Prognostic Algorithms Research Articles

Prognostic algorithm for risk assessment of retinal vein occlusion under geomagnetic perturbations

Aim. To develop a screening and prognostic algorithm for assessing the risk of retinal vein occlusion in patients with arterial hypertension under the conditions of geomagnetic disturbances. Material and methods. In total, 1512 patients with arterial hypertension of 1–4 stages were examined. Within the period of three years, 391 patients developed retinal venous occlusions. The parameters of systemic and regional hemodynamics in these patients, as well as ocular microcirculatory function, were compared both in a magnetically calm environment and during geomagnetic disturbances. To simulate the response of microcirculatory bed to stress, a functional pharmacological instillation test with a 10% Irifrin solution was performed. To assess the geomagnetic situation, the Кр index was used, which objectively characterizes fluctuations of the Earth’s magnetic field over a 3h time interval. The International Classification of Кр values was used. Results. For statistical analysis, 78 studied signs of systemic, regional hemodynamics, and microcirculation were selected. The prognostic significance of 30 studied signs was revealed. A training group (1434 people) and an examination group (78 people) were formed. Based on the training group, a predictive algorithm was formed. A number of regularities were established, which can be used to create a system for risk assessment of retinal vein thrombosis during geomagnetic disturbances in patients with hypertension. To determine the risk of retinal vein occlusion, a coefficient was developed. The algorithm showed the sensitivity and specificity of 89% and 94%, respectively. Conclusion. A prognostic algorithm with high sensitivity and specificity for assessing the risk of occlusive lesions of the retinal veins during geomagnetic disturbances in patients with arterial hypertension is proposed.

Classification of Predictors of Rapid Development of Kidney Failure and Short-Term Changes in Concentration of Circulating Proteins.

Limited knowledge exists regarding short-term changes/increases in concentrations of circulating proteins (referred here as deltas) and rapid development of kidney failure (rapid KF) in diabetes mellitus. Concentrations of 452 circulating proteins were measured by OLINK proteomics platform at baseline and after a median interval of 3-4 years in 106 individuals with type 1 and 77 with type 2 diabetes in two case-control studies. During 10-year follow-up, 31 and 26 individuals, respectively, developed rapid KF. Deltas for 40 proteins predicted rapid KF in both studies. All were better predictors than delta urine albumin-creatinine ratio, and half were better than delta glomerular filtration rate. Comparing the delta proteins with 46 circulating proteins of which elevated baseline concentrations were predictors of rapid KF risk in our previous study, 61 unique proteins were identified. Among these proteins, 21 were good predictors of rapid KF only when measured at baseline (predictors of initiation), 15 were good predictors when measured as deltas (predictors of progression) and 25 were good predictors when both baseline and delta concentrations were used (predictors of initiation and progression). An index score, developed for the latter 25 proteins, provided superior prediction of rapid KF. A subset of these latter proteins was associated with apoptotic processes/tumor necrosis factor (TNF) receptor signaling pathways. Development of rapid KF in diabetes was preceded by elevated concentrations of multiple circulating proteins both at baseline and during short follow-up. Comparing baseline and short-term changes in concentrations of circulating proteins classified predictors of rapid KF risk into those associated with initiation, progression, or both. Predictors of both initiation & progression flagged apoptosis processes and TNF receptor signaling pathways. Multi-protein prognostic algorithms using proteins associated with both initiation and progression improved prediction of rapid KF risk beyond clinical variables.

Lower early mortality after acute pulmonary embolism in patients with WHO-defined obesity: results from a post-hoc cohort analysis with external validation

