External Validation Test Research Articles

Cross-cultural adaptation and validation of the Thai version of the functional index for hand osteoarthritis (FIHOA)

BackgroundThe Functional Index for Hand Osteoarthritis (FIHOA) is a simple tool to assess functional impairment for hand OA patients. The purpose of this study was to translate the FIHOA into the Thai language, and validate it in Thai hand OA patients.MethodsThe FIHOA was translated into Thai (T-FIHOA) according to the principles of cross-cultural adaptation and administered to 102 hand OA patients recruited between September 2020 and July 2021 together with the modified Health Assessment Questionnaire (mHAQ), Disabilities of the Arm, Shoulder and Hand (DASH), and visual analogue scale (VAS) for hand pain. Spearman’s correlation coefficient and intraclass correlation coefficient (ICC) were used to check the test-retest reliability of each item and the total scores in the translated questionnaire. The internal consistency reliability was evaluated using Cronbach’s alpha. The external construct validity was assessed using correlations between the T-FIHOA, mHAQ, DASH and hand pain VAS.ResultsThe T-FIHOA had a unidimensional structure. The ICC was > 0.9 and the Cronbach’s alpha of 0.92 indicated excellent reliability and internal consistency, respectively. The external validity tests indicated moderate correlation with the hand pain VAS (r = 0.37, P < 0.01) and moderate to strong correlations with the mHAQ (r = 0.63, P < 0.01), and DASH score (r = 0.52, P < 0.01). The T-FIHOA had the highest effect size (ES) and standardized response mean (SRM) (− 0.37 and − 0.58 respectively) among all questionnaires except for the VAS when assessing changes between baseline and week 4.ConclusionsThe T-FIHOA is a good and reliable assessment tool freely available for practitioners/researchers to evaluate functional impairment in Thai hand OA patients.

Perioperative Risk Factors Associated with Unplanned Neurological Intensive Care Unit Events Following Elective Infratentorial Brain Tumor Resection

Our aim of this study was to identify risk factors and develop a prediction model for unplanned neurological intensive care unit (NICU) events after elective infratentorial brain tumor resection in order to propose an individualized admission to the NICU tailored to patient needs. Patients admitted to our NICU between September 2018 and May 2021 after elective infratentorial brain tumor resection were reviewed. Prolonged NICU stays and unplanned NICU admissions were defined as unplanned NICU events. The prognostic model of unplanned NICU events was developed using a forward stepwise logistic regression analysis, and external validation was evaluated. The C-statistic was used to assess discrimination, and a smooth, nonparametric calibration line was used to assess calibration graphically in the model. Of the 1,710 patients in the development cohort, unplanned NICU events occurred in 162 (9.5%). Based on the lesion type, a Karnofsky Performance Status score <70 at admission, longer duration of surgery, bleeding in the operative area evident on postoperative computed tomography, higher fibrinogen and blood glucose levels at admission, and more intraoperative blood loss were independently associated with unplanned NICU events. The external validation test showed good discrimination (C-statistic= 0.811) and calibration (Hosmer-Lemeshow P= 0.141) for unplanned NICU events. Several patient and operative characteristics are associated with a greater likelihood of the occurrence of unplanned NICU events. In the future, we may be able to provide better help for the resource allocation of NICUs according to these risk factors and prediction models.

First QSPR models to predict the thermal stability of potential self-reactive substances

Self-reactive substances are unstable chemical substances which can easily decompose and may lead to explosion in transport, storage, or process situations. For this reason, their thermal stability properties are required to assess possible process safety issues and for classification purpose. In this study, the first quantitative structure–property relationships (QSPR) dedicated to this class of compounds were developed to predict the heat of decomposition of possible self-reactive substances from their molecular structures. The database used to develop and validate the models was issued from a dedicated experimental campaign on 50 samples using differential scanning calorimetry in homogeneous experimental conditions. QSPR models were derived using the GA-MLR methods (using a genetic algorithm and multi-linear regressions) using molecular descriptors calculated by Dragon software based on two types of inputs: 3D molecular structures determined using the density functional theory (DFT), allowing access to three-dimensional descriptors, and from SMILES codes, favoring the access to simpler models, requiring no preliminary quantum chemical calculations. All models respected the OECD validation guidelines for regulatory acceptability of QSPR models. They were tested by internal and external validation tests and their applicability domains were defined and analyzed.

