Forecasting Trial Milestones: A Predictive Analysis for Early Termination of the SOUL Study.

INTRODUCTION: Semaglutide, a glucagon-like peptide 1 receptor agonist (GLP1RA), is available in both parenteral and oral preparations. Studies of injectable preparations have convincingly demonstrated its beneficial effect on major adverse cardiac events (MACE). This predictive analysis was undertaken to forecast early termination of the SOUL trial (oral semaglutide) as well as the primary events. METHODS: SOUL is a multicenter, double-blind, placebo-controlled randomized controlled trial (RCT) evaluating the reduction in MACE associated with oral semaglutide versus placebo in patients with type 2 diabetes (T2D) and cardiovascular (CV) disease. A sample of 9642 participants will be followed for 5 years and 5 months. A random-effects model meta-analysis, pooling hazard ratios from previous RCTs, was conducted using R software to inform the predictive model. The background CV event rates from the placebo arms of previous RCTs with semaglutide were matched with the pre-adjudicated assumptions of the SOUL trial to create the predictive model. The truncated trial duration, MACE, and its individual components in the intervention and placebo arms were estimated. The predicted difference between the two groups was estimated using the chi-squared test. RESULTS: A pooled analysis of 10,013 patients revealed a significant reduction in the number of MACEs associated with semaglutide (HR 0.79, 95% CI 0.69-0.91). Predictive analysis indicated that 1225 events would be achieved by 3.78 years, suggesting premature termination. CONCLUSION: The mathematical model based on the meta-analysis predicts that the SOUL study on oral semaglutide will be terminated early, with oral semaglutide showing benefits in terms of MACE compared to placebo. If the SOUL study corroborates the findings of this model, it may not only form the basis for the calculation of power but also define the duration of such studies, reducing costs and easing the process of designing cardiovascular outcome trials (CVOTs). PROTOCOL REGISTRATION: INPLASY202460061.

Latent profiles as predictors of response to instruction for students with reading difficulties.

The program code developed by others is appropriately cited in the text and listed in the references section. The raw and processed data on which study conclusions are based are not available. The statistical syntax needed to reproduce analyses in the article is available upon request. The methods section provides references for the materials described therein. We report how we determined our sample size, all data exclusions, all manipulations, and all measures in the study, and we follow APA Style Journal Article Reporting Standards. This study's design, hypotheses, and data analytic plan were not pre-registered. Prior research supports the need for elementary-aged students with reading difficulties (RD) to receive explicit systematic small group evidence-based reading instruction. Yet for many students, simply receiving an evidence-based reading instruction in a small group setting is insufficient to reach the progress milestones needed to meet grade level reading standards. The current study examined whether: (1) elementary school students with RD constitute a homogeneous or heterogeneous groups when considering their basic language and cognitive skills (using a latent profile analysis), and (2) if latent profiles are predictive of response to reading comprehension instruction (using a mixed modeling approach). The sample consisted of 335 students, including students with RD and typical students (n = 57). The results revealed heterogeneity within students with RD - there were two distinct profiles, with one having higher basic language (reading fluency and decoding) and cognitive (verbal domain productivity, cognitive flexibility, working memory) skills and lower attention skills, and the other having stronger attention skills and lower basic language and cognitive skills. The findings also suggested that latent profiles were predictive of response to reading comprehension instruction. Our results provide a convincing argument for leading the field in the direction of developing customized interventions. It is conceivable, but remains to be further examined, that researchers and educators could potentially improve reading outcomes through providing a customized reading intervention to a student based on their cognitive-language profile.

IntelliGenes: Interactive and user-friendly multimodal AI/ML application for biomarker discovery and predictive medicine.

