Search

Abstract Handling missing data in clinical prognostic studies is an essential yet challenging task. This study aimed to provide a comprehensive assessment of the effectiveness and reliability of different machine learning (ML) imputation methods across various analytical perspectives. Specifically, it focused on three distinct classes of performance metrics used to evaluate ML imputation methods: post-imputation bias of regression estimates, post-imputation predictive accuracy, and substantive model-free metrics. As an illustration, we applied data from a real-world breast cancer survival study. This comprehensive approach aimed to provide a thorough assessment of the effectiveness and reliability of ML imputation methods across various analytical perspectives. A simulated dataset with 30% Missing At Random (MAR) values was used. A number of single imputation (SI) methods - specifically KNN, missMDA, CART, missForest, missRanger, missCforest - and multiple imputation (MI) methods - specifically miceCART and miceRF - were evaluated. The performance metrics used were Gower’s distance, estimation bias, empirical standard error, coverage rate, length of confidence interval, predictive accuracy, proportion of falsely classified (PFC), normalized root mean squared error (NRMSE), AUC, and C-index scores. The analysis revealed that in terms of Gower’s distance, CART and missForest were the most accurate, while missMDA and CART excelled for binary covariates; missForest and miceCART were superior for continuous covariates. When assessing bias and accuracy in regression estimates, miceCART and miceRF exhibited the least bias. Overall, the various imputation methods demonstrated greater efficiency than complete-case analysis (CCA), with MICE methods providing optimal confidence interval coverage. In terms of predictive accuracy for Cox models, missMDA and missForest had superior AUC and C-index scores. Despite offering better predictive accuracy, the study found that SI methods introduced more bias into the regression coefficients compared to MI methods. This study underlines the importance of selecting appropriate imputation methods based on study goals and data types in time-to-event research. The varying effectiveness of methods across the different performance metrics studied highlights the value of using advanced machine learning algorithms within a multiple imputation framework to enhance research integrity and the robustness of findings.

Abstract Background The excess mortality observed in Acute Myeloblastic Leukaemia (AML) patients, partly attributed to unequal access to curative treatments, could be linked to care pathways. Methods We included 1039 AML incident cases diagnosed between 2012–2016 from the 3 French blood cancer registries (3,625,400 inhabitants). We describe patients according to age, the medical entry unit and access to the specialised haematology unit (SHU) during follow‐up. Multivariate logistic regression model was done to determine the association between covariables and access to SHU. A total of 713 patients (69%) had access to SHU during care. Results The most common care pathway concerned referral from the general practitioner to SHU, n = 459(44%). The univariate analysis observed a downward trend for the most deprived patients. Patients who consulted in SHU were younger (66 years vs. 83, p

Background: Infective endocarditis (IE) is a serious condition which is difficult to diagnose and to treat, both medically and surgically. Objectives: The objective of this study was to evaluate the impact of the SARS-CoV-2 pandemic on the management of patients with IE. Methods: We conducted a single-centre retrospective study including patients hospitalized for IE during the pandemic (Group 2) compared with the same period the year before (Group 1). We compared clinical, laboratory, imagery, therapeutic, and patient outcomes between the two groups. Results: A total of 283 patients were managed for possible or definite IE (164 in Group 1 and 119 in Group 2). There were more intravenous drug-related IE patients in Group 2 (p = 0.009). There was no significant difference in surgery including intra-cardiac device extraction (p = 0.412) or time to surgery (p = 0.894). The one-year mortality was similar in both groups (16% versus 17.7%, p = 0.704). The recurrence rate was not significantly different between the two groups (5.9% in Group 2 versus 9.1% in Group 1, p = 0.311). Conclusions: The SARS-CoV-2 pandemic did not appear to have had a negative impact on the management of patients with IE. Maintenance of the activities of the endocarditis team within the referral centre probably contributed to this result. Nevertheless, the high proportion of intravenous drug-addicted patients in the pandemic cohort suggests that the SARS-CoV-2 pandemic had a major psychosocial impact.

