Separate Set Research Articles

Editorial: Introduction to the special issue, innovative approaches to visual methods in mixed method research in psychological fields

The use of integrative visual displays to advance analysis is a rapidly evolving topic of inquiry in mixed methods research. This editorial serves dual purposes. The first is to introduce articles appearing in a special issue about visual methods in Methods in Psychology . The second is to introduce two cutting edge examples of the use of dynamic visual displays as a mixed analytical strategy. The article concludes with an argument that a separate set of guidelines are needed for using visual displays for purposes of analysis from those generated for purposes of reporting.

Analytical Validation of Dual-Pole Permanent Magnet Machine Theory

Dual-pole line start permanent magnet (PM) synchronous machine is an emerging technology for replacing induction machines in two-speed applications, such as air coolers, compressors, and pumps. The machine structure includes two magnetic pole numbers on a single rotor layout and two separate sets of stator windings. Due to the unconventional and complex rotor structure, to this date, the design and analysis have solely been based on finite element (FE) method. This article aims to analytically validate the theory and the overall functionality of dual-pole PM machines in both steady state and transient regime. For this propose, a detailed magnetic circuit model is developed for calculating the PM flux distribution and the back electromotive force waveform. However, a single magnetic circuit cannot adequately represent the flux flow of the armature reaction, since the path of the armature flux is a function of rotor position. This is even more challenging in dual-pole machines, where the armature flux is originated from two different sets of stator winding. To avoid the necessity of having multiple magnetic circuits, the concept of magnetic islands is employed to capture the motor response at the loaded condition. For verification, analytical results are all supported via FE, and partially with experimental tests.

A cross-country study of gambling fallacies : South Korea, USA, and Switzerland

This study assesses gambling fallacy roles in three countries (South Korea, USA, and Switzerland) based on their problem gambling status and independent and interdependent self-construal. Online surveys obtained three separate data sets for South Korea, USA, and Switzerland via local online panel companies, and a confirmatory factor analysis confirmed the convergent and discriminant validity of the measurement. An ANOVA also tested differences in gambling fallacy factors between recreational and pathological gamblers in the three countries. The ANOVA results indicate that each gambling fallacy factor had significant main effects on gambler types. Pathological gamblers in USA scored highest on the system-to-win factor, followed by Switzerland and Korea. Superstitions and follow and blame factors for pathological gamblers in Korea were higher than in USA and Switzerland. Additionally, the cultural backgrounds of pathological gamblers produced gambling fallacy variances. This study contributes to the literature in that a three-country data set validated the distinctive four-factor setting of the gambling fallacy scale. Findings highlight each gambling fallacy factor for recreational and pathological gamblers as unique across the three countries. Furthermore, the results provide managerial implications for developing responsible gambling strategies by considering gambling fallacy factors according to gambler types.

Ethical Frameworks for Disclosure of Alzheimer Disease Biomarkers to Research Participants: Conflicting Norms and a Nuanced Policy.

More and more frequently, clinical trials for Alzheimer disease (AD) are targeting cognitively unimpaired individuals who are at increased risk of developing the disease. It is not always clear whether AD biomarker information should be disclosed to research participants: on the one hand, research participants may be interested in learning this information because of its perceived utility, but on the other hand, learning this information may be harmful, as there are very few effective preventive or therapeutic options available for AD. In this article, we bring together three separate sets of ethical guidance literature: on the return of individual research results, on an individual's right to access personal data, and on transparent enrollment into clinical trials. Based on these literatures, we suggest policies for the disclosure of AD biomarker test results in longitudinal observational cohort studies, clinical trials, and hybrid research projects, such as the European Prevention of Alzheimer's Dementia (EPAD) project, in which we served as an ethics team. We also present and critically discuss recommendations for disclosure of AD biomarkers in practice. We underscore that, as long as the clinical validity of AD biomarkers remains limited, there are good reasons to avoid actively disclosing them to cognitively unimpaired research participants.

Applying machine learning to the pharmacokinetic modeling of cyclosporine in adult renal transplant recipients: a multi-method comparison.