Artificial intelligence (AI) and machine learning (ML) have advanced in several areas and fields of life; however, its progress in the field of multi-omics is not matching the levels others have attained. Challenges include but are not limited to the handling and analysis of high volumes of complex multi-omics data, and the expertise needed to implement and execute AI/ML approaches. In this article, we present IntelliGenes, an interactive, customizable, cross-platform, and user-friendly AI/ML application for multi-omics data exploration to discover novel biomarkers and predict rare, common, and complex diseases. The implemented methodology is based on a nexus of conventional statistical techniques and cutting-edge ML algorithms, which outperforms single algorithms and result in enhanced accuracy. The interactive and cross-platform graphical user interface of IntelliGenes is divided into three main sections: (i) Data Manager, (ii) AI/ML Analysis, and (iii) Visualization. Data Manager supports the user in loading and customizing the input data and list of existing biomarkers. AI/ML Analysis allows the user to apply default combinations of statistical and ML algorithms, as well as customize and create new AI/ML pipelines. Visualization provides options to interpret a diverse set of produced results, including performance metrics, disease predictions, and various charts. The performance of IntelliGenes has been successfully tested at variable in-house and peer-reviewed studies, and was able to correctly classify individuals as patients and predict disease with high accuracy. It stands apart primarily in its simplicity in use for nontechnical users and its emphasis on generating interpretable visualizations. We have designed and implemented IntelliGenes in a way that a user with or without computational background can apply AI/ML approaches to discover novel biomarkers and predict diseases.

Full Bayesian analysis of double seasonal autoregressive models with real applications.

We present a full Bayesian analysis of multiplicative double seasonal autoregressive (DSAR) models in a unified way, considering identification (best subset selection), estimation, and prediction problems. We assume that the DSAR model errors are normally distributed and introduce latent variables for the model lags, and then we embed the DSAR model in a hierarchical Bayes normal mixture structure. By employing the Bernoulli prior for each latent variable and the mixture normal and inverse gamma priors for the DSAR model coefficients and variance, respectively, we derive the full conditional posterior and predictive distributions in closed form. Using these derived conditional posterior and predictive distributions, we present the full Bayesian analysis of DSAR models by proposing the Gibbs sampling algorithm to approximate the posterior and predictive distributions and provide multi-step-ahead predictions. We evaluate the efficiency of the proposed full Bayesian analysis of DSAR models using an extensive simulation study, and we then apply our work to several real-world hourly electricity load time series datasets in 16 European countries.

A fresh-cut papaya freshness prediction model based on partial least squares regression and support vector machine regression.

This study investigated the physicochemical and flavor quality changes in fresh-cut papaya that was stored at 4 °C. Multivariate statistical analysis was used to evaluate the freshness of fresh-cut papaya. Aerobic plate counts were selected as a predictor of freshness of fresh-cut papaya, and a prediction model for freshness was established using partial least squares regression (PLSR), and support vector machine regression (SVMR) algorithms. Freshness of fresh-cut papaya could be well distinguished based on physicochemical and flavor quality analyses. The aerobic plate counts, as a predictor of freshness of fresh-cut papaya, significantly correlated with storage time. The SVMR model had a higher prediction accuracy than the PLSR model. Combining flavor quality with multivariate statistical analysis can be effectively used for evaluating the freshness of fresh-cut papaya.

A comprehensive exploration of artificial intelligence in orthopaedics within lower-middle-income countries: a narrative review.

Integrating Artificial Intelligence (AI) in orthopaedic within lower-middle-income countries (LMICs) promises landmark improvement in patient care. Delving into specific use cases-fracture detection, spine imaging, bone tumour classification, and joint surgery optimisation-the review illuminates the areas where AI can significantly enhance orthopaedic practices. AI could play a pivotal role in improving diagnoses, enabling early detection, and ultimately enhancing patient outcomes- crucial in regions with constrained healthcare services. Challenges to the integration of AI include financial constraints, shortage of skilled professionals, data limitations, and cultural and ethical considerations. Emphasising AI's collaborative role, it can act as a complementary tool working in tandem with physicians, aiming to address gaps in healthcare access and education. We need continued research and a conscientious approach, envisioning AI as a catalyst for equitable, efficient, and accessible orthopaedic healthcare for patients in LMICs.

Atorvastatin Treatment Significantly Increased the Concentration of Bone Marrow-Derived Mononuclear Cells and Transcutaneous Oxygen Pressure and Lowered the Pain Scale after Bone Marrow Cells Treatment in Patients with "No-Option" Critical Limb Ischaemia.

