Predictive Test Research Articles

Digital Literacy toward Historical Knowledge: Implementation of the Bukittinggi City History Website as an Educational Technology

This research aims to identify the challenges and opportunities in integrating digital literacy skills into history education. This research focuses on understanding educators' difficulties in integrating digital technologies into the traditional history curriculum. Educational technology as a means and facility to support education and learning is no exception for historical knowledge through access to historical websites. This study analyses digital literacy toward historical knowledge using the Bukittinggi City history website. This research is quantitative research with a survey approach with closed-ended questions. The research population is the millennial generation in Indonesia. Samples were taken with a non-probability sampling approach with purposive sampling. This study involved 831 respondents spread throughout Indonesia. The data analysis technique is partial Least Square Structural Equation Modelling (PLS-SEM). The results showed no difference in historical knowledge scores between males and girls. With a value of 0.697 and a 69.7% variance, the coefficient of determination (R2) result demonstrates significant volatility in historical knowledge. Additionally, Q2's value serves as a gauge for the model's predictive usefulness. The predictive relevance of the model's independent variables was assessed using the predictive relevance test (Q2). Men might be more adept at using online resources to broaden their knowledge of the city's past. Understanding the disparities in digital literacy between men and women will significantly impact the design of educational and literacy programs in Bukittinggi. Enhancing digital literacy can promote access to and understanding of the city's history, especially among women

Bridging a Gap in the Workers' Compensation System: A Scale Development and Validation of an Employee Workers' Compensation Experience Scale

When accidents occur, employees rely on the workers' compensation system to provide continuing wages and medical benefits. This study addresses a fundamental workers’ compensation gap—the lack of an Employee Workers’ Compensation Experience (EWCE) scale. While current metrics monitor direct costs, they often overlook the psycho-social impacts on employees. The study introduces a structured EWCE scale that encompasses dimensions of claim communication, psychological and emotional impacts, and uncertainty regarding the claim outcome. The EWCE scales relevance is emphasized by its ability to predict turnover intentions, burnout, and obligations to come to work sick outcomes. Discriminate, convergent, and predictive validity tests corroborate the scales' effectiveness. These findings allow employers, policymakers, and researchers to create a safer, more inclusive work environment by measuring and monitoring workers' compensation claim outcomes. This scale bridges the critical knowledge gap and offers an analytical tool to enhance workers' compensation policies and outcomes.

Metabolic syndrome: a comprehensive review

Metabolic syndrome (syndrome X) includes several components like diabetes, hypertension, hyperlipidemia etc. Every patient should undergo detailed assessment for the silent presence of the components of metabolic syndrome. Genetic predisposition, increased nutrient- dense food, decreased physical activity and chronic stress are common in metabolic syndrome. Insulin resistance, obesity and hyperglycaemia are commonly seen which can later lead to serious consequences like cardiovascular complications, thrombotic events etc. Clinical features depend on the components of the metabolic syndrome in a patient. Some may present with complications and advanced disease. For non-diabetic individuals, oral glucose tolerance test is indicated. It is better to study serum uric acid level and to screen for silent kidney stones. Specific drugs are prescribed as indicated. Drugs for stress and insomnia are also prescribed. Thrombotic status of the patient should be considered, and antiplatelet drugs are prescribed if risk factors are present. Non-pharmacological measures like diet modification and increased physical activity should be given on a priority basis. Patient compliance of these two measures should be monitored regularly. Future deployment of “artificial intelligence – powered” predictive diagnostic tests will help in detecting and controlling metabolic syndrome. “At risk” individuals and patients showing some components of metabolic syndrome should undergo full investigations to detect other components of metabolic syndrome. Full range of therapeutic drugs, diet modification and increased physical activity should be prescribed.