Abstract Background Heart failure- (HF) and arrhythmia-related complications are the main causes of morbidity and mortality in patients with nonischemic dilated cardiomyopathy (NIDCM). Cardiovascular magnetic resonance (CMR) imaging is a noninvasive tool for risk stratification based on fibrosis assessment. Diffuse interstitial fibrosis in NIDCM may be a limitation for fibrosis assessment through late gadolinium enhancement (LGE), which might be overcome through quantitative T1 and extracellular volume (ECV) assessment. T1 and ECV prognostic value for arrhythmia-related events remain poorly investigated. We asked whether T1 and ECV have a prognostic value in NIDCM patients. Methods This prospective multicenter study analyzed 225 patients with NIDCM confirmed by CMR who were followed up for 2 years. CMR evaluation included LGE, native T1 mapping and ECV values. The primary endpoint was the occurrence of a major adverse cardiovascular event (MACE) which was divided in two groups: HF-related events and arrhythmia-related events. Optimal cutoffs for prediction of MACE occurrence were calculated for all CMR quantitative values. Results Fifty-eight patients (26%) developed a MACE during follow-up, 42 patients (19%) with HF-related events and 16 patients (7%) arrhythmia-related events. T1 Z-score (p = 0.008) and global ECV (p = 0.001) were associated with HF-related events occurrence, in addition to left ventricular ejection fraction (p 32.1% (optimal cutoff) remained the only CMR independent predictor of HF-related events occurrence (HR 2.15 [1.14–4.07], p = 0.018). In the arrhythmia-related events group, patients had increased native T1 Z-score and ECV values, with both T1 Z-score > 4.2 and ECV > 30.5% (optimal cutoffs) being independent predictors of arrhythmia-related events occurrence (respectively, HR 2.86 [1.06–7.68], p = 0.037 and HR 2.72 [1.01–7.36], p = 0.049). Conclusions ECV was the sole independent predictive factor for both HF- and arrhythmia-related events in NIDCM patients. Native T1 was also an independent predictor in arrhythmia-related events occurrence. The addition of ECV and more importantly native T1 in the decision-making algorithm may improve arrhythmia risk stratification in NIDCM patients. Trial registration NCT02352129. Registered 2nd February 2015—Retrospectively registered, https://clinicaltrials.gov/ct2/show/NCT02352129

Polysaccharide protein conjugate is usually prepared by electrostatic interactions or Maillard reaction. In this study, coconut protein concentrate (CPC)-pectin conjugate was synthesized by a combination between the electrostatic and early stage Maillard reaction. The objective was to evaluate the effect of CPC-pectin ratio, temperature, and pH on emulsion stability index (ESI) and emulsion activity index (EAI). Furthermore, the obtained conjugate was used to stabilize the red palm oil emulsion. The conjugate was prepared by mixing CPC and pectin solution, and dried in a cabinet dryer. Factors, such as CPC-pectin ratio (1:3, 1:2, 1:1, 2:1, 3:1), incubation temperature (50, 60, 70, 80, 90 °C), and pH (3; 3.5; 4; 4.5; 5) were evaluated. The result show that CPC contained 67.40% ± 0.93 protein. ESI and EAI of CPC was not detected. CPC-pectin ratio, temperature, and pH had a significant effect on ESI and EAI, except temperature was not significant effect on EAI. Early stage Maillard reaction was confirmed by FTIR analysis since the peak intensity of amida I increased and amida II decreased. The best CPC-pectin conjugate was found at CPC-pectin ratio of 1:2 (w/w), incubation temperature of 80 °C, and pH of 4. ESI, EAI, droplet size and zeta potential of red palm oil emulsion were 165.263 min; 72.314 m2/g; 553.4 nm and −45.5 mV, respectively. The emulsion droplets were uniform in size and equally dispersed. In summary, drying of conjugate on cabinet dryer induced early stage Maillard reaction and the conjugate can be used to stabilize red palm oil emulsion.