BACKGROUND: The present study investigated the outcomes and possible predictive factors of autologous bone marrow cells (BMCs) therapy in patients with "no-option" critical limb ischaemia (CLI). It was focused on exploring the clinical background and prior statin and renin-angiotensin system (RAS)-acting agents pharmacotherapy related to the therapeutic efficacy of BMCs treatment. METHODS: In the present study, we reviewed thirty-three patients (mean age 64.9 ± 10 years; 31 males) with advanced CLI after failed or impossible revascularisation, who were treated with 40 mL of autologous BMCs by local intramuscular application. Patients with limb salvage and wound healing (N = 22) were considered as responders to BMCs therapy, and patients with limb salvage and complete ischemic wound healing (N = 13) were defined as super-responders. Logistic regression models were used to screen and identify the prognostic factors, and a receiver operating characteristics (ROC) curve, a linear regression, and a survival curve were drawn to determine the predictive accuracy, the correlation between the candidate predictors, and the risk of major amputation. RESULTS: Based on the univariate regression analysis, baseline C-reactive protein (CRP) and transcutaneous oxygen pressure (TcPO2) values were identified as prognostic factors of the responders, while CRP value, ankle-brachial index (ABI), and bone marrow-derived mononuclear cells (BM-MNCs) concentration were identified as prognostic factors of the super-responders. An area under the ROC curve of 0.768 indicated good discrimination for CRP > 8.1 mg/L before transplantation as a predictive factor for negative clinical response. Linear regression analysis revealed a significant dependence between the levels of baseline CRP and the concentration of BM-MNCs in transplanted bone marrow. Patients taking atorvastatin before BMCs treatment (N = 22) had significantly improved TcPO2 and reduced pain scale after BMCs transplant, compared to the non-atorvastatin group. Statin treatment was associated with reduced risk for major amputation. However, the difference was not statistically significant. Statin use was also associated with a significantly higher concentration of BM-MNCs in the transplanted bone marrow compared to patients without statin treatment. Patients treated with RAS-acting agents (N = 20) had significantly reduced pain scale after BMCs transplant, compared to the non-RAS-acting agents group. Similar results, reduced pain scale and improved TcPO2, were achieved in patients treated with atorvastatin and RAS-acting agents (N = 17) before BMCs treatment. Results of the Spearman correlation showed a significant positive correlation between CLI regression, responders, and previous therapy before BMCs transplant with RAS-acting agents alone or with atorvastatin. CONCLUSIONS: CRP and TcPO2 were prognostic factors of the responders, while CRP value, ABI, and BM-MNCs concentration were identified as predictive factors of the super-responders. Atorvastatin treatment was associated with a significantly increased concentration of BM-MNCs in bone marrow concentrate and higher TcPO2 and lower pain scale after BMCs treatment in CLI patients. Similarly, reduced pain scales and improved TcPO2 were achieved in patients treated with atorvastatin and RAS-acting agents before BMCs treatment. Positive correlations between responders and previous treatment before BMCs transplant with RAS-acting agents alone or with atorvastatin were significant.

[Carbon Reduction Analysis of Life Cycle Prediction Assessment of Hydrogen Fuel Cell Vehicles：Considering Regional Features and Vehicle Type Differences].

As one of the important paths for China to achieve the "dual carbon" strategy， developing hydrogen fuel cell vehicles is currently being promoted in various regions across the country， including passenger cars， coaches， and heavy-duty trucks. Quantifying the carbon reduction potential of hydrogen fuel cell vehicles for different vehicle types and regions has become a hot research topic. Using a life cycle assessment method that considers future vehicle fuel economy， power generation carbon emission factors， hydrogen production carbon emission factors， and regional differences in the scale and hydrogen production methods， this study quantitatively evaluated the life cycle carbon emissions of different types of vehicles， including fuel cell vehicles （FCV）， traditional fuel vehicles （ICEV）， and battery electric vehicles （BEV）. We compared and analyzed the carbon reduction potential of hydrogen fuel cell vehicles at different times and in different regions and conducted an uncertainty analysis on hydrogen consumption per hundred kilometers. The results showed that by 2025， the life cycle carbon emissions of hydrogen fuel cell coaches would decrease by 36.0% compared to that of traditional fuel coaches， but the reduction in carbon emissions for hydrogen fuel cell heavy-duty trucks was not significant. By 2035， as the hydrogen energy source structure in China continues to improve， the life cycle carbon emissions of hydrogen fuel cell heavy-duty trucks were predicted to decrease by 36.5% compared to that of traditional fuel heavy-duty trucks. The decarbonization potential was most significant for heavy-duty trucks compared to that of passenger cars and coaches. Taking the Beijing-Tianjin-Hebei demonstration group as an example in 2035， as the hydrogen consumption per hundred kilometers decreases by 20%， the carbon reduction potential of FCV passenger cars， coaches， and heavy-duty trucks would increase by 7.29%， 9.93%， and 19.57%， respectively. Therefore， it is recommended to prioritize the promotion of hydrogen fuel cell coaches in the short term， heavy-duty trucks in the long term， and passenger cars as a supplement. Promoting hydrogen fuel cell vehicles in different regions and stages will help advance the low-carbon development of the automotive industry in China.