Abstract Background The relationship between obesity, defined as a Body Mass Index (BMI) ≥ 30 kg/m2, and mortality in venous thrombo-embolism remains controversial. Objectives To compare early outcomes after pulmonary embolism (PE) between obese patients, and non-obese, non-underweight patients. Methods We performed a post-hoc analysis based on prospectively recorded individual patient data from the multicenter BFC-FRANCE registry. We compared rates of outcomes using multivariable logistic regression or a Cox model for 30-day and 6-month outcomes respectively. We assessed the incremental value of adding BMI information on top of the 30-day European Society of Cardiology (ESC) prognostic algorithm. Results A total of 2,390 patients with a BMI ≥ 18.5 kg/m2 (mean age, 66.9±16.8 years; 1,188 men [49.7%]) were included, 686 patients [28.7%] in the obese group, and 1,704 patients [71.3%] in the non-obese group. Mortality rates were significantly lower in obese patients versus non-obese patients at 30 days (OR, 0.59; 95% CI, 0.35-0.98), and 6 months. Cox-model-derived adjusted curves for all-cause death at 6 months, with hazard ratios (HRs) between obese and non-obese patients, after acute PE, are shown in the Figure. Rates of secondary non-fatal outcomes (including recurrent VTE) did not differ between groups. The addition of the obesity information on top of the ESC prognostic model improved global model fit, and discriminatory and calibration capacities, yielding significant reclassification based on the observed mortality rates with the ESC model as reference. Findings were confirmed in an external validation using 35,796 PE patients from the RIETE registry. Conclusion We present evidence indicating lower early and mid-term mortality after PE in patients classified as obese based on BMI, compared with non-obese, non-underweight patients. BMI should likely be incorporated into algorithms or scoring systems for predicting early mortality following PE.

Prognostic algorithm for early diagnosis of subcritical conditions as predictors of sudden cardiac death

Aim. To develop a method for early diagnosis of subcritical homeostasis disorders leading to sudden cardiac death (SCD). The basis is to improve the efficiency of predictive algorithms.Material and methods. This pilot, controlled, open-label, randomized, prospective clinical trial included 220 patients at risk of SCD and 150 patients without risk of SCD. Main and control groups was formed according to the global cardiovascular risk score. Based on the informative features proposed by specialized experts using multivariate statistics methods (discriminant analysis), two condition classes were formed. The conducted exploratory analysis confirmed the significance of diagnostic criteria in relation to SCD manifestation (manifestation of cardiac arrest — MCA), which is an integral assessment of a fatal complication. The development of decision rules was carried out on the basis of soft computing technology.Results. Taking into account the priority of clinical research, namely, the identification of subcritical stages of MCA, a classifier is proposed according to basic severity of patients — the severity of critical condition risk (SCCR). The discriminant function and intersection areas between MCA subclasses in the conditions of early SCD diagnosis determine the transition to soft computing technology. Membership functions for severe MCA are formed, followed by their iteration according to E. Shortliffe. The final decision rule, using a fuzzy classifier, differentiates the MCA into stages with different SCCR. In parallel with standard protocols for the management of severe somatic patients (chronic obstructive pulmonary disease, chronic kidney disease, hepatocellular failure), based on the proposed algorithm with an integral assessment of critical conditions, using the MCA decision rule in the main group in 30,5% of cases, subcritical stage was revealed, followed by targeted treatment and preventive support. In the first group, a subcritical condition was detected in 67 patients (30,5%); a critical condition without SCD — in 3 patients (1,4%). In all noted cases, early prevention of SCD was successfully carried out (these patients were transferred to a class with a lower SCD degree). Using conventional prognostic scores in this group, 46 patients (20,9%) were identified with a subcritical condition and 1 (0,4%) with a critical condition. In the control group, subcritical condition was determined in 35 patients (23,3%), of which 17 patients (11,3%) had a moderate risk of SCD. Using conventional prognostic scores, 23 patients (15,3%) with subcritical condition were identified.Conclusion. In the conditions of intensive care unit, general medicine departments, hemodialysis department, cardiac surgery, and organ transplantation department, an algorithm for early diagnosis and risk stratification of SCD with an integral assessment (MCA) should be used. The fuzzy classifier MCA according to SCCR makes it possible to carry out timely correction of treatment measures in addition to standard protocols.