Objective: The aim of this study was to identify the important factors affecting cyclosporine (CsA) blood concentration and estimate CsA concentration using seven different machine learning (ML) algorithms. We also assessed the predictability of established ML models and previously built population pharmacokinetic (popPK) model. Finally, the most suitable ML model and popPK model to guide precision dosing were determined. Methods: In total, 3,407 whole-blood trough and peak concentrations of CsA were obtained from 183 patients who underwent initial renal transplantation. These samples were divided into model-building and evaluation sets. The model-building set was analyzed using seven different ML algorithms. The effects of potential covariates were evaluated using the least absolute shrinkage and selection operator algorithms. A separate evaluation set was used to assess the ability of all models to predict CsA blood concentration. R squared (R 2) scores, median prediction error (MDPE), median absolute prediction error (MAPE), and the percentages of PE within 20% (F20) and 30% (F30) were calculated to assess the predictive performance of these models. In addition, previously built popPK model was included for comparison. Results: Sixteen variables were selected as important covariates. Among ML models, the predictive performance of nonlinear-based ML models was superior to that of linear regression (MDPE: 3.27%, MAPE: 34.21%, F20: 30.63%, F30: 45.03%, R 2 score: 0.68). The ML model built with the artificial neural network algorithm was considered the most suitable (MDPE: -0.039%, MAPE: 25.60%, F20: 39.35%, F30: 56.46%, R 2 score: 0.75). Its performance was superior to that of the previously built popPK model (MDPE: 5.26%, MAPE: 29.22%, F20: 33.94%, F30: 51.22%, R 2 score: 0.68). Furthermore, the application of the most suitable model and the popPK model in clinic showed that most dose regimen recommendations were reasonable. Conclusion: The performance of these ML models indicate that a nonlinear relationship for covariates may help to improve model predictability. These results might facilitate the application of ML models in clinic, especially for patients with unstable status or during initial dose optimization.

Assessing academic impairment in college students with disabilities: A new measure to promote evidence-based accommodation granting

College students with disabilities may be entitled to academic accommodations such as additional time on exams, testing in a separate setting, or assistance with note-taking. To receive accommodations, students must request services from their college and show that they experience substantial limitations in academic functioning. Without norm-referenced data, it is difficult for college disability support professionals to determine if students’ self-reported academic problems reflect substantial limitations characteristic of a disability, or academic challenges experienced by most other students. The Academic Impairment Measure (AIM) is a brief, multidimensional, norm-referenced rating scale that can help professionals identify college students with significant impairment who need academic support. Exploratory and confirmatory factor analysis indicate that the AIM assesses seven distinct and interpretable domains of academic functioning relevant to postsecondary students. Initial studies also provide evidence of internal and temporal consistency; composite reliability; content, convergent and discriminant validity; and the ability to differentiate students with and without disabilities. Finally, the AIM includes a response validity scale to detect non-credible ratings. Normative data from a large, diverse standardization sample allow professionals to use AIM scores to screen students for significant impairment, tailor accommodations to students’ specific limitations, and monitor the effectiveness of accommodations over time.

The Agronomic Performance of Rice Seeds Coated with N-Enriched Organomineral Fertilizer

Seed coating with silicate rock-basis organomineral fertilizer (OMF) was proposed as an appropriate method to improve the productivity and profitability of rice farming. This research aimed to evaluate the growth and yield components of rice grown from coated seeds with N-enriched OMF. The coated seeds of two rice varieties, i.e., Trisakti (T) and Nutri Zinc (NZ) were tested in separate experimental sets. A randomized block design was applied for each experiment with the treatment consisting of non-coated seed (NCS), coated seeds containing 4.5% N (CS-1), 7.8% N (CS-2), and 9.0% N (CS-3) in 3 blocks. The coating material of OMF was a mixture of 90% basaltic rock and 10% rock phosphate, enriched with N accordingly to the treatment; and the weight ratio of seed to OMF was about 1:16. The coated seeds were planted directly to the ground (without sowing and transplanting steps), and only NCS was fertilized with NPK (15:15:15) equivalent to 300 kg. ha-1. Results reveal that there was no significant difference in growth components (number of tillers and the weight of top-biomass) and quality of rice grains (weight of 1,000 grains) for the plants of coated and non-coated seeds. Enriching OMF with N up to 9% consistently improved the total yield of rice. Therefore, seed coating with OMF containing about 9% N was an appropriate method to optimize rice yield.

