscript provides practical recommendations on how to screen and optimize frailty management in older patients with heart failure.