Next-generation lung cancer pathology: Development and validation of diagnostic and prognostic algorithms

Non-small cell lung cancer (NSCLC) is one of the most common malignant tumors. In this study, we develop a clinically useful computational pathology platform for NSCLC that can be a foundation for multiple downstream applications and provide immediate value for patient care optimization and individualization. We train the primary multi-class tissue segmentation algorithm on a substantial, high-quality, manually annotated dataset of whole-slide images with lung adenocarcinoma and squamous cell carcinomas. We investigate two downstream applications. NSCLC subtyping algorithm is trained and validated using a large, multi-institutional (n= 6), multi-scanner (n= 5), international cohort of NSCLC cases (slides/patients 4,097/1,527). Moreover, we develop four AI-derived, fully explainable, quantitative, prognostic parameters (based on tertiary lymphoid structure and necrosis assessment) and validate them for different clinical endpoints. The computational platform enables the high-precision, quantitative analysis of H&E-stained slides. The developed prognostic parameters facilitate robust and independent risk stratification of patients with NSCLC.

ПРОГНОСТИЧЕСКИЙ АЛГОРИТМ ФОРМИРОВАНИЯ ЗАДЕРЖКИ ФИЗИЧЕСКОГО РАЗВИТИЯ У ДЕТЕЙ, ПЕРЕНЕСШИХ ВНУТРИУТРОБНУЮ НАРКОТИЧЕСКУЮ ИНТОКСИКАЦИЮ

Objective: to create prognostic tables for delayed physical development of children who have experienced drug intoxication in the prenatal period. Materials and methods. The research materials are presented by the study group (51 children) and the verification group of children (10 people). The study group consisted of children aged 1 to 14 years who had prenatal exposure to opiates. Research methods included medical history, follow-up observation and statistical processing of the data obtained using the “Statistica 9.0” program. Results. A prognostic algorithm has been created in tabular expression of the most informationally significant 19 risk factors that have both a prognostically significant and leveling effect on the formation of future delays in the child’s physical development. prognostic table of risk data for the development of delayed physical development in children born to drug-addicted women. The obtained data was verified by a verification group. The effectiveness was 90 % (9 prognostic scenarios adequately reflected upcoming events. Conclusion. The developed predictive algorithms for delayed physical development in children who were exposed to opiates in the prenatal period are applicable in the practice of a pediatrician and create a real opportunity to draw up individual scenarios. The data obtained will help to prevent the development of pathology in a timely manner.

Prognostic communication in amyotrophic lateral sclerosis: findings from a Nationwide Italian survey.

Amyotrophic Lateral Sclerosis (ALS) is a fatal motor neuron disease with a highly variable prognosis. Among the proposed prognostic models, the European Network for the cure of ALS (ENCALS) survival model has demonstrated good predictive performance. However, few studies have examined prognostic communication and the diffusion of prognostic algorithms in ALS care. To investigate neurologists' attitudes toward prognostic communication and their knowledge and utilization of the ENCALS survival model in clinical practice. A web-based survey was administered between May 2021 and March 2022 to the 40 Italian ALS Centers members of the Motor Neuron Disease Study Group of the Italian Society of Neurology. Twenty-two out of 40 (55.0%) Italian ALS Centers responded to the survey, totaling 37 responses. The model was known by 27 (73.0%) respondents. However, it was predominantly utilized for research (81.1%) rather than for clinical prognostic communication (7.4%). Major obstacles to prognostic communication included the unpredictability of disease course, fear of a negative impact on patients or caregivers, dysfunctional reaction to diagnosis, and cognitive impairment. Nonetheless, the model was viewed as potentially useful for improving clinical management, increasing disease awareness, and facilitating care planning, especially end-of-life planning. Despite the widespread recognition and positive perceptions of the ENCALS survival model among Italian neurologists with expertise in ALS, its implementation in clinical practice remains limited. Addressing this disparity may require systematic investigations and targeted training to integrate tailored prognostic communication into ALS care protocols, aligning with the growing availability of prognostic tools for ALS.