Attitudes towards attractive and credible celebrities in advertisements

The saying, beauty is in the eye of the beholder, is relevant in the use of attractive and crediblecelebrities in advertisements. A celebrity endorser is seen as a model who enjoys recognition fromthe public and who can be seen as an ubiquitous feature of marketing today. The use of celebrityendorsers is a fairly common practice in many organisations in supporting their corporate orbrand image.This article focuses on both the attractiveness and also the credibility of celebrities in advertisements.It is anticipated that attractive celebrities and credible celebrities could influence attitudes positively,and that this will eventually lead to the purchasing of the advertised products and services.O’Mahony and Meenaghan’s (1997/1998) Perceptions of Celebrity Endorsements Scale was usedto measure the overall attitudes of students on celebrity endorsements. Separate sets of itemswere developed to measure attractive and credible celebrities separately. The internal consistencyreliability of these measurement scales reflected high scores (α > 0.70) on all items.In general, the respondents positively perceived celebrity endorsements. However, the overallrating of respondents in respect of an attractive celebrity in an advertisement was decidedly moreunfavourable. Results also showed attitudes towards credible celebrity endorsements to be neitherpositive nor negative

Assessing the DNA Damaging Effectiveness of Ionizing Radiation Using Plasmid DNA.

Plasmid DNA is useful for investigating the DNA damaging effects of ionizing radiation. In this study, we have explored the feasibility of plasmid DNA-based detectors to assess the DNA damaging effectiveness of two radiotherapy X-ray beam qualities after undergoing return shipment of ~8000 km between two institutions. The detectors consisted of of pBR322 DNA enclosed with an aluminum seal in nine cylindrical cavities drilled into polycarbonate blocks. We shipped them to Toronto, Canada for irradiation with either or X-ray beams to doses of 10, 20, and 30 in triplicate before being shipped back to San Diego, USA. The Toronto return shipment also included non-irradiated controls and we kept a separate set of controls in San Diego. In San Diego, we quantified DNA single strand breaks (SSBs), double strand breaks (DSBs), and applied Nth and Fpg enzymes to quantify oxidized base damage. The rate of DSBs/Gy/plasmid was greater for the 100 kVp than the 6 MV irradiation. The irradiation also resulted in times more DSBs/SSB than the beam, demonstrating that the detector is sensitive enough to quantify relative DNA damage effectiveness, even after shipment over thousands of kilometers.

Can Radiomics and Machine Learning Predict Diagnosis in Musculoskeletal Myxoid Soft Tissue Tumors?

Introduction: Differentiating benign and malignant musculoskeletal myxoid soft tissue tumors is challenging due to their shared clinical, imaging, and histologic features. We assess if radiomics and machine learning can assist in differentiating benign and malignant musculoskeletal myxoid tumors. Methods: Forty patients with a pre-treatment MRI and a histologically confirmed myxoid soft tissue tumor (20 myxomas and 20 myxofibrosarcomas) on final resection pathology were reviewed. Baseline clinical features consisted of patient age, sex, tumor size, tumor depth, tumor location, pain, and tumor as an incidental finding. Manual image segmentation of the tumor was performed on T1 and T2 images by attending clinicians. A LASSO model was used for MRI feature reduction. The performance of five machine learning models were implemented using cross validation and compared with classify benign and malignant myxoid soft tissue tumors. Results: The five models using T1 and T2 radiomics features + clinical features achieved mean area under the ROC curves (AUC) of 0.729 to 0.780 and accuracy of 0.696 to 0.757. The highest AUC achieved was 0.780 using a support vector machine model. All combined radiomics + clinical feature models outperformed the classification models using clinical features alone. Conclusion: Classification models using T1 and T2 radiomics features + clinical features perform better in differentiating benign and malignant myxoid soft tissue tumors than models using clinical features alone. Future studies include validation of these preliminary findings in a larger and separate data set, and comparison of the diagnostic performance of radiomics to manual review of images by clinicians.

