Prognostic System Research Articles

The prognostic significance of genetics in acute myeloid leukemia under venetoclax-based treatment.

Acute myeloid leukemia (AML) is the most prevalent hematologic malignancy in adults. In 2022, the European LeukemiaNet (ELN) has updated its prognostic system that incorporates cytogenetics and molecular genetics based on data from patients undergoing intensive chemotherapy (IC). Recently, a risk stratification framework has been established for hypomethylating agents (HMA)-based low-intensity treatment (LIT) to fill the gaps in stratification for this treatment modality, but this needs further refinement. Venetoclax (VEN), a BH3 mimetic, targets BCL-2 to modulate apoptosis and metabolism in AML cells. Its combination with HMA or low-dose cytarabine (LDAC) has been shown to enhance the response rates and prolong the survival outcomes of older or unfit patients with AML. In this review, we delved into the prognostic significance of FLT3-ITD and IDH mutations when used in combination with VEN and HMA, as well as in conjunction with their specific inhibitors. We also explored the role of VEN in NPM1-mutated AML and its efficacy in splicing factor mutations AML. Additionally, we examined the response rates and survival outcomes of CBF-AML when treated with a VEN-based regimen. Moving forward, it is imperative that risk stratification for LIT becomes more nuanced to better align with the requirements of personalized diagnosis and treatment strategies.

Prognostic staging system correctly identifies high risk groups in cardiac transthyretin amyloidosis treated with tafamidis

Abstract Background The development of different multiparametric staging systems improved the risk assessment of cardiac transthyretin amyloidosis (ATTR-CA) patients substantially. However, to date, all staging systems were validated in treatment-naive ATTR-CA patients. The introduction of tafamidis led to significant changes in the disease trajectory of ATTR-CA, indicating that it may also have an impact on the prognostic accuracy of these staging systems. Purpose Thus, we sought to assess whether the prognostic value of the National Amyloidosis Centre (NAC) staging system, currently considered as the most accurate, is sustained in ATTR-CA patients treated with tafamidis. Methods This retrospective observational study included ATTR-CA patients treated with tafamidis. Patients were continuously followed from treatment initiation to time of death. NT-proBNP and eGFR data collected at baseline were used to stratify patients into low (stage I), intermediate (stage II) and high-risk (stage III) subgroups according to the NAC staging system. Kaplan-Meier analyses were conducted to illustrate overall survival. Differences in overall survival between subgroups were assessed by log rank tests. P-values <0.05 were considered statistically significant. Results A total of 166 ATTR-CA patients (95.2% wild-type) were enrolled. 81 (48.8%), 51 (30.7%) and 34 (20.5%) patients were stratified into stages I, II and III, respectively. Median follow-up was 539 [323-865] days, during which 20 deaths were recorded. Overall survival of the subgroups over time is demonstrated in figure 1. The probability of overall survival was significantly lower for patients in stage III compared to patients in stages I (log rank; p=0.002) and II (log rank; p=0.031). However, no differences in the probability of overall survival were identified between patients in stage I and II (log rank; p=0.679). Conclusions In this cohort of ATTR-CA patients treated with tafamidis, the NAC staging system effectively identified patients at elevated risk of mortality. However, the distinction in survival rates between low- and intermediate-risk groups was less pronounced, suggesting that tafamidis may have a stronger prognostic impact in these groups.Overall Survival across NAC Stages

A practical nomogram and risk stratification system for predicting in-hospital mortality of patients with non-acute myocardial infarction related cardiogenic shock