Sex differences in the anticompulsive-like effect of memantine: Involvement of nitric oxide pathway but not AMPA receptors

Memantine, an N-Methyl-D-Aspartate (NMDA) antagonist, has been examined as a potential treatment for Obsessive-Compulsive Disorder (OCD). Yet, there is limited knowledge regarding how it works to reduce compulsive behaviour and whether it has different effects on individuals based on their sex. Herein, we investigated if there are sex differences in the anticompulsive-like effect of memantine in adult Swiss mice. Additionally, we explored whether the nitric oxide (NO) pathway and α-amino-3-hydroxy-5-methyl-4-isoazolepropionic acid (AMPA) receptors play a role in memantine's effects. To start, we assessed the impact of a single intraperitoneal dose of memantine (at 3, 5, and 10 mg/kg) on behaviours exhibited in the open field test (OFT) and the marble-burying test (MBT), the latter being a predictive test for anticompulsive effects. All doses of memantine reduced marble-burying behaviour in both male and female mice without affecting their locomotor activity in the OFT. This anticompulsive-like effect was also confirmed in another predictive test, the nest-building test, with the highest memantine dose (10 mg/kg) reducing nest-building behaviour without significant differences between male and female mice. We observed that pre-treatment with L-arginine, a NO precursor, mitigated the anticompulsive-like effect of memantine in male mice but had no effect in female mice in the MBT. Finally, NBQX, an AMPA receptor antagonist, did not block the anticompulsive-like effect of memantine. In summary, our study suggests that the anticompulsive-like effect of memantine does not appear to be sex-specific, does not depend on AMPA receptors, and involves the NO pathway primarily in male mice.

Long-term follow-up of Parkinsonian patients operated on with deep brain electromodulation without intraoperative microrecording

Background: Deep brain electromodulation (DBEM), also known as deep brain stimulation in different intracerebral targets, is the most widely used surgical treatment due to its effects in reducing motor symptoms of Parkinson’s disease. The intracerebral microelectrode recording has been considered for decades as a necessary tool for the success of Parkinson’s surgery. However, some publications give more importance to intracerebral stimulation as a better predictive test. Since 2002, we initiated a technique of brain implant of electrodes without micro recording and based solely on image-guided stereotaxis followed by intraoperative macrostimulation. In this work, we analyze our long-term results, taking into account motor skills and quality of life (QL) before and after surgery, and we also establish the patient’s time of clinical improvement. Methods: This is a descriptive clinical study in which the motor state of the patients was evaluated with the unified Parkinson’s disease scale (UPDRS) and the QL using the Parkinson’s disease QL questionnaire 39 questionnaires before surgery, in the “on” state of the medication; and after surgery, under active stimulation and in the “on” state. Results: Twenty-four patients with ages ranging from 37 to 78 years undergoing surgery DBEM on the subthalamic nucleus were studied. An improvement of 41.4% in motor skills and 41.7% in QL was obtained. Conclusion: When microrecording is not available, the results that can be obtained, based on preoperative imaging and clinical intraoperative findings, are optimal and beneficial for patients.

(Invited) Electrochemical Interfaces in Energy Storage: Theory Meets Experiment

Understanding the dynamic processes at solid-liquid interfaces in electrochemical devices like batteries is key to developing more efficient and durable technologies for the green transition. Fundamental and performance-limiting interfacial processes like the formation of the Solid-Electrolyte Interphase (SEI) [1,2] and dendritic growth [3] span numerous time- and length scales. Despite decades of research, the fundamental understanding of structure-property relations remains elusive. Ab initio molecular dynamics (AIMD) generally provides sufficient accuracy to describe chemical reactions and the making and breaking of chemical bonds at these interfaces [4]. Still, the cost is prohibitively high to reach sufficiently long time- and length scales to ensure proper statistical sampling [5]. Machine learning (ML) potentials offer a potential solution to this challenge. Still, training ML-based potentials capable of handling activated processes in organic or aqueous electrolytes remains a fundamental challenge since the potential must capture both intra- and intermolecular interactions in the electrolyte and during chemical reactions at the interface [5]. Here, we present new approaches using phase field models [3], graph neural networks [6] and new transition state training sets [7] for chemical reaction networks, and machine/deep learning models to predict the spatio-temporal evolution of electrochemical interphases [2]. We also discuss the development of methods like symbolic regression to learn the laws of electrolyte transport [8], uncertainty quantification training and evaluating neural network ensemble models [9] using models trained on multi-sourced and multi-fidelity data from multiscale computer simulations, operando characterization, high-throughput synthesis, and testing, to provide, e.g., uncertainty-aware and explainable ML for early prediction of battery degradation trajectories (Figure 1) [10]. Figure 1