Multivariate versus machine learning-based classification of rapid evaporative Ionisation mass spectrometry spectra towards industry based large-scale fish speciation

Detection and prevention of fish food fraud are of ever-increasing importance, prompting the need for rapid, high-throughput fish speciation techniques. Rapid Evaporative Ionisation Mass Spectrometry (REIMS) has quickly established itself as a powerful technique for the instant in situ analysis of foodstuffs. In the current study, a total of 1736 samples (2015–2021) - comprising 17 different commercially valuable fish species - were analysed using iKnife-REIMS, followed by classification with various multivariate and machine learning strategies. The results demonstrated that multivariate models, i.e. PCA-LDA and (O)PLS-DA, delivered accuracies from 92.5 to 100.0%, while RF and SVM-based classification generated accuracies from 88.7 to 96.3%. Real-time recognition on a separate test set of 432 samples (2022) generated correct speciation between 89.6 and 99.5% for the multivariate models, while the ML models underperformed (22.3–95.1%), in particular for the white fish species. As such, we propose a real-time validated modelling strategy using directly amenable PCA-LDA for rapid industry-proof large-scale fish speciation.

Postoperative vault prediction for phakic implantable collamer lens surgery: LASSO formulas.

To develop and evaluate reliable formulas for predicting postoperative vault more accurately after implantable collamer lens (ICL) surgery in a White patient population with varying degrees of ametropia. Private clinical practice. Retrospective analysis on dataset split into a separate training and test set. 115 eyes of 59 patients were used to train regression models predicting postoperative vault based on anterior segment optical coherence tomography (OCT) parameters (Least Absolute Shrinkage and Selection Operator [LASSO]-OCT formula), ocular biometry data (LASSO-Biometry formula), or data from both devices (LASSO-Full formula). The performance of these models was evaluated against the manufacturer's nomogram (Online Calculation and Ordering System [OCOS]) and Nakamura 1 (NK1) and 2 (NK2) formulas on a matched separate test set of 37 eyes of 19 patients. The mean preoperative spherical equivalent was -5.32 ± 3.37 (range: +3.75 to -17.375 diopters). The mean absolute errors of the estimated vs achieved postoperative vault for the LASSO-Biometry, LASSO-OCT, and LASSO-Full formulas were 144.1 ± 107.9 μm, 145.6 ± 100.6 μm, and 132.0 ± 86.6 μm, respectively. These results were significantly lower compared with the OCOS, NK1, and NK2 formulas ( P < .006). Postoperative vault could be estimated within 500 μm in 97.3% (LASSO-Biometry) to 100% of cases (LASSO-OCT and LASSO-Full). The LASSO suite provided a set of powerful, reproducible yet convenient ICL sizing formulas with state-of-the-art performance in White patients, including those with low to moderate degrees of myopia. The calculator can be accessed at http://icl.emmetropia.be .

Transcutaneous Pulsed RF Energy Transfer Mitigates Tissue Heating in High Power Demand Implanted Device Applications: In Vivo and In Silico Models Results.