Predictive model of nocturnal hypoglycemia based on the data from mobile application for glucose monitoring

Objective: to develop a prognostic algorithm of nocturnal hypoglycemia (NH) based on the glucose monitoring mobile application data. Material and methods. The retrospective analysis of 524 continuous glucose monitoring (CGM) profiles of patients with type 1 diabetes mellitus was performed. CGM was performed using the Medtronic iPro2 system for 6-7 days, overnight periods of CGM were analyzed to identify systematic NH. There were 239 patients included in the study, among them 65 (27.1%) were identified as having systematic NH. Models of 7-point glycemic profiles were built and their data were uploaded to the DiaLog GM mobile application to calculate standardized glucose monitoring parameters. The prognostic model of NH was developed based on the logistic regression method. Results. According to the results of regression analysis the most significant predictors of NH included in the prognostic model were: glycated hemoglobin (p=0.001), using of insulin pump therapy (p=0.001), time below target range level 1 (p<0.001), coefficient of variation for glucose (p=0.02). The area under the ROC curve for the prediction model was 0.917; the optimal cut-off point for the predicted probability of NH was 0.317, with model sensitivity of 85% and specificity of 90%. Conclusions. The developed prediction model based on data from a specialized mobile application allows to improve the existing approaches to NH risk assessment due to higher predictive ability.

Artificial intelligence streamlines diagnosis and assessment of prognosis in Brugada syndrome: a systematic review and meta-analysis

Aim: The objective of this systematic review and meta-analysis was to determine the diagnostic and prognostic utility of artificial intelligence/machine learning (AI/ML) algorithms in Brugada Syndrome (BrS). Methods: A systematic review and meta-analysis of the literature was conducted in accordance with the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) guidelines. MEDLINE, EMBASE, SCOPUS, and WEB OF SCIENCE databases were searched for relevant articles. Abstract and title screening, full-text review, and data extraction were conducted independently by two of the authors. Conflicts were resolved via discussion among authors. A risk-of-bias assessment was performed using the QUADAS-2 tool for diagnostic studies and the PROBAST tool for prognostic studies. Forest plots and the summary area under the receiver operating characteristic (SAUROC) curve were done in R. Results: A total of 12 papers were included in our study. Among the best-performing diagnostic algorithms from each study, the sensitivity and specificity ranged from 0.80 to 0.89 and 0.74 to 0.97, respectively. In overall studies, sensitivity was 0.845 ± 0.014 and specificity was 0.892 ± 0.062 using a random effects model. A pooled analysis of the summary area under the receiver operating characteristic curve (SAUROC) was 0.77 for diagnostic studies. Prognostic studies showed good performance as well, with the AUC of the best-performing prognostic algorithms ranging from 0.71 to 0.90. Conclusions: Overall, AI/ML algorithms had high diagnostic and prognostic accuracy. These results highlight the potential of AI/ML algorithms for the diagnosis and prognosis of BrS and permit a choice of the best-performing ML algorithms.

Inflammatory risk and cardiovascular events in patients without obstructive coronary artery disease: the ORFAN multicentre, longitudinal cohort study