Abstract Background The morbidity and mortality of Cardiogenic Shock(CS) remain high despite the advance in management these years1.As acute myocardial infarction (AMI) is considered to be the most common reason for cardiogenic shock,Non-AMI related CS is excluded from the majority of CS studies and remains largely understudied2. Considering its inherent complexity and hemodynamically multiplicity, it is needed to focusing on these patients to identify specific risk factors, which may be conducive to the promotion of critically CS patients with early decision and timely intervention. Purpose In this study,we sought to investigate the variables which are predictive of in hospital mortality in non AMI related CS patients, developed and validated a practical nomogram for risk quantification. Methods 1298 patients and 548 patients with cardiogenic shock from the MIMIC-IV (version 1.0) and MIMIC-III(version1.4) databaes were included in the study after excluding acute myocardial infarction. We used in-hospital death and 30 day survival as the end points. Lasson and logistic regression analysis were used to identify statistically significant predictors which were finally involved in the nomogram. The predictive performance of the nomogram was evaluated by Harrell’s concordance index (C-index) and calibration after comparing with commonly used ICU scores for in-hospital death.Lastly, we plotted Kaplan-Meier curves of three subgroup classified by the identified cutoff values of the nomogram to further assess the discriminative ability of the prognosis. Results The in-hospital mortality of patients with non-AMI related CS is about 36.6%.After the analysis of regression, age, heart rate, wbc, albumin, lactic acid, GCS score, urine volume, using vasopressor were identified as the most critical factors for the in-hospital death. Based on the these results, a nomogram for predicting in-hospital death was established.The calibration plot also shows good consistency between nomogram prediction and actual in-hospital mortality.In addition, compared with other scores, the AUC value of nomogram was 0.806 (95% CI = 0.799-0.831) in the training queue, 0.814 (95% CI = 0.771-0.852) in the internal validation queue and 0.730 (95% CI = 0.690-0.767) in the external validation set, which was significantly higher than other commonly used ICU scoring systems(SAPSII, APSIII and SOFA).Also, three risk subgroups were created using two boundary points (303 and 339) of the nomogram score and the survival curve shows that there were significant differences in the 30 day survival of each subgroup. Conclusion A prognostic nomogram and risk stratification system of non-AMI related CS were established and verified, which can provide a practical tool for individualized clinical management of patients.Workflow of the study.Nomogram for non-AMI related CS patients

Development and validation of a novel prognostic prediction system based on GLIM-defined malnutrition for colorectal cancer patients post-radical surgery.

Malnutrition often occurs in patients with colorectal cancer. This study aims to develop a predictive model based on GLIM criteria for patients with colorectal cancer who underwent radical surgery. From December 2015 to May 2021, patients with colorectal cancer who underwent radical surgery at our center were recruited for this study. We prospectively collected data on GLIM-defined malnutrition and other clinicopathological characteristics. Using Cox regeneration, we developed a novel nomogram for prognostic prediction, which was validated and compared to traditional nutritional factors for predictive accuracy. Among the 983 patients enrolled in this study, malnutrition was identified in 233 (23.70%) patients. Multivariate analysis indicated that GLIM-defined malnutrition is the independent risk factor for overall survival (HR = 1.793, 95% CI = 1.390-2.313 for moderate malnutrition and HR = 3.485, 95% CI = 2.087-5.818 for severe malnutrition). The novel nomogram based on the GLIM criteria demonstrated a better performance than existing criteria, with AUC of 0.729, 0.703, and 0.683 for 1-year, 3-year, and 5-year OS, respectively, in the validation cohort. In addition, the risk score determined by this system exhibited significantly poorer short-term and long-term clinical outcomes in high-risk groups in both malnourished and well-nourished patients. Combining handgrip strength, serum albumin level, and TNM stage would help improve the predictive effect of GLIM criteria for colorectal cancer patients post-radical surgery and benefit the individual prognostic prediction of colorectal cancer.

Machine learning identification of NK cell immune characteristics in hepatocellular carcinoma based on single-cell sequencing and bulk RNA sequencing.