This article presents the development of a power loss emulation (PLE) system device to study and find ways of mitigating skin tissue heating effects in transcutaneous energy transmission systems (TETS) for existing and next generation left ventricular assist devices (LVADs). Skin thermal profile measurements were made using the PLE system prototype and also separately with a TETS in a porcine model. Subsequent data analysis and separate computer modelling studies permit understanding of the contribution of tissue blood perfusion towards cooling of the subcutaneous tissue around the electromagnetic coupling area. A 2-channel PLE system prototype and a 2-channel TETS prototype were implemented for this study. The heating effects resulting from power transmission inefficiency were investigated under varying conditions of power delivery levels for an implanted device. In the part of the study using the PLE setup, the implanted heating element was placed subcutaneously 6–8 mm below the body surface of in vivo porcine model skin. Two operating modes of transmission coupling power losses were emulated: (a) conventional continuous transmission, and (b) using our proposed pulsed transmission waveform protocols. Experimental skin tissue thermal profiles were studied for various levels of LVAD power. The heating coefficient was estimated from the porcine model measurements (an in vivo living model and a euthanised cadaver model without blood circulation at the end of the experiment). An in silico model to support data interpretation provided reliable experimental and numerical methods for effective wireless transdermal LVAD energization advanced solutions. In the separate second part of the study conducted with a separate set of pigs, a two-channel inductively coupled RF driving system implemented wireless power transfer (WPT) to a resistive LVAD model (50 Ω) to explore continuous versus pulsed RF transmission modes. The RF-transmission pulse duration ranged from 30 ms to 480 ms, and the idle time (no-transmission) from 5 s to 120 s. The results revealed that blood perfusion plays an important cooling role in reducing thermal tissue damage from TETS applications. In addition, the results analysis of the in vivo, cadaver (R1Sp2) model, and in silico studies confirmed that the tissue heating effect was significantly lower in the living model versus the cadaver model due to the presence of blood perfusion cooling effects.

M6A/ m1A /m5C/m7G-related methylation modification patterns and immune characterization in prostate cancer.

Methylation has a close relationship with immune reactions, metastasis, and cancer cell growth. Additionally, RNA methylation-related proteins have emerged as potential cancer therapeutic targets. The connection between the tumor microenvironment (TME) and methylation-related genes (MRGs) remains unclear. We explored the expression patterns of the MRGs in the genome and transcriptional fields of 796 prostate cancer (PCa) samples using two separate data sets. We identified a relationship between patient clinicopathological characteristics, prognosis, TME cell infiltrating qualities, and different MRG changes, as well as the identification of two distinct molecular groupings. Then, we formed an MRGs model to predict overall survival (OS), and we tested the accuracy of the model in patients with PCa. In addition, we developed a very accurate nomogram to improve the MRG model’s clinical applicability. The low-risk group had fewer tumor mutational burden (TMB), greater tumor immune dysfunction and exclusion (TIDE) ratings, fewer mutant genes, and better OS prospects. We discuss how MGRs may affect the prognosis, clinically important traits, TME, and immunotherapy responsiveness in PCa. In order to get a better understanding of MRGs in PCa, we could further explore the prognosis and create more effective immunotherapy regimens to open new avenues.

Analyses of the collective properties of hadronic matter in Au-Au collisions at 54.4 GeV

We investigated the strange hadrons transverse momentum (${p}_{T}$) spectra in Au-Au collision at $\sqrt{{s}_{NN}}=54.4\text{ }\text{ }\mathrm{GeV}$ in the framework of modified Hagedorn function with embedded flow. It is found that the model can describe the particle spectra well. We extracted the kinetic freeze-out temperature ${T}_{0}$, transverse flow velocity ${\ensuremath{\beta}}_{T}$, kinetic freeze-out volume $V$, mean transverse momentum $⟨{p}_{T}⟩$, the entropy parameter $n$, and the multiplicity parameter ${N}_{0}$. We reported that all these parameters increase towards the central collisions. The larger kinetic freeze-out temperature, transverse flow velocity, kinetic freeze-out volume, and the entropy parameter ($n$) in central collisions compared to peripheral collisions show the early decoupling of the particles in central collisions. In addition, all the above parameters are mass dependent. The kinetic freeze-out temperature (${T}_{0}$), the entropy parameter $n$, and mean transverse momentum ($⟨{p}_{T}⟩$) are larger for massive particles, while the transverse flow velocity (${\ensuremath{\beta}}_{T}$), kinetic freeze-out volume ($V$), and the multiplicity parameter (${N}_{0}$) show the opposite behavior. Larger ${T}_{0}$, $n$, and smaller ${\ensuremath{\beta}}_{T}$ as well as $V$ of the heavier particles indicate the early freeze-out of the heavier particles, while larger $⟨{p}_{T}⟩$ for the heavier particles evince that the effect of radial flow is stronger in heavier particles. The separate set of parameters for each particle shows the multiple kinetic freeze-out scenario, where the mass-dependent kinetic freeze-out volume shows the volume differential freeze-out scenario. We also checked the correlation among different parameters, which include the correlation of ${T}_{0}$ and ${\ensuremath{\beta}}_{T}$, ${T}_{0}$ and $V$, ${\ensuremath{\beta}}_{T}$ and $V$, $⟨{p}_{T}⟩$ and ${T}_{0}$, $⟨{p}_{T}⟩$ and ${\ensuremath{\beta}}_{T}$, $⟨{p}_{T}⟩$, and $V$, $n$ and ${T}_{0}$, $n$ and ${\ensuremath{\beta}}_{T}$, and $n$ and $V$, and they all are observed to have positive correlations with each other which validates our results.