Coronary computed tomography angiography (CCTA) is the first line investigation for chest pain, and it is used to guide revascularisation. However, the widespread adoption of CCTA has revealed a large group of individuals without obstructive coronary artery disease (CAD), with unclear prognosis and management. Measurement of coronary inflammation from CCTA using the perivascular fat attenuation index (FAI) Score could enable cardiovascular risk prediction and guide the management of individuals without obstructive CAD. The Oxford Risk Factors And Non-invasive imaging (ORFAN) study aimed to evaluate the risk profile and event rates among patients undergoing CCTA as part of routine clinical care in the UK National Health Service (NHS); to test the hypothesis that coronary arterial inflammation drives cardiac mortality or major adverse cardiac events (MACE) in patients with or without CAD; and to externally validate the performance of the previously trained artificial intelligence (AI)-Risk prognostic algorithm and the related AI-Risk classification system in a UK population. This multicentre, longitudinal cohort study included 40 091 consecutive patients undergoing clinically indicated CCTA in eight UK hospitals, who were followed up for MACE (ie, myocardial infarction, new onset heart failure, or cardiac death) for a median of 2·7 years (IQR 1·4-5·3). The prognostic value of FAI Score in the presence and absence of obstructive CAD was evaluated in 3393 consecutive patients from the two hospitals with the longest follow-up (7·7 years [6·4-9·1]). An AI-enhanced cardiac risk prediction algorithm, which integrates FAI Score, coronary plaque metrics, and clinical risk factors, was then evaluated in this population. In the 2·7 year median follow-up period, patients without obstructive CAD (32 533 [81·1%] of 40 091) accounted for 2857 (66·3%) of the 4307 total MACE and 1118 (63·7%) of the 1754 total cardiac deaths in the whole of Cohort A. Increased FAI Score in all the three coronary arteries had an additive impact on the risk for cardiac mortality (hazard ratio [HR] 29·8 [95% CI 13·9-63·9], p<0·001) or MACE (12·6 [8·5-18·6], p<0·001) comparing three vessels with an FAI Score in the top versus bottom quartile for each artery. FAI Score in any coronary artery predicted cardiac mortality and MACE independently from cardiovascular risk factors and the presence or extent of CAD. The AI-Risk classification was positively associated with cardiac mortality (6·75 [5·17-8·82], p<0·001, for very high risk vs low or medium risk) and MACE (4·68 [3·93-5·57], p<0·001 for very high risk vs low or medium risk). Finally, the AI-Risk model was well calibrated against true events. The FAI Score captures inflammatory risk beyond the current clinical risk stratification and CCTA interpretation, particularly among patients without obstructive CAD. The AI-Risk integrates this information in a prognostic algorithm, which could be used as an alternative to traditional risk factor-based risk calculators. British Heart Foundation, NHS-AI award, Innovate UK, National Institute for Health and Care Research, and the Oxford Biomedical Research Centre.

The seasonal-trend disentangle based prognostic framework for PEM fuel cells

Prognostics and Health Management (PHM) offer a potential solution to improve the durability of Proton Exchange Membrane Fuel Cells (PEMFCs), where degradation prognostic is the key component of the PHM system. However, limited by the dynamic operating environment, accurate and efficient prognostic algorithms still required for real applications. In this paper, the Seasonal-Trend Disentangle (STD) based prognostic framework is proposed to enhance the Remaining Useful Life (RUL) prediction of PEMFC system. Specifically, a lightweight parameter estimation neural network is introduced to estimate the aging parameters of the FC degradation model directly from PEMFC measurements. Besides, the integral of the FC degradation model at the specified current density range serves as the comprehensive Health Index (HI), which could combine different aging parameters and mitigate the effect of load dynamics. The STD-based prognostic model effectively captures the time-invariant features in the HI sequence from trend and seasonal phases, improving Remaining Useful Life (RUL) prediction performance. The proposed prognostic model is compared with RNN-family, ESN, and Dilated CNN methods using three distinct durability datasets from FCs operating under static, quasi-dynamic, and cyclically varying dynamic current loads. Experimental results demonstrate that the proposed algorithm outperforms the reference methods in terms of RMSE and MAPE metrics in the aging prognostic, and the proposed method could obtain satisfactory RUL prediction results 100–150 h earlier than the reference methods.

A structural model of glucose regulation for building prognostic algorithms for controlling insulin therapy

A structural model of glucose regulation for building prognostic algorithms for controlling insulin therapy

Elucidating a genomic signature associated with behavioral and executive function after moderate to severe pediatric TBI: a systems biology informed approach

Introduction: There is significant unexplained variability in behavioral and executive functioning after pediatric traumatic brain injury (TBI). Prior research indicates that there are likely genetic contributions; however, current research is limited. The purpose of this study is to use a systems biology informed approach to characterize the genomic signature related to behavioral and executive functioning ∼12 months after moderate through severe TBI in children.Methods: Participants were from two prospective cohorts of children with severe TBI (Cohort #1) and moderate-severe TBI and an orthopedic injury (OI) group (Cohort #2). Participants included 196 children (n = 72 and n = 124 total from each respective cohort), ranging in age between 0–17 years at the time of injury. In total, 86 children had severe TBI, 49 had moderate TBI, and 61 had an OI. Global behavioral functioning assessed via the Child Behavior Checklist and executive function assessed via the Behavioral Rating Inventory of Executive Function at ∼ 12 months post injury served as outcomes. To test for a genomic signature, we compared the number of nominally significant (p &amp;lt; 0.05) polymorphisms associated with the outcomes in our systems biology identified genes to a set 10,000 permutations using control genes (e.g., not implicated by systems biology). We used the ToppFun application from Toppgene Suite to identify enriched biologic processes likely to be associated with behavioral and executive function outcomes.Results: At 12 months post injury, injury type (TBI vs OI) by polymorphism interaction was significantly enriched in systems biology selected genes for behavioral and executive function outcomes, suggesting these genes form a genomic signature. Effect sizes of the associations from our genes of interest ranged from .2–.5 for the top 5% of variants. Systems biology analysis of the variants associated with the top 5% effect sizes indicated enrichment in several specific biologic processes and systems.Discussion: Findings indicate that a genomic signature may explain heterogeneity of behavioral and executive outcomes after moderate and severe TBI. This work provides the foundation for constructing genomic signatures and integrating systems biology and genetic information into future recovery, prognostic, and treatment algorithms.