Using Artificial Intelligence to Revolutionise the Patient Care Pathway in Hip and Knee Arthroplasty (ARCHERY): Protocol for the Development of a Clinical Prediction Model.

BackgroundHip and knee osteoarthritis is substantially prevalent worldwide, with large numbers of older adults undergoing joint replacement (arthroplasty) every year. A backlog of elective surgery due to the COVID-19 pandemic, and an aging population, has led to substantial issues with access to timely arthroplasty surgery. A potential method to improve the efficiency of arthroplasty services is by increasing the percentage of patients who are listed for surgery from primary care referrals. The use of artificial intelligence (AI) techniques, specifically machine learning, provides a potential unexplored solution to correctly and rapidly select suitable patients for arthroplasty surgery.ObjectiveThis study has 2 objectives: (1) develop a cohort of patients with referrals by general practitioners regarding assessment of suitability for hip or knee replacement from National Health Service (NHS) Grampian data via the Grampian Data Safe Haven and (2) determine the demographic, clinical, and imaging characteristics that influence the selection of patients to undergo hip or knee arthroplasty, and develop a tested and validated patient-specific predictive model to guide arthroplasty referral pathways.MethodsThe AI to Revolutionise the Patient Care Pathway in Hip and Knee Arthroplasty (ARCHERY) project will be delivered through 2 linked work packages conducted within the Grampian Data Safe Haven and Safe Haven Artificial Intelligence Platform. The data set will include a cohort of individuals aged ≥16 years with referrals for the consideration of elective primary hip or knee replacement from January 2015 to January 2022. Linked pseudo-anonymized NHS Grampian health care data will be acquired including patient demographics, medication records, laboratory data, theatre records, text from clinical letters, and radiological images and reports. Following the creation of the data set, machine learning techniques will be used to develop pattern classification and probabilistic prediction models based on radiological images. Supplemental demographic and clinical data will be used to improve the predictive capabilities of the models. The sample size is predicted to be approximately 2000 patients—a sufficient size for satisfactory assessment of the primary outcome. Cross-validation will be used for development, testing, and internal validation. Evaluation will be performed through standard techniques, such as the C statistic (area under curve) metric, calibration characteristics (Brier score), and a confusion matrix.ResultsThe study was funded by the Chief Scientist Office Scotland as part of a Clinical Research Fellowship that runs from August 2021 to August 2024. Approval from the North Node Privacy Advisory Committee was confirmed on October 13, 2021. Data collection started in May 2022, with the results expected to be published in the first quarter of 2024. ISRCTN registration has been completed.ConclusionsThis project provides a first step toward delivering an automated solution for arthroplasty selection using routinely collected health care data. Following appropriate external validation and clinical testing, this project could substantially improve the proportion of referred patients that are selected to undergo surgery, with a subsequent reduction in waiting time for arthroplasty appointments.Trial RegistrationISRCTN Registry ISRCTN18398037; https://www.isrctn.com/ISRCTN18398037International Registered Report Identifier (IRRID)PRR1-10.2196/37092

Convolutional neural network propagation on electroencephalographic scalograms for detection of schizophrenia

ObjectiveElectroencephalographic analysis (EEG) has emerged as a powerful tool for brain state interpretation. Studies have shown distinct deviances of patients with schizophrenia in EEG activation at specific frequency bands. MethodsEvidence is presented for the validation of a Convolutional Neural Network (CNN) model using transfer learning for scalp EEGs of patients and controls during the performance of a speeded sensorimotor task and a working memory task. First, we trained a CNN on EEG data of 41 schizophrenia patients (SCZ) and 31 healthy controls (HC). Secondly, we used a pretrained model for training. Both models were tested in an external validation set of 15 SCZ, 16 HC, and 12 first-degree relatives. ResultsUsing the layer-wise relevance propagation on the classification decision, a heatmap was produced for each subject, specifying the pixel-wise relevance. The CNN model resulted in the first case in a balanced accuracy of 63.7% and 81.5% in the second case, on the external validation test 64.5% and 83.2%, respectively. ConclusionsThe theta and alpha frequency bands of the EEG signals had significant relevance to the CNN classification decision and predict the first-degree relatives indicating potential heritable functional deviances. SignificanceThe proposed methodology results in important advancements for the identification of biomarkers in schizophrenia heritability.