Selection of an appropriate hybridization method and use of molecular markers to study genetic purity of hybrids are important factors in crop improvement. In this study, our objective was to analyze two emasculation methods in finger millet and to present a strategy for the assessment of the genetic purity of F1 hybrids using molecular markers. Two parental lines of finger millet, PR 202 and IE 2606, were used for reciprocal crossing. Emasculation was performed with hot-water and hand methods; their efficiencies were compared. The hand method produced ~50-120 seeds per panicle and the hot-water method yielded ~30-90 seeds per panicle. The crossing efficiency was checked using molecular markers. The hot-water method was more efficient (52–80%) compared with the hand-emasculation method (16–40%). Simple sequence repeat (SSR), random amplified polymorphic DNA (RAPD) and inter simple sequence repeat (ISSR) markers were used to analyze the genetic variation in the parental lines. Twelve out of 28 RAPD markers, 4 out of 20 ISSR markers and 21 out of 101 SSR markers showed polymorphism between parental lines. The genetic purity was 16–80% based on RAPD and SSR markers. This study suggested that molecular markers can be utilized to compare the efficiency of emasculation methods and are highly useful for the identification of true hybrid seedlings in the early stages of growth. [ABSTRACT FROM AUTHOR]

Abstract Background In survival analysis, data can be modeled using either a multiplicative hazards regression model (such as the Cox model) or an additive hazards regression model (such as Lin’s or Aalen’s model). While several diagnostic tools are available to check the assumptions underpinning each type of model, there is no defined procedure to fit these models optimally. Moreover, the two types of models are rarely combined in survival analysis. Here, we propose a strategy for optimal fitting of multiplicative and additive hazards regression models in survival analysis. Methods This section details our proposed strategy for optimal fitting of multiplicative and additive hazards regression models, with a focus on the assumptions underpinning each type of model, the diagnostic tools used to check these assumptions, and the steps followed to fit the data. The proposed strategy draws on classical diagnostic tools (Schoenfeld and martingale residuals) and less common tools (pseudo-observations, martingale residual processes, and Arjas plots). Results The proposed strategy is applied to a dataset of patients with myocardial infarction (TRACE data frame). The effects of 5 covariates (age, sex, diabetes, ventricular fibrillation, and clinical heart failure) on the hazard of death are analyzed using multiplicative and additive hazards regression models. The proposed strategy is shown to fit the data optimally. Conclusions Survival analysis is improved by using multiplicative and additive hazards regression models together, but specific steps must be followed to fit the data optimally. By providing different measures of the same effect, our proposed strategy allows for better interpretation of the data.

Abstract Background In high-dimensional data analysis, the complexity of predictive models can be reduced by selecting the most relevant features, which is crucial to reduce data noise and increase model accuracy and interpretability. Thus, in the field of clinical decision making, only the most relevant features from a set of medical descriptors should be considered when determining whether a patient is healthy or not. This statistical approach known as feature selection can be performed through regression or classification, in a supervised or unsupervised manner. Several feature selection approaches using different mathematical concepts have been described in the literature. In the field of classification, a new approach has recently been proposed that uses the $$\gamma$$ γ -metric, an index measuring separability between different classes in heart rhythm characterization. The present study proposes a filter approach for feature selection in classification using this $$\gamma$$ γ -metric, and evaluates its application to automatic atrial fibrillation detection. Methods The stability and prediction performance of the $$\gamma$$ γ -metric feature selection approach was evaluated using the support vector machine model on two heart rhythm datasets, one extracted from the PhysioNet database and the other from the database of Marseille University Hospital Center, France (Timone Hospital). Both datasets contained electrocardiogram recordings grouped into two classes: normal sinus rhythm and atrial fibrillation. The performance of this feature selection approach was compared to that of three other approaches, with the first two based on the Random Forest technique and the other on receiver operating characteristic curve analysis. Results The $$\gamma$$ γ -metric approach showed satisfactory results, especially for models with a smaller number of features. For the training dataset, all prediction indicators were higher for our approach (accuracy greater than 99% for models with 5 to 17 features), as was stability (greater than 0.925 regardless of the number of features included in the model). For the validation dataset, the features selected with the $$\gamma$$ γ -metric approach differed from those selected with the other approaches; sensitivity was higher for our approach, but other indicators were similar. Conclusion This filter approach for feature selection in classification opens up new methodological avenues for atrial fibrillation detection using short electrocardiogram recordings.