Biomarkers of oxidative stress and proteopathies in the diagnosis of neurodegenerative diseases

Introduction. Despite numerous studies in the field of neurodegenerative diseases, the exact mechanisms of these processes have not yet been identified. The purpose of this review is to analyze the methodological approaches necessary to revise the traditional and create new reliable prognostic and diagnostic algorithms that reflect pathogenetic features at different stages of neurodegeneration and atypical course of the disease. Material and methods. The review highlights the results of clinical and experimental studies obtained using a complex of clinical, laboratory and instrumental methods with an emphasis on markers of oxidative stress and proteopathy. In preparing the materials, sources from international and domestic databases were used: Scopus, Web of Science, Pub Medline, RSCI mainly for the last 15 years. Results. An idea has been formed about the molecular mechanisms of neural tissue regression in a number of neurodegenerative diseases such as multiple sclerosis, amyotrophic lateral sclerosis, Alzheimer’s and Parkinson’s disease. The relationship between the parameters of the oxidative process and the features of metal-energy shifts in organs and organ systems is demonstrated. The role of markers of oxidative stress in the early stages, when the process of inflammation prevails and in the atypical course of the disease, is shown. Valuable biochemical markers are cytokines, glutathione levels, myeloperoxidase activation, and isoprostanes. The review points to the prospect of including in screening indicators of iron and other metals such as Zn, Mg, affecting the clinic accumulation of β-amyloid, in connection with which they can be considered as the basis for the progression of neurodegeneration. New data on the contribution of halogenating stress to the pathogenesis of neuroinflammation are presented. An aspect requiring development in the field of biomarkers for assessing the duration of the disease and prognostic prospects is the data on the correlation of metabolic shifts in the intestinal microbiota with the duration of the disease and the inflammatory process. Essential for the creation of express diagnostic methods is the determination of redox balance as an integral marker in saliva, which has obvious advantages over the use of biological fluids, such as liquor and serum. Conclusion. The prospects of creating new prognostic and diagnostic schemes are associated with complexes, including laboratory and instrumental methods, in blood, liquor and saliva. Evaluation of the sensitivity and specificity of new markers depending on the clinical diagnosis allows the selection of pathogenetically significant markers in the early stages of the disease, with atypical neurodegeneration, to establish subtypes of the disease, to carry out their differential diagnosis.