Theoretical activity prediction, structure-based design, molecular docking and pharmacokinetic studies of some maleimides against Leishmania donovani for the treatment of leishmaniasis

BackgroundLeishmaniasis is a neglected tropical disease caused by a group of protozoan of the genus Leishmania and transmitted to humans majorly through the bite of the female sand fly. It is prevalent in the tropical regions of the world especially in Africa and estimated to affect a population of about 12 million people annually. This theoretical study was therefore conducted in support of the search for more effective drug candidates for the treatment of leishmaniasis. This study focuses on the in silico activity prediction of twenty-eight (28) maleimides, structure-based design, molecular docking study and pharmacokinetics analysis of the newly designed maleimides. All the studied compounds were drawn using ChemDraw Ultra and optimized by the density functional theory (DFT) approach using B3LYP with 6-31G⁄ basis set.ResultsThe built QSAR model was found to satisfy the requirement of both internal and external validation tests for an acceptable QSAR model with R2 = 0.801, R2adj = 0.748, Q2cv = 0.710, R2test = 0.892 and cRp2 = 0.664 and has shown excellent prediction of the studied compounds. Among the five (5) protein receptors utilized for the virtual docking screening, pyridoxal kinase (PdxK) receptor (Pdb id = 6k91) showed the strongest binding interactions with compounds 14, 21 and 24 with the highest binding affinities of − 7.7, − 7.7 and − 7.8 kcal/mol, respectively. The selected templates (14, 21 and 24) were used to design twelve (12) new compounds (N1–N12) with higher docking scores than the templates. N7 (affinity = − 8.9 kcal/mol) and N12 (− 8.5 kcal/mol) showed higher binding scores than the reference drug pentamidine (− 8.10 kcal/mol), while N3 and N7–N12 showed higher predicted pIC50 than the templates. Also, the pharmacokinetics properties prediction revealed that the newly designed compounds, obeyed the Lipinski’s rule for oral bio-availability, showed high human intestinal absorption (HIA), low synthetic accessibility score, CNS and BBB permeability and were pharmacologically active.ConclusionsThe activities of the various maleimides were predicted excellently by the built QSAR model. Based on the pharmacokinetics and molecular docking studies therefore, the newly designed compounds are suggested for further practical evaluation and/or validation as potential drug candidates for the treatment of leishmaniasis.

Artificial Intelligence in Fracture Detection: A Systematic Review and Meta-Analysis.

Background Patients with fractures are a common emergency presentation and may be misdiagnosed at radiologic imaging. An increasing number of studies apply artificial intelligence (AI) techniques to fracture detection as an adjunct to clinician diagnosis. Purpose To perform a systematic review and meta-analysis comparing the diagnostic performance in fracture detection between AI and clinicians in peer-reviewed publications and the gray literature (ie, articles published on preprint repositories). Materials and Methods A search of multiple electronic databases between January 2018 and July 2020 (updated June 2021) was performed that included any primary research studies that developed and/or validated AI for the purposes of fracture detection at any imaging modality and excluded studies that evaluated image segmentation algorithms. Meta-analysis with a hierarchical model to calculate pooled sensitivity and specificity was used. Risk of bias was assessed by using a modified Prediction Model Study Risk of Bias Assessment Tool, or PROBAST, checklist. Results Included for analysis were 42 studies, with 115 contingency tables extracted from 32 studies (55 061 images). Thirty-seven studies identified fractures on radiographs and five studies identified fractures on CT images. For internal validation test sets, the pooled sensitivity was 92% (95% CI: 88, 93) for AI and 91% (95% CI: 85, 95) for clinicians, and the pooled specificity was 91% (95% CI: 88, 93) for AI and 92% (95% CI: 89, 92) for clinicians. For external validation test sets, the pooled sensitivity was 91% (95% CI: 84, 95) for AI and 94% (95% CI: 90, 96) for clinicians, and the pooled specificity was 91% (95% CI: 81, 95) for AI and 94% (95% CI: 91, 95) for clinicians. There were no statistically significant differences between clinician and AI performance. There were 22 of 42 (52%) studies that were judged to have high risk of bias. Meta-regression identified multiple sources of heterogeneity in the data, including risk of bias and fracture type. Conclusion Artificial intelligence (AI) and clinicians had comparable reported diagnostic performance in fracture detection, suggesting that AI technology holds promise as a diagnostic adjunct in future clinical practice. Clinical trial registration no. CRD42020186641 © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Cohen and McInnes in this issue.