[Common Malignant Tumors in the Reproductive System of Chinese Women: Disease Burden During 1990-2019 and Prediction of Future Trend].

Objective To analyze the trends of disease burden of cervical cancer,uterine cancer,and ovarian cancer among Chinese women from 1990 to 2019,and to provide a basis for formulating precise prevention and control measures in China. Methods The global disease burden data in 2019 were used to describe the changes in indicators such as incidence,mortality,years of life lost due to premature mortality(YLL),years lived with disability(YLD),and disability-adjusted life year(DALY) of cervical,uterine,and ovarian cancers in China from 1990 to 2019.Furthermore,the Bayesian age-period-cohort model was adopted to predict the incidence and mortality of the cancers from 2020 to 2030. Results From 1990 to 2019,the incidence rates and mortality of cervical,uterine,and ovarian cancers in Chinese women showed an upward trend,and the age-standardized incidence rate of ovarian cancer increased the most(0.78%).In 2019,the incidence of cervical cancer and uterine cancer concentrated in the women of 55-59 years old,and ovarian cancer mainly occurred in the women of 70-74 years old.The DALY,YLL,and YLD of cervical,uterine,and ovarian cancers all presented varying degrees of growth at all ages.The Bayesian age-period-cohort model predicted that from 2020 to 2030,the incidence and mortality of cervical cancer in China showed a decreasing trend,while those of uterine cancer and ovarian cancer showed an increasing trend.There was no significant change in the age with high incidence of the three cancers. Conclusions From 1990 to 2019,the overall disease burden of cervical,uterine,and ovarian cancers in China increased,while the disease burden of cervical cancer decreased after 2020.It is recommended that the efforts should be doubled for the prevention and control of cervical,uterine,and ovarian cancers.

Impact of the COVID-19 pandemic on cardiovascular mortality and contrast analysis within subgroups.

Background: An increase in deaths has been perceived during the pandemic, which cannot be explained only by COVID-19. The actual number of deaths far exceeds the recorded data on deaths directly related to SARS-CoV-2 infection. Data from early and short-lived pandemic studies show a dramatic shift in cardiovascular mortality. Grounded in the post-pandemic era, macroscopic big data on cardiovascular mortality during the pandemic need to be further reviewed and studied, which is crucial for cardiovascular disease prevention and control. Methods: We retrieved and collected data associated with cardiovascular disease mortality from the National Vital Statistic System from the Center for Disease Control and Prevention Wide-Ranging Online Data for Epidemiologic Research (CDC WONDER) platform based on the ICD-10 codes. We applied regression analysis to characterize overall cardiovascular disease mortality trends from 2010 to 2023 and built a time series model to predict mortality for 2020-2023 based on mortality data from 2010 to 2019 in order to affirm the existence of the excess deaths by evaluating observed vs. predicted mortality. We also conducted subgroup analyses by sex, age and race/ethnicity for the purpose of obtaining more specific sociodemographic information. Results: All-cause age-standardised mortality rates (ASMRs) for CVD dramatically increased between 2019 and 2021[annual percentage change (APC) 11.27%, p < 0.01], and then decreased in the following 2021-2023(APC: -7.0%, p < 0.01). Subgroup analyses found that the ASMR change was most pronounced in Alaska Indians/Native American people (APC: 16.5% in 2019-2021, -12.5% in 2021-2023, both p < 0.01), Hispanics (APC: 12.1% in 2019-2021, -12.2% in 2021-2023, both p < 0.05) and non-Hispanic Black people (APC:11.8% in 2019-2021, -10.3% in 2021-2023, both p < 0.01)whether during the increasing or declining phase. Similarly, the ASMR change was particularly dramatic for the 25-44 age group (APC:19.8% in 2019-2021, -15.4% in 2021-2023, both p < 0.01) and males (APC: 11.5% in 2019-2021, -7.6% in 2021-2023, both p < 0.01). By the end of 2023, the proportion of COVID-related excess death remained high among the elderly (22.4%), males (42.8%) and Alaska Indians/Native American people(39.7%). In addition, we did not find the presence of excess deaths in the young (25-44) and middle-aged cohort (45-64) in 2023, while excess deaths remained persistent in the elderly. Conclusions: All-cause ASMRs for CVD increased notably during the initial two years of the COVID-19 pandemic and then witnessed a decline in 2021-2023. The cohorts (the young, males and minorities) with the steepest rise in mortality decreased at the fastest rate instead. Previous initiatives to promote cardiovascular health were effective, but further research on cardiovascular healthcare for the elderly and racial disparities should be attached to priority considering the presence of sociodemographic differences in CVD death.