Hepatocellular carcinoma (HCC) is a highly malignant tumor; however, its immune microenvironment and mechanisms remain elusive. Single-cell sequencing allows for the exploration of immune characteristics within tumor at the cellular level. However, current knowledge regarding the roles of different immune cell populations in liver cancer progression is limited. The main objective of this study is to identify molecular markers with NK cell immune characteristics in hepatocellular carcinoma using various machine learning methods based on Single-Cell Sequencing and Bulk RNA Sequencing. We collected samples from eight normal liver tissues and eight HCC tumor tissues and performed single-cell RNA sequencing for immune cell clustering and expression profile analysis. Using various bioinformatic approaches, we investigated the immune phenotype associated with natural killer (NK) cells expressing high CD7 level. In addition, we verified the role of CD7 in the growth of HCC after NK cell and HCC cells cocultured by RT-qPCR, MTS and Flow cytometer experiments. Finally, we constructed a machine learning model to develop a prognostic prediction system for HCC based on NK cell-related genes. Through single-cell typing, we found that the proportions of hepatocytes and NK cells were significantly elevated in the tumor samples. Moreover, we found that the expression of CD7 was high in HCC and correlated with prognosis. More importantly, Overexpression of CD7 in NK cells significantly inhibited the activity of MHCC97 cells and increased the number of apoptosis of HCC cells (p < 0.05). Furthermore, we observed that NK cells with high CD7 expression were associated with an activated immune phenotype. Our study found that CD7 is an important biomarker for assessing immune status and predicting survival of HCC patients; hence, it is a potential target for immune therapy against HCC.

Multi-level attention graph feature fusion smooth prognostics approach for aircraft engines remaining useful life prediction

In the development of a prognostic and health management system, it is a challenge to mine the degradation characteristics, estimate the RUL reliably and smoothly, and explain the RUL prediction results from the multi-sensor condition monitoring data collected under the non-fixed-length equipment operation cycle and multi-operating conditions. In this paper, a Multi-level Attention Graph feature Fusion Smooth Prognostics Approach (MAGF-SPA) is proposed to achieve accurate, smooth, and interpretable RUL prediction results. In this method, firstly, multivariate time series (MTS) are transformed into graph signals from a purely data-driven perspective. Secondly, the four-level feature extraction strategy, which includes node-level, subgraph-level, cyclical-level, and temporal-level feature extraction, is designed to extract the inherent hidden degradation characteristics of MTS. Finally, a smoothing trick proposed in this paper can optimise the RUL prediction value corresponding to the degradation characteristics in real time. Experimental results show that the proposed method achieves state-of-the-art on the N-CMAPSS dataset.

Exploring the significance and potential mechanisms of hippo pathway-associated genes in prognosis of glioma patients

PurposeDespite the efforts of countless researchers to develop glioma treatment strategies, the current therapeutic effect of glioma is still not ideal, and it is necessary to further explore the mechanism to guide treatment. Thus, this study aims to introduce a novel approach for predicting patient prognosis and guiding further treatment interventions.MethodsInitially, we conducted a differential gene expression analysis to identify Hippo pathway-associated genes overexpressed in tumors and determined genes correlated with prognosis. Subsequently, employing cluster analysis, we categorized samples into two groups and performed further analyses including prediction, immune cell infiltration abundance, and drug response rates. We utilized weighted gene co-expression analysis to reveal gene sets with high co-variation, delineate inter-sample gene correlation patterns, and conduct enrichment analysis. Prognostic models were built using ten machine learning algorithms combined in 101 different combinations, followed by evaluation and validation. Immune infiltration analysis, differential expression analysis of depleted T cell-related markers, drug sensitivity analysis, and exploration of pathway dysregulation were performed for different risk groups. Quality control and batch integration were performed, and single-cell data were analyzed using dimensionality reduction clustering algorithms and annotation tools to evaluate the activity of the prognostic model in malignant cells.ResultsWe conducted data filtering to identify genes overexpressed in tumors, intersecting these genes with Hippo pathway-related genes, identifying 62 genes correlated with prognosis, and performing cluster analysis to divide tumor tissues into two groups. Cluster 2 exhibited a poorer prognosis and demonstrated differences in immune cell infiltration. Utilizing weighted gene co-expression analysis on Cluster 2, we identified gene modules, conducted functional enrichment analysis, and delineated pathways. Employing a combined model based on ten machine learning algorithm combinations, we selected the optimal prognostic model system and validated the model’s predictive ability within the dataset. Through immune-related analysis and drug sensitivity analysis, we uncovered differences in immune infiltration and varying sensitivities to chemotherapy drugs. Additionally, the enrichment analysis of gene set revealed discrepancies in upregulation within relevant pathways between the high and low-risk groups. Finally, annotation and evaluation of malignant cells via single-cell analysis showed increased activity of the prognostic model and variations in distribution across different prognostic levels in malignant cells.ConclusionThis study introduces a novel approach utilizing the Hippo pathway and associated genes for glioma prognosis research, demonstrating the potential and significance of this method in evaluating the outcome for patients with glioma. These findings hold substantial clinical significance in guiding therapy and predicting outcomes for individuals diagnosed with glioma, offering significant clinical utility.