Development and Calibration of the PREMIUM Item Bank for Measuring Respect and Dignity for Patients with Severe Mental Illness.

Most patient-reported experience measures (PREMs) are paper-based, leading to a high burden for patients and care providers. The aim of this study was to (1) calibrate an item bank to measure patients’ experience of respect and dignity for adult patients with serious mental illnesses and (2) develop computerized adaptive testing (CAT) to improve the use of this PREM in routine practice. Patients with schizophrenia, bipolar disorder, and major depressive disorder were enrolled in this multicenter and cross-sectional study. Psychometric analyses were based on classical test and item response theories and included evaluations of unidimensionality, local independence, and monotonicity; calibration and evaluation of model fit; analyses of differential item functioning (DIF); testing of external validity; and finally, CAT development. A total of 458 patients participated in the study. Of the 24 items, 2 highly inter-correlated items were deleted. Factor analysis showed that the remaining items met the unidimensional assumption (RMSEA = 0.054, CFI = 0.988, TLI = 0.986). DIF analyses revealed no biases by sex, age, care setting, or diagnosis. External validity testing has generally supported our assumptions. CAT showed satisfactory accuracy and precision. This work provides a more accurate and flexible measure of patients’ experience of respect and dignity than that obtained from standard questionnaires.

412 Outcome Forecasting in Aneurysmal Subarachnoid Hemorrhage: Comparison of a Neural Network Model With Conventional Logistic Regression

INTRODUCTION: Interest in machine-learning-(ML)-based predictive modeling has led to the development of models predicting aneurysmal subarachnoid hemorrhage (aSAH) outcome, including the Nijmegen acute Subarachnoid Hemorrhage calculator (Nutshell). Generalizability of such models to external data and their performance in comparison to more established conventional logistic-regression-based models, such as the Subarachnoid-Hemorrhage-International-Trialists-(SAHIT) calculator tool, remains unclear. METHODS: A prospectively-maintained database of aSAH patients presenting consecutively to our institution in the 2013-2018 period was used. The web-based Nutshell (https://nutshell-tool.com/) and SAHIT (http://sahitscore.com) calculators were used to derive the risks of poor long-term (12-18 month) outcome and 30-day mortality. Discrimination and calibration were evaluated using area under the curve (AUC) and calibration plots. Literature on relevant ML models was surveyed for a synopsis. RESULTS: The SAHIT models outperformed the Nutshell tool in predicting long-term functional outcome (AUC: 0.786 vs. 0.689, p = 0.025) and 30-day mortality (AUC: 0.810 vs. 0.636, p &lt; 0.001). Calibration properties were additionally more favorable for the SAHIT models. Most published aneurysm-related ML-based outcome models lack external validation and usable testing platforms. In total, 24 studies utilizing ML models were identified in our literature review, evaluating various aSAH-related and aneurysm treatment outcomes. Only two studies pursued external validation, and only five provided a testing platform for their model to be used by external researchers (e.g. scoring system, calculator, decision tree etc.). CONCLUSION: The Nutshell tool demonstrated limited performance upon external validation in comparison to the SAHIT models. External validation and the dissemination of testing platforms for ML models must be emphasized.

Machine learning to predict progression of non-alcoholic fatty liver to non-alcoholic steatohepatitis or fibrosis.