486 Quantification of serum neurofilament light chain (NfL) in cubital tunnel

OBJECTIVES/GOALS: The long-term goal of our lab is to develop clinical and intra-operative methods to aid in assessment of compressive and traumatic peripheral neuropathies. The overall objective of this project is toidentify the potential of serum neurofilament light chain as a diagnostic biomarker for nerve injury. METHODS/STUDY POPULATION: The objective of this prospective study is to obtain data on serum NfL levels in patients with cubital tunnel syndrome and traumatic nerve injuries. Serum NfL from patients with cubital tunnel and traumatic nerve injuries will be compared to serum NfL of asymptomatic, sex and aged matched controls. Pre-operative and post-operative serum levels will be measured and compared topatient’s pre-operative physical exam findings, motor and sensory function testing, electrodiagnostic studies, ultrasound, presence of intraneural vascularity, and post-operative patient reported outcome measures for cubital tunnel patients. For patients with traumatic nerve injury, acute phase and a subsequent serum NfL measurement will be used to assess temporal changes in NfL. RESULTS/ANTICIPATED RESULTS: The central hypothesis of this study is that symptomatic compression of the ulnar nerve or traumatic injury to the brachial plexus leading to axonotmesis will result in measurable increases in serum NfL proportional to the degree of nerve injury. This hypothesis has been formulated based on clinical experience and published studies demonstrating increased expression of serum NfL levels with axonal injury secondary to varying forms of peripheral neuropathy. DISCUSSION/SIGNIFICANCE: The significance of this project is that characterization of the relationship of clinical symptoms, non-invasive imaging and expression of NfL will lead to better diagnostic and prognostic algorithms in the treatment of compressive and traumatic peripheral neuropathies.

Abstract 7641: Prognostic impact of functional germline mutations in muscle-invasive bladder cancer identified by neural network analysis

Abstract Background: An accurate prognostic algorithm based on germline whole exome sequencing (WES) would complement tumor omics as a non-invasive source of biomarkers for guiding cancer patient therapy. In a previous study, we used WES and RNA-seq data from muscle-invasive bladder cancer (MIBC) and normal host cells to train a survival model, wherein we discovered that mutated germline genes accounted for 90% of feature importance. We have since defined a larger cohort to identify key germline biomarkers of overall survival (OS) that may be scalable for application in the clinic. Methods: 169 patients from The Cancer Genome Atlas (TCGA) with MIBC stages T2-T4 that underwent radical cystectomy (RC) w/o neoadjuvant treatment were eligible. OS at 4 years was the primary clinical endpoint as it is associated with death due to metastatic tumor recurrence. Patients were dichotomized to control survivors who were alive at 4+ years, and cases who died within 4 years but no less than 4 months after RC. 49 qualifying survivors were propensity matched against 49 dead patients by stage, adjuvant treatment, gender, race, and age. The remaining 71 dead patients served as a holdout. Only high (e.g. frameshift) and moderate (e.g. indel) impact germline variants were included. Mutations were weighted for allele frequency (penalize common) and genotype (reward homozygous) before grouping at the gene level. A panel of the 21 most differential genes in stratified patients were selected for neural network training using AIQC. The model forced protective/pathogenic genes to interact and produced individual survival probabilities. Gene importance was determined via permutation. Results: OS was accurately predicted for 98.2% of patients: 1 FN, 2 FP, 37 TN, 119 TP. The top 3 permuted genes (and related pathways) were: SORL1 (Aβ), KIF27 (hedgehog), CUL7 (p53). The most differential gene was CUL7: 31% of survivors mutated vs 2% of dead. Conclusion: Neural network analysis identified the promise of germline genetics as an accurate predictor of survival and tumor recurrence in MIBC patients. Upon validation in an external cohort, these biomarkers could be used to inform adjuvant therapy and complement molecular residual disease alongside circulating tumor (ct)-DNA. Citation Format: Guru P. Sonpavde, Amin H. Nassar, Arvind Ravi, Layne Sadler. Prognostic impact of functional germline mutations in muscle-invasive bladder cancer identified by neural network analysis [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 7641.

Comparative analysis of CRASH and IMPACT in predicting the outcome of 340 patients with traumatic brain injury.