Spatial layout optimization model integrating layered attention mechanism in the development of smart tourism management

Tourism demand projection is paramount for both corporate operations and destination management, facilitating tourists in crafting bespoke, multifaceted itineraries and enriching their vacation experiences. This study proposes a multi-layer self attention mechanism recommendation algorithm based on dynamic spatial perception, with the aim of refining the analysis of tourists’ emotional inclinations and providing precise estimates of tourism demand. Initially, the model is constructed upon a foundation of multi-layer attention modules, enabling the semantic discovery of proximate entities to the focal scenic locale and employing attention layers to consolidate akin positions, epitomizing them through contiguous vectors. Subsequently, leveraging tourist preferences, the model forecasts the likelihood of analogous attractions as a cornerstone for the recommendation system. Furthermore, an attention mechanism is employed to refine the spatial layout, utilizing the forecasted passenger flow grid to infer tourism demand across multiple scenic locales in forthcoming periods. Ultimately, through scrutiny of data pertaining to renowned tourist destinations in Beijing, the model exhibits an average MAPE of 8.11%, markedly surpassing benchmarks set by alternative deep learning models, thereby underscoring its precision and efficacy. The spatial layout optimization methodology predicated on a multi-layer attention mechanism propounded herein confers substantive benefits to tourism demand prognostication and recommendation systems, promising to elevate the operational standards and customer contentment within the tourism sector.

Robust feature design for early detection of ball screw preload loss

The ball screw is a critical device for precision linear motion control that has widespread applications in industrial robots, computer numerical control (CNC) machines, and high-precision leveling systems, among others. Because high-precision positioning is ensured by the addition of a preload to the ball screw system, it is crucial to detect and monitor the loss of preload at the earliest possible stage of degradation. The degradation process of the ball screw can be characterized in two stages: the initial reduction of preload without backlash, followed by a loss of preload with an emergence of backlash. To explore the change of the ball screw dynamics caused by degradation, a novel fixed cycle feature test (FCFT) is implemented in combination with multi-level mass experiments and a run-to-failure (RTF) test. The relationships of the ball screw dynamics with preload, worktable mass, and axis position are investigated, with a focus on the axial natural frequency as an indicator of preload loss. Experimental results validate the axial natural frequency’s role as a reliable early detector of preload loss for interventive use in a prognostic system.