BackgroundNon‐alcoholic fatty liver (NAFL) can progress to the severe subtype non‐alcoholic steatohepatitis (NASH) and/or fibrosis, which are associated with increased morbidity, mortality, and healthcare costs. Current machine learning studies detect NASH; however, this study is unique in predicting the progression of NAFL patients to NASH or fibrosis.AimTo utilize clinical information from NAFL‐diagnosed patients to predict the likelihood of progression to NASH or fibrosis.MethodsData were collected from electronic health records of patients receiving a first‐time NAFL diagnosis. A gradient boosted machine learning algorithm (XGBoost) as well as logistic regression (LR) and multi‐layer perceptron (MLP) models were developed. A five‐fold cross‐validation grid search was utilized for hyperparameter optimization of variables, including maximum tree depth, learning rate, and number of estimators. Predictions of patients likely to progress to NASH or fibrosis within 4 years of initial NAFL diagnosis were made using demographic features, vital signs, and laboratory measurements.ResultsThe XGBoost algorithm achieved area under the receiver operating characteristic (AUROC) values of 0.79 for prediction of progression to NASH and 0.87 for fibrosis on both hold‐out and external validation test sets. The XGBoost algorithm outperformed the LR and MLP models for both NASH and fibrosis prediction on all metrics.ConclusionIt is possible to accurately identify newly diagnosed NAFL patients at high risk of progression to NASH or fibrosis. Early identification of these patients may allow for increased clinical monitoring, more aggressive preventative measures to slow the progression of NAFL and fibrosis, and efficient clinical trial enrollment.

External Validation of a Neural Network Model in Aneurysmal Subarachnoid Hemorrhage: A Comparison With Conventional Logistic Regression Models

Interest in machine learning (ML)-based predictive modeling has led to the development of models predicting outcomes after aneurysmal subarachnoid hemorrhage (aSAH), including the Nijmegen acute subarachnoid hemorrhage calculator (Nutshell). Generalizability of such models to external data remains unclear. To externally validate the performance of the Nutshell tool while comparing it with the conventional Subarachnoid Hemorrhage International Trialists (SAHIT) models and to review the ML literature on outcome prediction after aSAH and aneurysm treatment. A prospectively maintained database of patients with aSAH presenting consecutively to our institution in the 2013 to 2018 period was used. The web-based Nutshell and SAHIT calculators were used to derive the risks of poor long-term (12-18 months) outcomes and 30-day mortality. Discrimination was evaluated using the area under the curve (AUC), and calibration was investigated using calibration plots. The literature on relevant ML models was surveyed for a synopsis. In 269 patients with aSAH, the SAHIT models outperformed the Nutshell tool (AUC: 0.786 vs 0.689, P = .025) in predicting long-term functional outcomes. A logistic regression model of the Nutshell variables derived from our data achieved adequate discrimination (AUC = 0.759) of poor outcomes. The SAHIT models outperformed the Nutshell tool in predicting 30-day mortality (AUC: 0.810 vs 0.636, P < .001). Calibration properties were more favorable for the SAHIT models. Most published aneurysm-related ML-based outcome models lack external validation and usable testing platforms. The Nutshell tool demonstrated limited performance on external validation in comparison with the SAHIT models. External validation and the dissemination of testing platforms for ML models must be emphasized.

A novel prognostic model: which group of esophageal squamous cell carcinoma patients could benefit from adjuvant chemotherapy.

BackgroundThis study aimed to establish a reliable model for predicting the overall survival (OS) of esophageal squamous cell carcinoma (ESCC) patients and identifying the potential beneficiaries of adjuvant chemotherapy after esophagectomy.MethodsThis retrospective study included 819 ESCC patients who underwent esophagectomy as the training cohort. We constructed a prognostic model named GTLN2. Both internal and external validation tests were performed. Potential beneficiaries were defined as ESCC patients who obtained a significantly longer OS after adjuvant chemotherapy. Propensity score matching (PSM) was utilized in the subgroup analysis to screen ESCC beneficiaries of adjuvant chemotherapy.ResultsWe enrolled a total of 819 cT1b-3 patients in the training cohort. Multiple prognostic factors were associated with adjuvant chemotherapy. Using uni-/multivariate analysis, histological grade (G), tumor invasion depth (T), regional lymph node metastasis (N), and the number of cleared lymph nodes (NCLNs) were identified as independent prognostic factors. Then, we developed the GTLN2 model based on these predictors and validated it using internal calculations [the 1-, 3- and 5-year area under the curves (AUCs) were 0.692, 0.685 and 0.680, respectively; P<0.001] and external cohorts (the 1-, 3-, and 5-year AUCs were 0.651, 0.619 and 0.650, respectively; P<0.001). ESCC patients were categorized into high- and low-risk groups based on their assigned risk scores. After 1:1 patient pairing was performed by PSM in the high-risk group, better OS was noted in patients receiving adjuvant chemotherapy (P=0.024).ConclusionsDifferentiating high- and low-risk patient groups via a novel mathematical prediction model allows physicians to identify patients in need of adjuvant chemotherapy accurately.