A comparison of ratio of patient’s height to thyromental distance with modified mallampati test and upper lip bite test for prediction of difficult laryngoscopy

Various airway evaluation tests are performed to predict difficult intubation. The ratio of Height to thyromental distance has been reported to have a good predictability. This study tested the performance of ratio of height to thyromental distance and compared it with commonly performed airway evaluation tests: the modified Mallampati test and upper lip bite test. This descriptive study was conducted in 120 patients presenting for surgery under general anesthesia with endotracheal intubation. Preoperative airway assessment was done using Modified Mallampati test, upper lip bite test and ratio of height to thyromental distance. The Cormack and Lehane grading was done during laryngoscopy to determine easy or difficult visualization of larynx. Sensitivity, specificity, positive predictive value, negative predictive value and accuracy of three tests were calculated. Difficult laryngoscopy was seen in 9 patients (7.5%). The sensitivity, specificity, positive predictive value, negative predictive value respectively for the tests were modified Mallampati test (22.2%, 89.2%, 14.3% and 93.4%), upper lip bite test (22.2%, 100%, 100% and 94.1%), ratio of height to thyromental distance (77.8%, 95.5%, 58.3% and 94.16%). In conclusion, we found that the ratio of patient’s height to thyromental distance performed better than MMT and ULBT in predicting difficult visualization of larynx in our population.

Vairavimo stiliaus prognostinė analizė: demografinių ir kognityvinių veiksnių reikšmė

This study aimed to compare four driving styles among professional and non-professional Lithuanian drivers and to assess the significance of demographic and cognitive factors in predicting investigated driving styles. The study included data from 446 nonprofessional drivers (mean of age 32.6 years) and 200 professional drivers (mean of age 47.7 years) in Lithuania. The research questionnaire comprised demographic data and self-report instruments for driving styles road risk perception and driving skills (perceptual-motor and safety) assessment. An interactive, video-based hazard prediction test was used to evaluate road hazard perception skills. The study results showed that professional drivers possess a more aggressive and more careless driving style, while nonprofessional drivers exhibited a more anxious driving style. It was found that longer driving experience, better self-assessed perceptual-motor skills, but poorer self-reported safety driving skills, were significant predictors for a driving style associated with a careless as well as with aggression, demonstrated among younger drivers. A poorer self-assessment of perceptual-motor driving skills was significantly associated with an anxious driving style among both professional and nonprofessional drivers with more driving experience. Finally, this study revealed that a safe driving style is significantly predicted by greater self-assessed perceptual-motor and safety driving skills.

The value of self-determination theory in marketing studies: Insights from the application of PLS-SEM and NCA to anti-food waste apps

Self-determination theory (SDT) is a theory of human motivation that highlights the distinction between intrinsic and extrinsic motivations. Recent research has advocated its wider use in marketing studies, suggesting that it has strong predictive accuracy for consumer behaviors, and has proposed arguments about the necessity of both intrinsic and extrinsic motivations for marketing outcomes. However, these statements have not been empirically substantiated. We address this gap by studying the motivations for attitude and intention to use anti-food waste apps. Data from 141 users and 227 non-users of the app “Too Good To Go” are analyzed using partial least squares structural equation modeling (PLS-SEM) and several of its methodological extensions (e.g., multigroup analysis and the cross-validated predictive ability test), and necessary condition analysis (NCA). The findings support the argument that SDT accurately predicts consumer attitudes and behaviors, while NCA provides a nuanced view of the necessity of intrinsic and extrinsic motivations.

Optimized whole-genome sequencing workflow for tumor diagnostics in routine pathology practice.