Both the International Mission for Prognosis and Analysis of Clinical Trials (IMPACT) and the Corticosteroid randomization after significant head injury (CRASH) models are globally acknowledged prognostic algorithms for assessing traumatic brain injury (TBI) outcomes. The aim of this study is to externalize the validation process and juxtapose the prognostic accuracy of the CRASH and IMPACT models in moderate-to-severe TBI patients in the Chinese population. We conducted a retrospective study encompassing a cohort of 340 adult TBI patients (aged > 18 years), presenting with Glasgow Coma Scale (GCS) scores ranging from 3 to 12. The data were accrued over 2 years (2020-2022). The primary endpoints were 14-day mortality rates and 6-month Glasgow Outcome Scale (GOS) scores. Analytical metrics, including the area under the receiver operating characteristic curve for discrimination and the Brier score for predictive precision were employed to quantitatively evaluate the model performance. Mortality rates at the 14-day and 6-month intervals, as well as the 6-month unfavorable GOS outcomes, were established to be 22.06, 40.29, and 65.59%, respectively. The IMPACT models had area under the curves (AUCs) of 0.873, 0.912, and 0.927 for the 6-month unfavorable GOS outcomes, with respective Brier scores of 0.14, 0.12, and 0.11. On the other hand, the AUCs associated with the six-month mortality were 0.883, 0.909, and 0.912, and the corresponding Brier scores were 0.15, 0.14, and 0.13, respectively. The CRASH models exhibited AUCs of 0.862 and 0.878 for the 6-month adverse outcomes, with uniform Brier scores of 0.18. The 14-day mortality rates had AUCs of 0.867 and 0.87, and corresponding Brier scores of 0.21 and 0.22, respectively. Both the CRASH and IMPACT algorithms offer reliable prognostic estimations for patients suffering from craniocerebral injuries. However, compared to the CRASH model, the IMPACT model has superior predictive accuracy, albeit at the cost of increased computational intricacy.

Are Current Survival Prediction Tools Useful When Treating Subsequent Skeletal-related Events From Bone Metastases?

Are Current Survival Prediction Tools Useful When Treating Subsequent Skeletal-related Events From Bone Metastases?

Preliminary Nose Landing Gear Digital Twin for Damage Detection

An increase in aircraft availability and readiness is one of the most desired characteristics of aircraft fleets. Unforeseen failures cause additional expenses and are particularly critical when thinking about combat jets and Unmanned Aerial Vehicles (UAVs). For instance, these systems are used under extreme conditions, and there can be situations where standard maintenance procedures are impractical or unfeasible. Thus, it is important to develop a Health and Usage Monitoring System (HUMS) that relies on diagnostic and prognostic algorithms to minimise maintenance downtime, improve safety and availability, and reduce maintenance costs. In particular, within the realm of aircraft structures, landing gear emerges as one of the most intricate systems, comprising several elements, such as actuators, shock absorbers, and structural components. Therefore, this work aims to develop a preliminary digital twin of a nose landing gear and implement diagnostic algorithms within the framework of the Health and Usage Monitoring System (HUMS). In this context, a digital twin can be used to build a database of signals acquired under healthy and faulty conditions on which damage detection algorithms can be implemented and tested. In particular, two algorithms have been implemented: the first is based on the Root-Mean-Square Error (RMSE), while the second relies on the Mahalanobis distance (MD). The algorithms were tested for three nose landing gear subsystems, namely, the steering system, the retraction/extraction system, and the oleo-pneumatic shock absorber. A comparison is made between the two algorithms using the ROC curve and accuracy, assuming equal weight for missed detections and false alarms. The algorithm that uses the Mahalanobis distance demonstrated superior performance, with a lower false alarm rate and higher accuracy compared to the other algorithm.

An Integrated Monitoring, Diagnostics, and Prognostics System for Aero-Engines under Long-Term Performance Deterioration

In the field of aircraft engine diagnostics, many advanced algorithms have been proposed over the last few years. However, there is still wide room for improvement, especially in the development of more integrated and complete engine health management systems to detect, identify, and forecast complex faults in a short time. Furthermore, it is necessary to ensure that these systems preserve their capabilities over time despite engine deterioration. This paper addresses these necessities by proposing an integrated system that considers the joint operation of feature extraction, anomaly detection, fault identification, and prognostic algorithms for engines with long operation times. To effectively reveal the actual engine condition, light adaptive degraded engine models are computed along with different health indicators that are used as inputs to train and test recognition and prediction models. The system is developed and evaluated using a specialized NASA platform which provides data from a turbofan engine fleet simultaneously experiencing long-term performance deterioration and faults. Contrary to other compared solutions, our results show that the proposed system is robust against the effects of engine deterioration, maintaining its level of detection, recognition, and prediction accuracy over a total engine service life. The low computational cost algorithms has generally fast performance in all stages, making the system suitable for online applications.