Numerical Modeling Unlocks Remarkable Ion Selectivity of Capacitive Deionization

Ion-selective water treatment is an important frontier in water research, as for many applications removing all ions indiscriminately leads to significant extra energy and downstream re-ionization costs. Capacitive deionization (CDI) is under intensive investigations for ion-selective treatment of polluted feedwaters [1]. CDI has the remarkable feature of being not only highly selective, but additionally dynamically tuneable to adjust, real-time, to varying feedwater composition and produced water targets [1]. However, we will show that to further develop CDI technologies to achieve desired separations, in feedwaters of several competing anions and cations, requires detailed numerical models. Such models couple ion transport theory to nanopore electrosorption, and often include pH dynamics. We here describe our recent work exploring the limits of ion-ion selectivity by capacitive deionization with inexpensive nanoporous carbon electrodes. We show how theory enabled us to achieve in the lab remarkable selectivity and a diverse set of separations, such as “perfect” divalent cation selectivity[2], monovalent ion selectivity[3], and removal of amphoteric pollutant species such as boric acid and nutrient species[4]. We show using strong-acid functionalized electrodes that the same two-electrode system can be used for either excellent divalent selectivity, or long-lasting monovalent ion selectivity, depending on cell operational parameters [2,3]. Our work furthers the argument that membraneless CDI, based on inexpensive and easily-scalable porous carbon electrodes, can address a wide variety of important applications in water treatment.

Explaining women's political underrepresentation in democracies with high levels of corruption

AbstractMany democracies with high levels of corruption are also characterized by low levels of women's political representation. Do women candidates in democracies with high levels of corruption face overt voter discrimination? Do gender dynamics that are unique to highly corrupt, democratic contexts influence citizens’ willingness to vote for women? We answer these questions using two separate sets of experiments conducted in Ukraine: two vignette experiments and a conjoint analysis. In line with existing cross-sectional research on Ukraine, our experiments reveal little evidence of direct voter bias against women candidates. Our conjoint analysis also offers novel insights into the preferences of Ukrainian voters, showing that both men and women voters place a great deal of value in anti-corruption platforms, but voters are just as likely to support women and men candidates who say they will fight corruption. Our analysis suggests that women's political underrepresentation in highly corrupt contexts is driven more by barriers that prevent women from winning party nominations and running for office in the first place, rather than overt discrimination at the polls.

Defining the pressures of a fluid in a nanoporous, heterogeneous medium

We describe the thermodynamic state of a single-phase fluid confined to a porous medium with Hill’s thermodynamics of small systems, also known as nanothermodynamics. This way of defining small system thermodynamics, with a separate set of control variables, may be useful for the study of transport in non-deformable porous media, where presently no consensus exists on pressure computations. For a confined fluid, we observe that there are two pressures, the integral and the differential pressures. We use molecular simulations to investigate and confirm the nanothermodynamic relations for a representative elementary volume (REV). For a model system of a single-phase fluid in a face-centered cubic lattice of solid spheres of varying porosity, we calculate the fluid density, fluid-solid surface tension, replica energy, integral pressure, entropy, and internal energy.