High-accuracy gearbox fault detection using deep learning on vibrational data

Abstract In the face of escalating demands for reliability in industrial machinery, this study introduces an advanced deep-learning model aimed at the early detection of faults in rotating gear systems. Addressing the need for timely fault diagnosis to prevent operational disruptions and financial setbacks, our work utilizes a novel neural network approach applied to vibrational data from Kaggle’s Gearbox Fault Diagnosis Dataset. The methodology involves data preprocessing steps, including normalization and one-hot encoding, followed by training a sequential neural network with multiple dense layers and dropout for regularization. The model, trained using the Adam optimizer and evaluated over 50 epochs, significantly outperforms traditional machine learning techniques, achieving a remarkable 98.63% accuracy in distinguishing between healthy and compromised gear conditions. This research marks a significant stride in predictive maintenance, providing a robust foundation for future development toward prognostic health management systems that anticipate maintenance needs and ensure uninterrupted industrial productivity.

The clinical prognostic risk stratification system for HIV infected hepatocellular carcinoma

BackgroundPatients with human immunodeficiency virus (HIV) are more susceptible to liver cancer because of their compromised immune system. There is no specific prognostic model for HIV-infected hepatocellular carcinoma (HCC) patients. MethodsClinical data of 85 patients with HIV-infected HCC was divided into a 7:3 ratio for training and internal validation sets, while the data of 23 patients with HIV-infected HCC was served as the external validation set. Data of 275 HIV-negative HCC patients was considered as external HIV-negative validation set. Variables associated with overall survival (OS) in the training set were used to develop the HIV-infected HCC prognosis (HIHP) model. The model was tested in the internal and external validation sets. The predictive accuracy of the model was assessed with conventional HIV-negative HCC prognostic scoring systems. ResultsIn the training set, variables independently associated with OS in multivariable analysis were organ involvement and tumor number. The HIHP model demonstrated a significant association with OS in the training set, with a median OS of 13 months for low risk, 7 months for medium risk, and 3 months for high risk (p < 0.001). The HIHP model showed a significant association with OS, and exhibited greater discriminative abilities compared to conventional HIV-negative HCC prognostic models both in the internal and external validation sets. In the external HIV-negative validation set, the HIHP model did not show better discrimination than conventional HIV-negative HCC scores. ConclusionThe new model presented in the work provided a more accurate prognostic prediction of OS in HIV-infected HCC patients. However, the model is not applicable to patients with HIV-negative HCC.

The Tumour Immune Microenvironment Drives Survival Outcomes and Therapeutic Response in an Integrated Molecular Analysis of Gastric Adenocarcinoma.

We performed an integrated analysis of molecular classification systems proposed by The Cancer Genome Atlas (TCGA), the Asian Cancer Research Group (ACRG) and the Tumour Microenvironment Score (TME) to identify which classification scheme(s) are most promising to pursue in subsequent translational investigations. Supervised machine learning classifiers were created using 10-fold nested cross-validation for TCGA, ACRG and TME subtypes and applied to 2,202 gastric cancer patients from 11 separate publicly available datasets. Overall survival was assessed with a multivariable Cox proportional hazards model. A propensity score matched analysis was performed to evaluate the subgroup effect of adjuvant chemotherapy on molecular subtypes. A public external cohort comprised of metastatic gastric cancer treated with immunotherapy was used to externally validate the molecular subtypes. Classification models for TCGA, ACRG and TME achieved an accuracy ± standard deviation of 89.5% ± 0.04, 84.7% ± 0.04 and 89.3% ± 0.02, respectively. We identified the TME score as the only significantly prognostic classification system (HR 0.54 [95% CI 0.39, 0.74], global Wald test p<0.001). In our subgroup analysis, patients who received adjuvant chemotherapy achieved greater survival with increasing TME score (HR 0.47 [95% CI 0.29, 0.74], interaction p<0.05). The combination of TME High and microsatellite instability (MSI) scores significantly outperformed MSI as a univariable predictor of immunotherapy response. We conclude that the Tumour Microenvironment Score is a predominate driver of prognosis as well as chemotherapy and immunotherapy-related outcomes in gastric cancer. This paper provides a foundation for additional analyses and translational work.