Construction and Multicenter Diagnostic Verification of Intelligent Recognition System for Endoscopic Images From Early Gastric Cancer Based on YOLO-V3 Algorithm.

IntroductionEndoscopy is an important tool for the diagnosis of early gastric cancer. Therefore, a combination of artificial intelligence and endoscopy has the ability to increase the speed and efficiency of early gastric cancer diagnosis. YOU ONLY LOOK ONCE (YOLO) is an advanced object detection depth neural network algorithm that has not been widely used in gastrointestinal image recognition.ObjectiveWe developed an artificial intelligence system herein referred to as “EGC-YOLO” for the rapid and accurate diagnosis of endoscopic images from early gastric cancer.MethodsMore than 40000 gastroscopic images from 1653 patients in Yixing people’s Hospital were used as the training set for the system, while endoscopic images from the other two hospitals were used as external validation test sets. The sensitivity, specificity, positive predictive value, Youden index and ROC curve were analyzed to evaluate detection efficiencies for EGC-YOLO.ResultsEGC-YOLO was able to diagnose early gastric cancer in the two test sets with a high superiority and efficiency. The accuracy, sensitivity, specificity and positive predictive value for Test Sets 1 and 2 were 85.15% and 86.02%, 85.36% and 83.02%, 84.41% and 92.21%, and 95.22% and 95.65%, respectively. In Test Sets 1 and 2, the corresponding Threshold-values were 0.02, 0.16 and 0.17 at the maximum of the Youden index. An increase in Threshold-values was associated with a downward trend in sensitivity and accuracy, while specificity remained relatively stable at more than 80%.ConclusionsThe EGC-YOLO system is superior for the efficient, accurate and rapid detection of early gastric cancer lesions. For different data sets, it is important to select the appropriate threshold-value in advance to achieve the best performance of the EGC-YOLO system.

Quantitative Structure-Activity Relationship (QSAR) Study of a Series of Chalcone Derivatives Inhibiting Plasmodium Falciparum 3D7

This Quantitative Structure-Activity Relationship (QSAR) study was conducted using a series of twenty (20) chalcone derivatives with inhibitory activities against Plasmodium falciparum 3D7. The molecules were optimized at the B3LYP/LanL2DZ computational level, to obtain the molecular descriptors. This work was performed using the Linear Multiple Regression (LMR) method, the NonLinear Regression (NLMR) and the Artificial Neural Network (ANN) method. These tools allowed us to obtain three (3) quantitative models from the quantum descriptors that are, the overall softness (S), the bond lengths l(c=o) and l(c=c), and the polarizability (α). These models have good statistical performance. Among them, the ANN has a significantly better predictive ability <i>R² =</i>0.997; <I>RMCE</I> = 0.035; <I>F</I>= 3571.499. The external validation tests verify all the criteria of Tropsha <i>et al.</i> and Roy <i>et al.</i> Also, the applicability domain of this model determined from the levers shows that a prediction of the pIC50 of new chalcone derivatives is acceptable when its lever value is lower than 1.07. For the ANN method, the Ch19 molecule is certainly outside the applicability domain, but it is not an influential point for the model, because this derivative belongs to the validation set, and therefore was not used in the model development. The behavior of this molecule could be explained by its structural diversity.