Artificial intelligence in pediatric surgery.

Artificial intelligence (AI) is rapidly changing the landscape of medicine and is already being utilized in conjunction with medical diagnostics and imaging analysis. We hereby explore AI applications in surgery and examine its relevance to pediatric surgery, covering its evolution, current state, and promising future. The various fields of AI are explored including machine learning and applications to predictive analytics and decision support in surgery, computer vision and image analysis in preoperative planning, image segmentation, surgical navigation, and finally, natural language processing assist in expediting clinical documentation, identification of clinical indications, quality improvement, outcome research, and other types of automated data extraction. The purpose of this review is to familiarize the pediatric surgical community with the rise of AI and highlight the ongoing advancements and challenges in its adoption, including data privacy, regulatory considerations, and the imperative for interdisciplinary collaboration. We hope this review serves as a comprehensive guide to AI's transformative influence on surgery, demonstrating its potential to enhance pediatric surgical patient outcomes, improve precision, and usher in a new era of surgical excellence.

Associating T1-Weighted and T2-Weighted Magnetic Resonance Imaging Radiomic Signatures With Preoperative Symptom Severity in Patients With Cervical Spondylotic Myelopathy.

BACKGROUND: Preoperative symptom severity in cervical spondylotic myelopathy (CSM) can be variable. Radiomic signatures could provide an imaging biomarker for symptom severity in CSM. This study utilizes radiomic signatures of T1-weighted and T2-weighted magnetic resonance imaging images to correlate with preoperative symptom severity based on modified Japanese Orthopaedic Association (mJOA) scores for patients with CSM. METHODS: Sixty-two patients with CSM were identified. Preoperative T1-weighted and T2-weighted magnetic resonance imaging images for each patient were segmented from C2-C7. A total of 205 texture features were extracted from each volume of interest. After feature normalization, each second-order feature was further subdivided to yield a total of 400 features from each volume of interest for analysis. Supervised machine learning was used to build radiomic models. RESULTS: The patient cohort had a median mJOA preoperative score of 13; of which, 30 patients had a score of >13 (low severity) and 32 patients had a score of ≤13 (high severity). Radiomic analysis of T2-weighted imaging resulted in 4 radiomic signatures that correlated with preoperative mJOA with a sensitivity, specificity, and accuracy of 78%, 89%, and 83%, respectively (P < 0.004). The area under the curve value for the ROC curves were 0.69, 0.70, and 0.77 for models generated by independent T1 texture features, T1 and T2 texture features in combination, and independent T2 texture features, respectively. CONCLUSIONS: Radiomic models correlate with preoperative mJOA scores using T2 texture features in patients with CSM. This may serve as a surrogate, objective imaging biomarker to measure the preoperative functional status of patients.

Machine Learning Predictions on Outpatient No-Show Appointments in a Malaysia Major Tertiary Hospital.

Introduction: A no-show appointment occurs when a patient does not attend a previously booked appointment. This situation can cause other problems, such as discontinuity of patient treatments as well as a waste of both human and financial resources. One of the latest approaches to address this issue is predicting no-shows using machine learning techniques. This study aims to propose a predictive analytical approach for developing a patient no-show appointment model in Hospital Kuala Lumpur (HKL) using machine learning algorithms. Methods: This study uses outpatient data from the HKL's Patient Management System (SPP) throughout 2019. The final data set has 246,943 appointment records with 13 attributes used for both descriptive and predictive analyses. The predictive analysis was carried out using seven machine learning algorithms, namely, logistic regression (LR), decision tree (DT), k-near neighbours (k-NN), Naïve Bayes (NB), random forest (RF), gradient boosting (GB) and multilayer perceptron (MLP). Results: The descriptive analysis showed that the no-show rate was 28%, and attributes such as the month of the appointment and the gender of the patient seem to influence the possibility of a patient not showing up. Evaluation of the predictive model found that the GB model had the highest accuracy of 78%, F1 score of 0.76 and area under the curve (AUC) value of 0.65. Conclusion: The predictive model could be used to formulate intervention steps to reduce no-shows, improving patient care quality.