New histological risk grading system for prediction of lymph node metastasis in patients with penile cancer

AbstractInguinal lymph node surgery is a standard treatment for penile cancer patients with intermediate or high risk for lymph node metastasis (LNM) according to European Association of Urology (EAU) risk grading. We are proposing a more objective histological prognostic grading system for inguinal LNM in these patients. We assessed worst pattern of invasion, lymphocytic host response, lymphovascular invasion, and perineural invasion in a population-based cohort of 306 penile cancer patients. Patients were classified into low, intermediate, and high risk for inguinal LNM. There was a significant association both between risk groups and pT stage (p &lt; 0.001) and between risk groups and LNM. Univariate logistic regression showed 25.43 times higher odds of LNM for patients in the intermediate risk group compared with the low risk group (odds ratio (OR) 25.43; 95% confidence interval (CI): 5.94–108.97) and a 177.13 times higher odds in the high risk group compared to the low risk group (OR 177.13; 95% CI: 40.09–782.51). When comparing our histological risk grading with the EAU grading, we found a higher sensitivity, of 51.28% (95% CI: 45.68–56.88) versus 37.09% (95% CI: 31.68–42.50), as well as a higher area under the curve (0.86; 95% CI: 0.81–0.89; versus 0.65; 95% CI: 0.58–0.71) with our grading system. While our grading classified 111 patients as low risk, only 31 were considered low risk for LNM according to the EAU risk classification. The new histological risk grading system shows a higher sensitivity and includes a higher number of patients in the low risk group in whom lymph node surgery could be avoided, reducing morbidity and costs.

Predictive value of cuproptosis and disulfidptosis-related lncRNA in head and neck squamous cell carcinoma prognosis and treatment

ObjectiveHead and neck squamous cell carcinoma (HNSCC) is a highly lethal and prevalent malignant tumor with a poor prognosis due to its high recurrence rate, This study aims to develop a prognostic index for HNSCC patients based on Cuproptosis and Disulfidptosis-related long noncoding RNA. MethodsGene expression and clinical data for HNSCC were obtained from The Cancer Genome Atlas (TCGA). Using Lasso regression and multivariate Cox regression, we established a risk scoring model. The predictive ability of the nomogram, based on clinical features and risk scores, was verified using receiver operating characteristics and calibration curves. We compared independent prognostic parameters, risk score distribution, and survival between high-risk and low-risk groups, followed by preliminary validity evaluations of the model. ResultsOur systematic evaluation of prognostic risk provides a new direction for improving the survival prognosis of HNSCC patients in clinical practice, The model effectively categorized patients into high- and low-risk groups with distinct outcomes, identifying numerous gene mutations in these groups, A low-risk score was associated with a better prognosis and higher survival rates. ConclusionThe risk score prognostic prediction system developed in this study shows potential efficacy in predicting the prognosis of HNSCC patients and has practical applications in clinical settings.

Formation of Bachelor`s Skills in the Field of Machine Learning and Intelligent Data Analysis

The article presents the content of the educational disciplines “Workshop on Python Programming” and “Fundamentals of Artificial Intelligence”, included in the module “Data Analysis. Machine learning. Artificial Intelligence”, implemented in Ural universities. Modern teachers note that when preparing the next generation of teachers, the priority should be their acquisition of experience in using artificial intelligence tools in teaching. The objectives of mastering the module are developing students’ skills in the field of neural network mathematical modeling, developing knowledge about basic data analysis algorithms, development of skills in visualization and interpretation of data to solve applied problems using object-oriented programming technologies and artificial neural network technologies. As part of project activities, students gain experience in data mining by completing research projects (for example, a project on comparative assessment of the effectiveness of multilayer perceptron learning algorithms) and applied projects (for example, on the development of a neural network system for predicting the success of schoolchildren’s research work; on the development of a neural network system for predicting student attendance training sessions). At USPU, software systems have been developed in Python that implement the presented neural network prognostic systems. Educational and methodological materials for the disciplines of the module include video lectures and presentations for them, laboratory work (including those based on GoogleColab notebooks), datasets, test sets, theory questions and practical tasks for exams and tests. The effectiveness of the developed teaching methodology is confirmed by the results of a pedagogical experiment. Keywords: neural network technologies, data mining, predictive systems, machine learning, content of the academic discipline

-KIDS: A novel feature evaluation in the ultrahigh-dimensional right-censored setting, with application to Head and Neck Cancer.