Quantitative Structure-Activity Relationship Study of a Benzimidazole-Derived Series Inhibiting &amp;lt;i&amp;gt;Mycobacterium tuberculosis H37Rv&amp;lt;/i&amp;gt;

This work was carried out on a series of twenty-two (22) benzimidazole derivatives with inhibitory activities against Mycobacterium tuberculosis H37Rv by applying the Quantitative Structure-Activity Relationship (QSAR) method. The molecules were optimized at the level DFT/B3LYP/6-31 + G (d, p), to obtain the molecular descriptors. We used three statistical learning tools namely, the linear multiple regression (LMR) method, the nonlinear regression (NLMR) and the artificial neural network (ANN) method. These methods allowed us to obtain three (3) quantitative models from the quantum descriptors that are, chemical potential (μ), polarizability (α), bond length l (C = N), and lipophilicity. These models showed good statistical performance. Among these, the ANN has a significantly better predictive ability R2 = 0.9995; RMSE = 0.0149; F = 31879.0548. The external validation tests verify all the criteria of Tropsha et al. and Roy et al. Also, the internal validation tests show that the model has a very satisfactory internal predictive character and can be considered as robust. Moreover, the applicability range of this model determined from the levers shows that a prediction of the pMIC of the new benzimidazole derivatives is acceptable when its lever value is lower than 1.

Activity modeling, molecular docking and pharmacokinetic studies of some boron-pleuromutilins as anti-wolbachia agents with potential for treatment of filarial diseases

Lymphatic filariasis and Onchocerciasis remain one of the oldest known Neglected Tropical Diseases (NTD) caused by a group of parasitic filarial nematodes co-habiting with the bacteria wolbachia. One good treatment method focuses on the elimination of this symbiotic wolbachia. In this work, an in-silico study was conducted to investigate the anti-wolbachia activities of 52 boron-pleuromutilin analogues. The Density Functional Theory approach was employed to optimize the chemical structures of the various molecules while utilizing B3LYP with 6–31G⁄ basis set. Genetic Function Algorithm was used to generate four (4) models. Model 3 was found to best satisfy the conditions of the internal and external validation tests for a good QSAR model with R2 =0.9151, R2adj =0.8939, Q2cv =0.8509, R2test =0.7516 and cRp2 =0.7955. The result of standard docking performed between nine (9) selected ligands and the receptor Wol Tl IF-1 using iGEMDOCK showed binding energies ranging from -82.24 to -96.85 kcal/mol. ADMET and drug-likeness properties prediction showed that Compound 49 has the best pharmacokinetic profile, with good pharmacological interactions, majorly, H-bonding and hydrophobic interactions with receptor's amino acids. This study has, therefore, provided useful information for future works pertaining design of new wolbachia inhibitors with improved anti-proliferative activity.

Translation, Reliability Assessment, and Validation of the Persian Version of MedRisk Instrument for Measuring Patient Satisfaction With Physical Therapy Care (20-Item MRPS)

Introduction: This study aimed to evaluate the reliability and validity of the Persian version of the 20-item version of the MedRisk. Materials and Methods: In our study, we used a cross-sectional and prospective validation study design. This research was a test development study involving 297 outpatients with musculoskeletal disorders from the physiotherapy centers in Kerman City, Iran, in 2017. All patients completed the MedRisk instrument for measuring patient satisfaction with physical therapy care. Participants also answered a demographic questionnaire, visual analog score, and global rating of change. Internal consistency and reproducibility were investigated, too. To determine test-retest reliability, 40 randomly selected patients completed the MedRisk instrument again 5-7 days after their treatment. Factor analysis, divergent validity, convergent validity, and the floor and ceiling effects were tested, too. The Ethics Committee of the University of Social Welfare and Rehabilitation Sciences, Tehran, Iran, reviewed and approved this research project. The SPSS software-24 was used for statistical analysis. Results: Dimension of MedRisk demonstrated a high internal consistency (the Cronbach alpha=0.82). Reproducibility was also satisfactory (intraclass correlation coefficient=0.76). The standard error of measurement, minimal detectable changes, and coefficients of variation indices were respectively 0.63, 1.76, and 0.13 for the total score. In factor analysis, the 4-factor solution has emerged. The external validity testing revealed that the MedRisk instrument score correlated negatively with the visual analog scale (r=-0.18, P=0.002) and global rating of change (r=-0.19, P=0.001). Eighteen individual items of MedRisk were positively correlated with global satisfaction. The results showed that items 5 and 7 had a floor effect, and all other items except items 4, 5, and 7 had a ceiling effect. Conclusion: The Persian version of the MedRisk instrument is a valid and reliable instrument for measuring patient satisfaction with physical therapy and can be used in a clinical setting.