Interactive polar diagrams for model comparison.

OBJECTIVE: Evaluating the performance of multiple complex models, such as those found in biology, medicine, climatology, and machine learning, using conventional approaches is often challenging when using various evaluation metrics simultaneously. The traditional approach, which relies on presenting multi-model evaluation scores in the table, presents an obstacle when determining the similarities between the models and the order of performance. METHODS: By combining statistics, information theory, and data visualization, juxtaposed Taylor and Mutual Information Diagrams permit users to track and summarize the performance of one model or a collection of different models. To uncover linear and nonlinear relationships between models, users may visualize one or both charts. RESULTS: Our library presents the first publicly available implementation of the Mutual Information Diagram and its new interactive capabilities, as well as the first publicly available implementation of an interactive Taylor Diagram. Extensions have been implemented so that both diagrams can display temporality, multimodality, and multivariate data sets, and feature one scalar model property such as uncertainty. Our library, named polar-diagrams, supports both continuous and categorical attributes. CONCLUSION: The library can be used to quickly and easily assess the performances of complex models, such as those found in machine learning, climate, or biomedical domains.

Multi-omics indicators of long-term survival benefits after immune checkpoint inhibitor therapy.

Molecular indicators of long-term survival (LTS) in response to immune-checkpoint inhibitor (ICI) treatment have the potential to provide both mechanistic and therapeutic insights. In this study, we construct predictive models of LTS following ICI therapy based on data from 158 clinical trials involving 21,023 patients of 25 cancer types with available 1-year overall survival (OS) rates. We present evidence for the use of 1-year OS rate as a surrogate for LTS. Based on these and corresponding TCGA multi-omics data, total neoantigen, metabolism score, CD8+ T cell, and MHC_score were identified as predictive biomarkers. These were integrated into a Gaussian process regression model that estimates "long-term survival predictive score of immunotherapy" (iLSPS). We found that iLSPS outperformed the predictive capabilities of individual biomarkers and successfully predicted LTS of patient groups with melanoma and lung cancer. Our study explores the feasibility of modeling LTS based on multi-omics indicators and machine-learning methods.

Optimization models for patient and technician scheduling in hemodialysis centers.

Patient and technician scheduling problem in hemodialysis centers presents a unique setting in healthcare operations as (1) unlike other healthcare problems, dialysis appointments have a steady state and the treatment times are determined in advance of the appointments, and (2) once the appointments are set, technicians will have to be assigned to two types of jobs per appointment: putting on and taking off patients (connecting to and disconnecting from dialysis machines). In this study, we design a mixed-integer programming model to minimize technicians' operating costs (regular and overtime costs) at large-scale hemodialysis centers. As this formulation proves to be computationally challenging to solve, we propose a novel reformulation of the problem as a discrete-time assignment model and prove that the two formulations are equivalent under a specific condition. We then simulate instances based on the data from our collaborating hemodialysis center to evaluate the performance of our proposed formulations. We compare our results to the current scheduling policy at the center. In our numerical analysis, we reduced the technician operating costs by 17% on average (up to 49%) compared to the current practice. We further conduct a post-optimality analysis and develop a predictive model that can estimate the number of required technicians based on the center's attributes and patients' input variables. Our predictive model reveals that the optimal number of technicians is strongly related to the time flexibility of patients and their dialysis times. Our findings can help clinic managers at hemodialysis centers to accurately estimate the technician requirements.

Predictive analysis of the scoliotic curve using a subject's 3D model.

A predictive analysis of the conservative scoliosis treatment is necessary, in which a 3D model of an optimal treatment algorithm is a basic part in the design of a prosthetic corset. Since CAD technology has proven to be very useful in the field of prosthetics and orthotics, we used an open-source software to plan the correction of the scoliotic curve on a virtual model of the subject's torso. The shape of the scoliosis was simplified by means of a directional polygon, which was drawn in a reverse manner depending on the directional arcs of the scoliotic curve. The resulting scoliosis correction, simulated in a predictive analysis, was defined by changing the Cobb angle, eccentricity, and torso height. With the proposed low-cost method of predictive analysis, it is possible to help CPOs to a more accurate and effective design of orthoses and corrective aids and to comprehensively determine the entire treatment procedure.