As an increasing amount of data processing is done at the network edge, high energy costs and carbon emission of Edge Clouds (ECs) are becoming significant challenges. The placement of application components (e.g., in the form of containerized microservices) on ECs has an important effect on the energy consumption of ECs, impacting both energy costs and carbon emissions. Due to the geographic distribution of ECs, there is a variety of resources, energy prices and carbon emission rates to consider, which makes optimizing the placement of applications for cost and carbon efficiency even more challenging than in centralized clouds. This paper presents a Dynamic Energy cost and Carbon emission-efficient Application placement method (DECA) for ECs. DECA addresses both the initial placement of applications on ECs and the re-optimization of the placement using migrations. DECA considers geographically varying energy prices and carbon emission rates as well as optimizing the usage of both network and computing resources at the same time. By combining a prediction-based A* algorithm with a Fuzzy Sets technique, DECA makes intelligent decisions to optimize energy cost and carbon emissions. Simulation results show the ability of DECA in providing a tradeoff and optimizing energy cost and carbon emission at the same time.

BackgroundWhether left ventricular non-compaction (LVNC) bears a different prognosis than dilated cardiomyopathy (DCM) is still a matter of debate.MethodsFrom a multicenter French prospective registry, we compared the outcomes of 98 patients with LVNC and 65 with DCM. The primary endpoint combined cardiovascular death, heart transplantation, and hospitalization for cardiovascular events. The two groups presented similar outcomes but different left ventricular ejection fractions (LVEF) (43.3% in LVNC vs. 35.95% in DCM, p = 0.001). For this reason, a subgroup analysis was performed comparing only patients with LVEF ≤ 45%, including 56 with LVNC and 49 with DCM.ResultsAmong patients with LVEF≤ 45%, at 5-year follow-up, the primary endpoint occurred in 33 (58.9%) among 56 patients with LVNC and 18 (36.7%) among 49 patients with DCM (p = 0.02). Hospitalization for heart failure (18 [32.14%] vs. 5 [10.20%], p = 0.035) and heart transplantation were more frequent in the LVNC than in the DCM group. The incidences of rhythmic complications (24 [42.85%] vs. 12 [24.48%], p = 0.17), embolic events, and cardiovascular death were similar between LVNC and DCM cases. Among the 42 patients with LVNC and LVEF > 45%, the primary endpoints occurred in only 4 (9.52%) patients, including 2 hospitalizations for heart failure and 3 rhythmic complications, but no embolic events.ConclusionIn this prospective cohort, patients with LVNC who have left ventricular dysfunction present a poorer prognosis than DCM patients. Heart failure events were especially more frequent, but embolic events were not. Patients with LVNC and preserved ejection fraction present very few events in 5 years.