Identification of non-calcified coronary plaque characteristics using machine learning radiomic analysis of non-contrast high-resolution CT

Abstract Objective To explore whether machine learning (ML) radiomic analysis of low-dose, high-resolution, non-contrast, ECG gated cardiac CT scan allows identification of non-calcified coronary plaque characteristics. Background Novel imaging and analysis techniques may provide the ability to detect non-calcified or high risk coronary plaques on a non-contrast CT scan, advancing cardiovascular diagnostics. Methods We prospectively enrolled 125 patients with a non-calcified plaque and an adverse plaque characteristic (APC), and 25 controls without visible atherosclerosis on coronary CT angiography (CCTA). All patients underwent the non-contrast CT exam prior to CCTA. 419 radiomic features were calculated to identify: presence of any CAD, obstructive CAD (stenosis&amp;gt;50%), plaque with ≥2 APC, degree of calcification and specific APCs. ML models were trained on a training set (917 segmentations) and tested on a separate (validation) set (292 segmentations). Results Among the radiomic features 88.3% was associated with any plaque, 0.9% with obstructive CAD and 76.4% with presence of at least two APCs. Overall, 80.2%, 88.5% and 36.5%, of features were associated with calcified, partially calcified, and noncalcified plaques, respectively. Regarding APCs, 61.1%, 61.8%, 84.2%, and 61.3%, of features were associated with low attenuation (LAP), napkin-ring sign (NRS), spotty calcification (SC), and positive remodeling (PR), respectively. ML models outperformed conventional methods for the presence of plaque, obstructive stenosis, presence of 2 APC, as well as for noncalcified plaque and partially calcified plaque, but not for calcified plaque. ML models also significantly outperformed identification of LAP and PR, but neither NRS nor SC. Conclusions Radiomic analysis of non-contrast CT heart exams may allow identification of specific non-calcified coronary plaque characteristics which could aid cardiovascular risk stratification or pre-screening of individuals prior to contrast enhanced CCTA exam. Funding Acknowledgement Type of funding sources: Public grant(s) – National budget only. Main funding source(s): National Science Center

Differentiating Engineered Tissue Images and Experimental Factors to Classify Cardiomyocyte Content.

In this study, we used machine learning (ML) to classify the cardiomyocyte (CM) content on day 10 of the differentiation of human-induced pluripotent stem cell (hiPSC)-laden microspheroids using easily acquirable nondestructive phase-contrast images taken in the middle of differentiation and tunable experimental parameters. Scale-up suspension culture, use of engineered tissues to support stem cell differentiation, and CM production for improved control over cellular microenvironment in the suspension system need nondestructive methods to track engineered tissue development. The ability to couple images that capture experimenter perceived "good" or "bad" batches based on visualization at early differentiation time points with actual experimental outcomes in an unbiased way is a step toward building these methods. In recent years, ML techniques have been successfully applied to identify critical process parameters and use this information to build models that describe process outcomes in cell production and hiPSC differentiation. Building upon these successes, here, we utilize convolutional neural networks (CNNs) to build a binary classifier model for CM content on differentiation day 10 (dd10) for hiPSC-CMs. We consider two separate data sets as potential input features for the classification models. The first set includes phase-contrast images of microspheroid tissues taken on days 3 and 5 of the differentiation batches at different experimental conditions. The second set supplements the images with tunable experimental differentiation parameters, such as cell concentration and microspheroids' size. The CM content classes were sufficient and insufficient. The accuracy of the CNN classifier using images only was 63%. The addition of experimental features increased the accuracy to 85%, indicating the importance of tunable parameters in predicting CM content. Impact statement Machine learning approaches were used to predict the final cardiomyocyte (CM) content class (sufficient vs. insufficient) of engineered cardiac tissue microspheroids produced through suspension-based cardiac differentiation of human-induced pluripotent stem cell-laden engineered tissue microspheroids. The models used specified experimental features and data collected using nondestructive inexpensive methods, specifically phase-contrast images taken during the initial days of differentiation as inputs. The best model was a convolutional neural network trained using experimental features and differentiation day 5 images. It classified the CM content with 85% accuracy and replicated and formalized experimenter's visual intuition about differentiation outcomes by incorporating images from early time points.