Two decades after the genomics revolution, oncology is rapidly transforming into a genome-driven discipline, yet routine cancer diagnostics is still mainly microscopy based, except for tumor type-specific predictive molecular tests. Pathology laboratories struggle to quickly validate and adopt biomarkers identified by genomics studies of new targeted therapies. Consequently, clinical implementation of newly approved biomarkers suffers substantial delays, leading to unequal patient access to these therapies. Whole-genome sequencing (WGS) can successfully address these challenges by providing a stable molecular diagnostic platform that allows detection of a multitude of genomic alterations in a single cost-efficient assay and facilitating rapid implementation, as well as by the development of new genomic biomarkers. Recently, the Whole-genome sequencing Implementation in standard Diagnostics for Every cancer patient (WIDE) study demonstrated that WGS is a feasible and clinically valid technique in routine clinical practice with a turnaround time of 11 workdays. As a result, WGS was successfully implemented at the Netherlands Cancer Institute as part of routine diagnostics in January 2021. The success of implementing WGS has relied on adhering to a comprehensive protocol including recording patient information, sample collection, shipment and storage logistics, sequencing data interpretation and reporting, integration into clinical decision-making and data usage. This protocol describes the use of fresh-frozen samples that are necessary for WGS but can be challenging to implement in pathology laboratories accustomed to using formalin-fixed paraffin-embedded samples. In addition, the protocol outlines key considerations to guide uptake of WGS in routine clinical care in hospitals worldwide.

Assessment of Salivary MMP-8 and IL-1β for the Diagnosis of Periodontal Diseases in Pakistani Population.

Clinical methods use the subjective diagnosis of periodontal diseases by visual observation that could result in differences and variability of diagnosis. The addition of specific markers could aid in the accurate diagnosis of the local population. The objective of the study was to target two of the major proteins for possible significance in such an approach. Unstimulated saliva samples were collected from 60 participants aged between 18 and 70 years. Three groups each with twenty participants were recruited into periodontitis, gingivitis, and healthy control. The samples were analyzed using human enzyme-linked immunosorbent assay kits for matrix metalloproteinase-8 (MMP-8) and interleukin-1β (IL-1β). SPSS version 20 was used to analyze the result. Posthoc analysis by Tukey's test revealed that MMP-8 levels were higher in gingivitis and periodontitis groups as compared with healthy controls. The test also revealed that IL-1β levels were higher in the periodontitis group compared with the healthy control and gingivitis group. Additionally, one-way analysis of variance analysis showed a significant effect on probing depth in gingivitis and periodontitis patients. The mean age of periodontitis group was significantly higher than other groups. Salivary biomarkers may provide useful diagnostic information and could be utilized as tests for periodontal disease screening, prognosis, and prediction.

Symptom-based scoring technique by machine learning to predict COVID-19: a validation study

BackgroundCoronavirus disease 2019 (COVID-19) surges, such as that which occurred when omicron variants emerged, may overwhelm healthcare systems. To function properly, such systems should balance detection and workloads by improving referrals using simple yet precise and sensitive diagnostic predictions. A symptom-based scoring system was developed using machine learning for the general population, but no validation has occurred in healthcare settings. We aimed to validate a COVID-19 scoring system using self-reported symptoms, including loss of smell and taste as major indicators.MethodsA cross-sectional study was conducted to evaluate medical records of patients admitted to Dr. Sardjito Hospital, Yogyakarta, Indonesia, from March 2020 to December 2021. Outcomes were defined by a reverse-transcription polymerase chain reaction (RT-PCR). We compared the symptom-based scoring system, as the index test, with antigen tests, antibody tests, and clinical judgements by primary care physicians. To validate use of the index test to improve referral, we evaluated positive predictive value (PPV) and sensitivity.ResultsAfter clinical judgement with a PPV of 61% (n = 327/530, 95% confidence interval [CI]: 60% to 62%), confirmation with the index test resulted in the highest PPV of 85% (n = 30/35, 95% CI: 83% to 87%) but the lowest sensitivity (n = 30/180, 17%, 95% CI: 15% to 19%). If this confirmation was defined by either positive predictive scoring or antigen tests, the PPV was 92% (n = 55/60, 95% CI: 90% to 94%). Meanwhile, the sensitivity was 88% (n = 55/62, 95% CI: 87% to 89%), which was higher than that when using only antigen tests (n = 29/41, 71%, 95% CI: 69% to 73%).ConclusionsThe symptom-based COVID-19 predictive score was validated in healthcare settings for its precision and sensitivity. However, an impact study is needed to confirm if this can balance detection and workload for the next COVID-19 surge.