Recent advances in sequencing technologies have allowed collection of massive genome-wide information that substantially enhances the diagnosis and prognosis of head and neck cancer. Identifying predictive markers for survival time is crucial for devising prognostic systems, and learning the underlying molecular driver of the cancer course. In this paper, we introduce -KIDS, a model-free feature screening procedure with false discovery rate (FDR) control for ultrahigh dimensional right-censored data, which is robust against unknown censoring mechanisms. Specifically, our two-stage procedure initially selects a set of important features with a dual screening mechanism using nonparametric reproducing-kernel-based ANOVA statistics, followed by identifying a refined set (of features) under directional FDR control through a unified knockoff procedure. The finite sample properties of our method, and its novelty (in light of existing alternatives) are evaluated via simulation studies. Furthermore, we illustrate our methodology via application to a motivating right-censored head and neck (HN) cancer survival data derived from The Cancer Genome Atlas, with further validation on a similar HN cancer data from the Gene Expression Omnibus database. The methodology can be implemented via the R package DSFDRC, available in GitHub.

99mTc]Tc-hydroxydiphosphonate uptake in soft tissue is associated with amyloid load in subcutaneous abdominal fat tissue and mortality in wild-type transthyretin amyloidosis patients.

Bone scintigraphy is key to non-invasively diagnosing wild-type transthyretin (ATTRwt) amyloidosis, and is mainly used to assess cardiac radiotracer uptake. However, extracardiac radiotracer uptake is also observed. We investigated whether intensity of soft tissue radiotracer uptake is associated with amyloid load in subcutaneous abdominal fat tissue and with mortality. This prospective cohort study included 94 ATTRwt amyloidosis patients and 26 amyloid-negative heart failure controls who underwent whole-body [99mTc]Tc-hydroxydiphosphonate scintigraphy. Site-to-background ratios were calculated for heart, elbows, subcutaneous tissue, shoulders and wrists on anterior planar bone scintigraphy images using rib and whole-body radiotracer uptake as background. Fat tissue aspirates were stained with Congo red to grade amyloid load. Site-to-rib ratios were compared between ATTRwt amyloidosis patients and controls, and associations of site-to-background ratio with Congo red score and all-cause mortality were studied. ATTRwt amyloidosis patients had higher soft tissue-to-rib, heart-to-rib and heart-to-whole body ratios compared with controls. The intensity of soft tissue uptake was positively associated with amyloid load in fat tissue in ATTRwt amyloidosis patients. Estimated glomerular filtration rate, N-terminal brain natriuretic propeptide, high-sensitivity cardiac troponin T (hs-cTnT), and the prognostic Mayo and NAC staging system were associated with all-cause mortality in univariable models. Soft tissue/rib ratio, hs-cTnT and the prognostic staging systems were the only two variables that were independently associated withall-cause mortality. Soft tissue radiotracer uptake on bone scintigraphy in ATTRwt amyloidosis patients is positively associated with amyloid load in abdominal fat tissue and is independently associated with mortality.

Exploring the accuracy of tooth loss prediction between a clinical periodontal prognostic system and a machine learning prognostic model.