Non-invasive candidate protein signature predicts hepatic venous pressure gradient reduction in cirrhotic patients after sustained virologic response.

BACKGROUND AND AIMS: A reduction in hepatic venous pressure gradient (HVPG) is the most accurate marker for assessing the severity of portal hypertension and the effectiveness of intervention treatments. This study aimed to evaluate the prognostic potential of blood-based proteomic biomarkers in predicting HVPG response amongst cirrhotic patients with portal hypertension due to Hepatitis C virus (HCV) and had achieved sustained virologic response (SVR). METHODS: The study comprised 59 patients from two cohorts. Patients underwent paired HVPG (pretreatment and after SVR), liver stiffness (LSM), and enhanced liver fibrosis scores (ELF) measurements, as well as proteomics-based profiling on serum samples using SomaScan® at baseline (BL) and after SVR (EOS). Machine learning with feature selection (Caret, Random Forest and RPART) methods were performed to determine the proteins capable of classifying HVPG responders. Model performance was evaluated using AUROC (pROC R package). RESULTS: Patients were stratified by a change in HVPG (EOS vs. BL) into responders (greater than 20% decline in HVPG from BL, or <10 mmHg at EOS with >10 mmHg at BL) and non-responders. LSM and ELF decreased markedly after SVR but did not correlate with HVPG response. SomaScan (SomaLogic, Inc., Boulder, CO) analysis revealed a substantial shift in the peripheral proteome composition, reflected by 82 significantly differentially abundant proteins. Twelve proteins accurately distinguished responders from non-responders, with an AUROC of .86, sensitivity of 83%, specificity of 83%, accuracy of 83%, PPV of 83%, and NPV of 83%. CONCLUSIONS: A combined non-invasive soluble protein signature was identified, capable of accurately predicting HVPG response in HCV liver cirrhosis patients after achieving SVR.

Locomotor, ecological and phylogenetic drivers of skeletal proportions in frogs.

Frogs exhibit complex anatomical features of the pelvis, limbs and spine, long assumed to represent specialisations for jumping. Yet frogs employ a wide range of locomotor modes, with several taxa featuring primary locomotor modes other than jumping. Using a combination of techniques (CT imaging and 3D visualization, morphometrics, phylogenetic mapping), this study aims to determine the link between skeletal anatomy and locomotor style, habitat type and phylogenetic history, shedding new light on how functional demands impact morphology. Body and limb measurements for 164 taxa from all the recognised anuran families are extracted from digitally segmented CT scans of whole frog skeletons and analysed using various statistical techniques. We find that the expansion of the sacral diapophyses is the most important variable for predicting locomotor mode, which was more closely correlated with frog morphology than either habitat type or phylogenetic relationships. Predictive analyses suggest that skeletal morphology is a useful indicator of jumping but less so for other locomotor modes, suggesting that there is a wide range of anatomical solutions to performing locomotor styles such as swimming, burrowing or walking.

Meta-analysis informed machine learning: Supporting cytokine storm detection during CAR-T cell Therapy.

Cytokine release syndrome (CRS), also known as cytokine storm, is one of the most consequential adverse effects of chimeric antigen receptor therapies that have shown otherwise promising results in cancer treatment. When emerging, CRS could be identified by the analysis of specific cytokine and chemokine profiles that tend to exhibit similarities across patients. In this paper, we exploit these similarities using machine learning algorithms and set out to pioneer a meta-review informed method for the identification of CRS based on specific cytokine peak concentrations and evidence from previous clinical studies. To this end we also address a widespread challenge of the applicability of machine learning in general: reduced training data availability. We do so by augmenting available (but often insufficient) patient cytokine concentrations with statistical knowledge extracted from domain literature. We argue that such methods could support clinicians in analyzing suspect cytokine profiles by matching them against the said CRS knowledge from past clinical studies, with the ultimate aim of swift CRS diagnosis. We evaluate our proposed methods under several design choices, achieving performance of more than 90% in terms of CRS identification accuracy, and showing that many of our choices outperform a purely data-driven alternative. During evaluation with real-world CRS clinical data, we emphasize the potential of our proposed method of producing interpretable results, in addition to being effective in identifying the onset of cytokine storm.