Quantative STRUCTURE Activity Relationship (QSAR) Study of a Series of Molecules Derived from 2,3-dihydro-1H- perimidine having Activity against Protein Tyrosine Phosphatase 1B

In order to study the Quantitative Structure Activity Relationship (QSAR) against protein tyrosine phosphatase 1B and descriptors, we used a series of fourteen (14) molecules derived from perimidine. The compounds were optimized at the computational level B3LYP / 6-31 G (d, p), to obtain the descriptors of the model. This study was performed using the Linear Multiple Regression (MLR) method. This tool allowed us to obtain a quantitative model from the descriptors that are, the overall softness (S), the energy of the lowest vacant (ELUMO), the bond length l (N-C1). This model has good statistical performance (R2 = 0.958; RMCE = 0.110; F = 43.870). In addition, the external validation test of Tropsha and the domain of applicability from the levers were verified.

Strategic-level performance enhancement of a 660 MWe supercritical power plant and emissions reduction by AI approach

Power plant heat rate is a plant level performance parameter that indicates the economy of power production, equipment’s safety, and availability. In this paper, seven operating parameters, including the performance indices of integrated energy devices and the environmental conditions are incorporated for modeling the power plant heat rate by Artificial Neural Network (ANN), Support Vector Machine (SVM), and automated machine learning (AutoML) approach. The parametric significance order is determined by ANN and SVM-based Monte Carlo analytics and other machine learning-driven algorithms. Subsequently, the best-performing model is selected based on the external validation test and deployed for knowledge mining purposes. The improvement in the power plant heat rate by the parametric adjustment is achieved and subsequently, up to 3.12 percentage point (pp) increase in the thermal efficiency of the power plant is confirmed.Moreover, the fuel savings corresponding to the improved power plant heat rate are also calculated at three power generation modes. Their equivalence to an annual reduction in emissions is quantified. It is estimated that the accumulated reduction in CO2, SO2, CH4, N2O, and Hg emissions, i.e., 288.2 kilo tons / year (kt/y), can be achieved under 3.15% improvement in the power plant heat rate, corresponding to 75% power generation mode.

Improving the accuracy of prognosis for clinical stage I solid lung adenocarcinoma by radiomics models covering tumor per se and peritumoral changes on CT.

To assess methods to improve the accuracy of prognosis for clinical stage I solid lung adenocarcinoma using radiomics based on different volumes of interests (VOIs). This retrospective study included patients with postoperative clinical stage I solid lung adenocarcinoma from two hospitals, center 1 and center 2. Three databases were generated: dataset A (training set from center 1), dataset B (internal test set from center 1), and dataset C (external validation test from center 2). Disease-free survival (DFS) data were collected. CT radiomics models were constructed based on four VOIs: gross tumor volume (GTV), 3 mm external to the tumor border (peritumoral volume [PTV]0~+3), 6 mm crossing tumor border (PTV-3~+3), and 6 mm external to the tumor border (PTV0~+6). The area under the receiver operating characteristic curve (AUC) was used to compare the model accuracies. A total of 334 patients were included (204 and 130 from centers 1 and 2). The model using PTV-3~+3 (AUC 0.81 [95% confidence interval {CI}: 0.75, 0.94], 0.81 [0.63, 0.90] for datasets B and C) outperformed the other three models, GTV (0.73 [0.58, 0.81], 0.73 [0.58, 0.83]), PTV0~+3 (0.76 [0.52, 0.87], 0.75 [0.60, 0.83]), and PTV0~+6 (0.72 [0.60, 0.81], 0.69 [0.59, 0.81]), in datasets B and C, all p < 0.05. A radiomics model based on a VOI of 6 mm crossing tumor border more accurately predicts prognosis of clinical stage I solid lung adenocarcinoma than that based on VOIs including overall tumor or external rims of 3 mm and 6 mm. • Radiomics is a useful approach to improve the accuracy of prognosis for stage I solid adenocarcinoma. • The radiomics model based on VOIs that includes 3 mm within and external to the tumor border (peritumoral volume [PTV]-3~+3) outperformed models that included either only the tumor itself or those that only included the peritumoral volume.