Lymphocyte transformation tests predict delayed-type allergy to piperacillin/tazobactam in patients with cystic fibrosis

BackgroundAntibiotic treatment is crucial for patients with chronic bacterial infections. Suspected drug allergies often lead to inconsistent therapies and challenging clinical management for patients and caregivers. The objective of this study was to evaluate the value of lymphocyte transformation tests in comparison to skin tests for the prediction of delayed-type allergic reactions. MethodsThis prospective, observational study tested the diagnostic value of skin prick tests, intradermal tests (reading: 15 min and 72 h) and lymphocyte transformations tests for the prediction of allergic reactions in CF patients with physician reported allergy to piperacillin/tazobactam, meropenem and ceftazidime. The tests were performed directly before a 14d intravenous drug challenge. ResultsWe performed 33 drug challenges in 29 subjects. 21 drug challenges were negative (63 %); 12 lead to a reaction (37 %), of those 2 were immediate and 10 were delayed-type. 100 % of the skin prick tests were negative. 97 % (33/34) of the intradermal tests with early reading and 100 % of the intradermal tests with late reading yielded negative results. 5/11 patients who experienced a delayed-type reaction during the drug challenge had a positive lymphocyte transformations test. All 17 patients who did not react had a negative lymphocyte transformations test. For piperacillin/tazobactam, 4/5 patients who experienced a delayed-type reaction during the drug challenge had positive lymphocyte transformations tests. Hence, for piperacillin/tazobactam, the sensitivity of the lymphocyte transformation test for prediction of reactions was 80.0 % and the specificity 100 %. ConclusionWe demonstrate that the lymphocyte transformation test predicts delayed-type allergy to piperacillin/tazobactam in contrast to skin tests.

Effects of Temperature on Axial Crushing Behavior of Circular Multi-Walled Tubes

In this work, the impact of temperature on the crushing performance of multi-walled tube (MWT) were investigated using a combined experimental, theoretical and numerical method. The MWT was fabricated using extrusion technology, and the temperature-dependent axial crushing experiment was performed on a hydraulic testing machine. The results show that the peak crushing force (PCF), the mean force (Pm) and the specific energy absorption (SEA) decreased near-linearly by 21.7%, 30.7% and 30.7% as the temperature increased from 25 °C to 250 °C, while the crushing load efficiency (CLE) was insensitive to temperature. The average forces obtained via numerical prediction, theoretical analysis and experimental testing were basically consistent. The numerical results indicate that varied temperature alters the number of dominant wavelets and the relative lateral deflections of MWT. In addition, compared with the competitive structures, the energy absorption property of MWT is excellent at high temperatures.

Machine-learning-aided hydrochar production through hydrothermal carbonization of biomass by engineering operating parameters and/or biomass mixture recipes

Hydrochar serves not only as a fuel source but also as a versatile carbon material that has found extensive application across various domains. The application performance of hydrochar, e.g., energy recovery and carbon stability, is substantially influenced by its mass yield, higher heating value (HHV), and compositions (C, H, O, N, S, and ash), so the prediction and engineering of these properties is promising. In this study, two machine learning algorithms, namely gradient boosting regression (GBR) and random forest (RF), were used to predict the hydrochar properties mentioned above. The GBR models (with test regression coefficient (R2) values of 0.87–0.98 for single-target prediction and average test R2 of 0.93 for multi-target prediction) exhibited superior predictive capabilities to the RF models (with test R2 of 0.78–0.97 for single-target and average test R2 of 0.90 for multi-target prediction). The interpretation of ML models revealed the importance ranking of features for all targets. Then, engineering hydrochar was carried out through three different optimizations to the as-built multi-target prediction model: i) optimizations of HTC conditions for given biomass samples; ii) optimization of biomass mixture recipes; iii) simultaneous optimization of both biomass mixing recipes and HTC conditions.

Experiences of Discrimination and Interest in Alzheimer’s Disease Predictive Testing in the Health and Retirement Study