The aim of this analysis was to compare a clinical periodontal prognostic system and a developed and externally validated artificial intelligence (AI)-based model for the prediction of tooth loss in periodontitis patients under supportive periodontal care (SPC) for 10 years. Clinical and radiographic parameters were analysed to assign tooth prognosis with a tooth prognostic system (TPS) by two calibrated examiners from different clinical centres (London and Pittsburgh). The prediction model was developed on the London dataset. A logistic regression model (LR) and a neural network model (NN) were developed to analyse the data. These models were externally validated on the Pittsburgh dataset. The primary outcome was 10-year tooth loss in teeth assigned with 'unfavourable' prognosis. A total of 1626 teeth in 69 patients were included in the London cohort (development cohort), while 2792 teeth in 116 patients were included in the Pittsburgh cohort (external validated dataset). While the TPS in the validation cohort exhibited high specificity (99.96%), moderate positive predictive value (PPV = 50.0%) and very low sensitivity (0.85%), the AI-based model showed moderate specificity (NN = 52.26%, LR = 67.59%), high sensitivity (NN = 98.29%, LR = 91.45%), and high PPV (NN = 89.1%, LR = 88.6%). AI-based models showed comparable results with the clinical prediction model, with a better performance in specific prognostic risk categories, confirming AI prediction model as a promising tool for the prediction of tooth loss.

Assessment of Endoscopy-Based Scoring Systems for Prognostication in Ulcerative Colitis: A Comparative Analysis.

Endoscopy-based scoring systems, including Mayo Endoscopic Score (MES), Modified Mayo Endoscopic Score (MMES), and Degree of Ulcerative Colitis Burden of Luminal Inflammation (DUBLIN) Score, have been introduced to evaluate UC prognosis. This study aims to compare their predictive capacity for clinical outcomes in UC patients. Consecutive UC patients from a tertiary hospital were included. The primary outcome was acute severe ulcerative colitis (ASUC), and secondary outcomes were UC-related admission, medication treatment escalation, disease extension and surgery. Predictive performance was assessed using receiver operating characteristic (ROC) curves. Among 300 patients, 15.3% developed ASUC. Robust correlations were observed among the three scoring systems and were with elevated serum inflammatory markers. The DUBLIN score exhibited superior predictive ability for UC-related admission (AUC 0.751; 95%CI 0.698-0.799) and medication treatment escalation (AUC 0.735; 95% CI 0.681-0.784). No statistical differences were found among three scoring systems for predicting ASUC, disease extension, and surgery. Employing respective cut-offs of 2, 11.25, and 3, higher MES (HR = 3.859, 95% CI 1.636-9.107, p = 0.002), MMES (HR = 3.352, 95% CI 1.879-5.980, p < 0.001), and DUBLIN score (HR = 5.619, 95% CI 2.378-13.277, p < 0.001) were associated with an increased risk of developing ASUC. The DUBLIN score, assessing the overall inflammatory burden of the intestinal tract, outperforms the MMES in predicting admission and medication treatment escalation related to UC. Its integration into clinical practice has the potential to enhance risk stratification for patients with UC.

Enhancing qualification via the use of diagnostics and prognostics techniques

AbstractQualification is a process that demonstrates whether a product meets or exceeds specified requirements. Testing and data analysis performed within a qualification procedure should verify that products satisfy those requirements, including reliability requirements. Most of the electronics industry qualifies products using procedures dictated within qualification standards. A review of common qualification standards reveals that those standards do not consider customer requirements or the product physics‐of‐failure in that intended application. As a result, qualification, as represented in the reviewed qualification standards, would not meet our definition of qualification for reliability assessment. This paper introduces the application of diagnostics and prognostics techniques to analyze real‐time data trends while conducting qualification tests. Diagnostics techniques identify anomalous behavior exhibited by the product, and prognostics techniques forecast how the product will behave during the remainder of the qualification test and how the product would have behaved if the test continued. As a result, combining diagnostics and prognostics techniques can enable the prediction of the remaining time‐to‐failure for the product undergoing qualification. Several ancillary benefits related to an improved testing strategy, parts selection and management, and support of a prognostics and health management system in operation also arise from applying prognostics and diagnostics techniques to qualification.