Abstract Background Methods for estimating relative survival are widely used in population-based cancer survival studies. These methods are based on splitting the observed (the overall) mortality into excess mortality (due to cancer) and background mortality (due to other causes, as expected in the general population). The latter is derived from life tables usually stratified by age, sex, and calendar year but not by other covariates (such as the deprivation level or the socioeconomic status) which may lack though they would influence background mortality. The absence of these covariates leads to inaccurate background mortality, thus to biases in estimating the excess mortality. These biases may be avoided by adjusting the background mortality for these covariates whenever available. Methods In this work, we propose a regression model of excess mortality that corrects for potentially inaccurate background mortality by introducing age-dependent multiplicative parameters through breakpoints, which gives some flexibility. The performance of this model was first assessed with a single and two breakpoints in an intensive simulation study, then the method was applied to French population-based data on colorectal cancer. Results The proposed model proved to be interesting in the simulations and the applications to real data; it limited the bias in parameter estimates of the excess mortality in several scenarios and improved the results and the generalizability of Touraine’s proportional hazards model. Conclusion Finally, the proposed model is a good approach to correct reliably inaccurate background mortality by introducing multiplicative parameters that depend on age and on an additional variable through breakpoints.

Objective The objective of this study was to assess the potential of the use of asynchronous tele-expertise (ASTE) to provide prenatal diagnosis from a medical and economic point of view. Population Patients screened by a midwife at a primary center. Methods A technical and clinical evaluation was conducted retrospectively, and a cost minimization study compared asynchronous tele-expertise to face-to-face consultations that would have been performed without ASTE. Main outcome measures In our study we assessed the feasibility of ASTE, what were the origins of the requests for expertise, whether patients need to be moved and the reasons for doing so, and the costs of tele-expertise and conventional consultation. Results In this retrospective analysis 322 advices from 260 patients were interpreted remotely via a platform. The results revealed a 90.68% feasibility of transmitting in a satisfactory and interpretable way ultrasound images and videos via the tele-expertise platform (292/322 files). In our series, asynchronous analysis allowed the required physician to make an accurate diagnosis and identify 74 (28.5%, 95% CI [23% –33.9%]) pregnancies associated with malformations and rule out abnormalities in 186 (71.5%, 95% CI [66.1% –77%]) of the cases. The ASTE was not associated with face-to-face consultations for 72.7% (189/260) of the patients, who without moving, were able to have access to a precise diagnosis by ruling out the presence of anomalies in 163/189 of these patients and confirming them in 26/189 patients. The practice of ASTE would result from a societal point of view, an average saving of 61.8% (€ 120.57) per patient compared to a face-to-face consultation. Conclusion The use of asynchronous tele-expertise (ASTE) using fetal ultrasound, is feasible and may contribute to increased diagnostic accuracy while generating a significant reduction in costs for society.

ObjectiveThe objective of this study was to assess the potential of the use of asynchronous tele-expertise (ASTE) to provide prenatal diagnosis from a medical and economic point of view.PopulationPatients screened by a midwife at a primary center.MethodsA technical and clinical evaluation was conducted retrospectively, and a cost minimization study compared asynchronous tele-expertise to face-to-face consultations that would have been performed without ASTE.Main outcome measuresIn our study we assessed the feasibility of ASTE, what were the origins of the requests for expertise, whether patients need to be moved and the reasons for doing so, and the costs of tele-expertise and conventional consultation.ResultsIn this retrospective analysis 322 advices from 260 patients were interpreted remotely via a platform. The results revealed a 90.68% feasibility of transmitting in a satisfactory and interpretable way ultrasound images and videos via the tele-expertise platform (292/322 files). In our series, asynchronous analysis allowed the required physician to make an accurate diagnosis and identify 74 (28.5%, 95% CI [23% -33.9%]) pregnancies associated with malformations and rule out abnormalities in 186 (71.5%, 95% CI [66.1% -77%]) of the cases. The ASTE was not associated with face-to-face consultations for 72.7% (189/260) of the patients, who without moving, were able to have access to a precise diagnosis by ruling out the presence of anomalies in 163/189 of these patients and confirming them in 26/189 patients. The practice of ASTE would result from a societal point of view, an average saving of 61.8% (€ 120.57) per patient compared to a face-to-face consultation.ConclusionThe use of asynchronous tele-expertise (ASTE) using fetal ultrasound, is feasible and may contribute to increased diagnostic accuracy while generating a significant reduction in costs for society.