AbstractBackgroundRapid developments in Alzheimer’s disease (AD) biomarker research suggest predictive testing may soon become a feasible option available to the public. Future reduction of racial and ethnic disparities in AD requires understanding of potential differences in drivers of interest in AD diagnostic testing. Experiences of discrimination may influence attitude toward AD testing, particularly among racially and ethnically minoritized populations. This study examines whether everyday or lifetime discrimination shapes interest in AD predictive testing.MethodData were collected from 1,472 participants in the 2010 and 2012 waves of the Health and Retirement Study who answered a module on interest in receiving a free test that could tell whether they would develop AD in the future, along with measures of Everyday Discrimination and Lifetime Discrimination. Logistic models were controlled for deciles of propensity scores (estimated using demographic and socioeconomic variables) and odds ratios were re‐expressed as risk differences (RD). The RD is the difference in the probability a person expressed interest in receiving a future AD predictive test based on past experiences of discrimination.ResultThe mean age of the sample was 67 (SD = 10.2), 65.9% were white, and 80% endorsed interest in AD predictive testing. Most (64.1%) participants indicated experiencing everyday discrimination in at least one domain, and 34.8% experienced major lifetime discrimination in at least one domain. Those interested in predictive testing were younger (66 vs 70 years) and more likely to be Black (20% vs 15%) or Latinx (14% vs 8%) than participants uninterested in testing. The probability of wanting an AD test was not associated with discrimination experiences for Black (RD everyday discrimination = 0.104, p = 0.285; RD lifetime discrimination = ‐0.038; p = 0.626) or Latinx (RD everyday discrimination = ‐0.003, p = 0.974; RD lifetime discrimination = ‐0.053; p = 0.692) participants.ConclusionDespite historical and contemporary experiences of discrimination, Black and Latinx individuals express interest in AD testing. This finding implicates structural and systemic barriers, such as systemic racism and institutional gaps in access to clinical research, as likely explanations for underrepresentation of racially and ethnically minoritized persons in research on AD testing.

Optimization design and analysis of the broadband acoustic absorber of the microperforated panel with an interpolated straight tube

The microperforated panel (MPP) structure is widely used in the field of noise reduction. The traditional MPP structure has a fixed absorption peak, and the optimized MPP structure has an improved absorption band, but the frequency range of the absorption is not ideal. For the design of broadband absorption in MPP structures, this paper presents a MPP acoustic absorber structure (N-MH) with an interpolated straight tube (IST) designed for superior broadband acoustic performance. The N-MH structure combines the advantages of the MPP and the embedded necked Helmholtz resonator, as well as having a sub-wavelength thickness of only 60 mm, which is only 1/14th of the wavelength at the first resonant frequency. The N-MH structure is optimized based on the particle swarm optimization (PSO) algorithm. In comparison to traditional microperforated panel structures, the N-MH structure exhibits a significantly broader sound absorption frequency band. Additionally, we thoroughly investigate the factors influencing the mid-low-frequency sound absorption performance of the N-MH structure. Through theoretical prediction, simulation analysis, and experimental testing, it is verified that the N-MH structure has excellent broadband sound absorption characteristics in the frequency interval of 0–2000 Hz, and the percentage of sound absorption bands with absorption coefficients exceeding 0.9 can reach 78.2%.

A comparison of word‐list and story recall tests for prediction of biomarker‐determined Alzheimer’s disease

AbstractBackgroundWord‐list and story recall tests are routinely employed in clinical practice for dementia screening. Previous research has shown that both types of tests are predictive of subsequent clinical diagnoses of dementia, including when examining process scores such as forgetting rate. In this study, our aim was to establish how well standard clinical metrics compared to process scores derived from word‐list and story recall tests in predicting biomarker‐determined Alzheimer’s disease (bdAD), as defined by CSF p‐tau/Abeta42 ratio.MethodData from 381 participants (mean age = 65, ± 9) were drawn from the University of Wisconsin – Madison Alzheimer’s Disease Research Center (ADRC) and Wisconsin Registry for Alzheimer’s Prevention (WRAP). Rey’s Auditory Verbal Learning Test (AVLT; word‐list) and Logical Memory Test (LMT; story) data were available. The conventional clinical scores examined were: AVLT total recall, AVLT delayed recall, LMT immediate recall, and LMT delayed recall. The process scores examined were: AVLT recency ratio (i.e., recency forgetting), AVLT total forgetting, LMT recency ratio, LMT total forgetting, and LMT primacy ratio (i.e., primacy forgetting). Bayesian linear regression analyses were carried out with either the nearest or farthest CSF p‐tau/Abeta42 ratio as outcome; the standard and process baseline memory scores as predictors; and baseline age, time elapsed from baseline to lumbar puncture, APOE risk score, sex, and years of education as control variables. Sensitivity analyses were carried out with logistic regressions using a cut‐off of 0.038 CSF p‐tau/Abeta42 ratio as outcome, to assess diagnosticity. CSF biomarkers were measured using the NeuroToolKit (Roche Diagnostics International Ltd, Rotkreuz, Switzerland).ResultLMT recency ratio and LMT primacy ratio were the best performing predictors (BF10 > 1 billion) both when evaluating the nearest (Figure 1a) and the farthest (Figure 1b) outcomes. However, sensitivity analyses with a binary cut‐off favored the primacy ratio. Areas under the curve (AUCs) ranged from 0.86 to 0.87 (including covariates). Specificity was consistently high for primacy ratio with 94% probability of correctly identifying individuals without bdAD.ConclusionOur study shows that story recall tests may be better than word‐list tests for dementia screening, especially when employing process scores alongside conventional clinical scores.

Machine learning composite of remote cognitive tests for screening of preclinical AD cohorts

AbstractBackgroundComputerized cognitive tests are critical in the screening of preclinical Alzheimer’s Disease (AD) given their ability to be conducted remotely at low cost. Here, we explore whether machine‐learning derived composites of remote cognitive tests can improve sensitivity when detecting brain amyloid (Aβ) accumulation in cognitively normal (CN) cohorts than traditional pen‐and‐paper alternatives.MethodBased on the CogState Brief Battery tests in CN individuals from the A4 dataset (n = 4230, Aβ‐ = 3094), we construct a data‐driven composite, denoted the Remote Empirical Cognitive composite for Alzheimer’s Disease (RECAD), designed to be sensitive to Aβ‐PET positivity. Specifically, the composite uses a random feature elimination logistic regression to identify a subset of predictive tests. We construct and evaluate the model using 10 repeat, 5‐fold cross‐validation in the A4 baseline data. We conduct temporal validation with the A4 second visit and external validation using CN participants from the ADNI (n = 389, Aβ‐ = 143), comparing against the pen‐and‐paper‐based PACC composite and previous computerized composites CBB and C3.ResultRECAD includes three accuracy scores (Identification, One‐Back and One‐card) and one reaction time (Detection). In cross‐validation in the A4 baseline, RECAD show a significantly higher ability to discriminate Aβ status [mean Cohen’s d = 0.26] than PACC [mean d = 0.25, t‐test p<0.001] and computerized composites CBB [median d = 0.13, p<0.001] and C3 [mean d = 0.18, p<0.001]. RECAD significantly improves beyond C3 in the A4 second visit (z‐test p<0.001). Moreover, these trends are replicated in the ADNI at baseline (RECAD d = 0.215, PACC d = 0.061) and 24 months (RECAD d = 0.295, PACC d = ‐0.026) but the small sample and effect size limits our ability to demonstrate statistical significance.ConclusionRECAD, as a machine‐learning derived composite of remotely conducted cognitive tests, shows a comparable or better sensitivity to the established pen‐and‐paper composite test when screening for Aβ+ among CN cohorts. While effect sizes are small, conducting such remote tests repeatedly may be a useful pre‐screening for downstream biofluid evaluation.

A Degradation Empirical-Model-Free Battery End-of-Life Prediction Framework Based on Gaussian Process Regression and Kalman Filter

Predicting the battery’s end-of-life (EOL) with uncertainty quantification is critical for ensuring system safety and reliability. This paper presents a hybrid framework for battery EOL prediction and its uncertainty assessment based on Gaussian process regression (GPR) and Kalman filter (KF). First, a KF-based empirical-model-free state tracking phase is applied for the available partial battery degradation data. Then, the original time series forecasting problem of degradation curves is converted to the prediction of the virtual degradation rate and acceleration. Next, the prediction of the virtual degradation rate and acceleration is executed by the iterative GPR multi-step ahead prediction strategy with moving sliding windows. Finally, the uncertainty assessment is carried out based on the sliding window length determination process. The effectiveness of our proposed method is validated on the open-source lithium-ion battery degradation dataset from the University of Oxford. Extensive EOL prediction tests have been carried out from 40% (early-stage), 60% (middle-stage), and 80% (late-stage) of the dataset, respectively. Compared with the popular EOL prediction method within particle filter framework, the predicted mean EOL cycle by our method is closer to the true value with a smaller range of prediction uncertainty.