The Image Biomarker Standardization Initiative: Standardized Convolutional Filters for Reproducible Radiomics and Enhanced Clinical Insights.

Filters are commonly used to enhance specific structures and patterns in images, such as vessels or peritumoral regions, to enable clinical insights beyond the visible image using radiomics. However, their lack of standardization restricts reproducibility and clinical translation of radiomics decision support tools. In this special report, teams of researchers who developed radiomics software participated in a three-phase study (September 2020 to December 2022) to establish a standardized set of filters. The first two phases focused on finding reference filtered images and reference feature values for commonly used convolutional filters: mean, Laplacian of Gaussian, Laws and Gabor kernels, separable and nonseparable wavelets (including decomposed forms), and Riesz transformations. In the first phase, 15 teams used digital phantoms to establish 33 reference filtered images of 36 filter configurations. In phase 2, 11 teams used a chest CT image to derive reference values for 323 of 396 features computed from filtered images using 22 filter and image processing configurations. Reference filtered images and feature values for Riesz transformations were not established. Reproducibility of standardized convolutional filters was validated on a public data set of multimodal imaging (CT, fluorodeoxyglucose PET, and T1-weighted MRI) in 51 patients with soft-tissue sarcoma. At validation, reproducibility of 486 features computed from filtered images using nine configurations × three imaging modalities was assessed using the lower bounds of 95% CIs of intraclass correlation coefficients. Out of 486 features, 458 were found to be reproducible across nine teams with lower bounds of 95% CIs of intraclass correlation coefficients greater than 0.75. In conclusion, eight filter types were standardized with reference filtered images and reference feature values for verifying and calibrating radiomics software packages. A web-based tool is available for compliance checking.

Evaluation of the Value of the Y-Balance Test to Predict Lower Limb Injuries in Professional Male Footballers.

CONTEXT: The aim of this prospective cohort study was to identify whether Y-Balance Test (YBT) performance and asymmetry are associated with lower limb injury in elite adult football athletes. DESIGN: A prospective cohort study. METHODS: Preseason YBT measures were obtained from 121 male footballers participating in National League One across the 2021-2022 season. Lower limb injuries were tracked across the season to determine the relationship between YBT variables and injury incidence using logistic regression analysis. The statistical significance level was .05. RESULTS: The average YBT score was 111.0 (5.8) cm on the left limb and 112.0 (5.5) cm on the right limb, with an average asymmetry of 2.3 (1.4) cm. Athletes with lower YBT scores on both the left (odds ratio = 2.9; 95% confidence interval, 1.7 to 4.8: P ≤ .001) and right (odds ratio = 2.3; 95% confidence interval, 1.6 to 3.2: P ≤ .001) limbs were at a greater risk of injury. Similarly, athletes with greater amounts of asymmetry were also more likely to get injured (odds ratio = 2.1; 95% confidence interval, 1.3 to 3.3: P = .002). CONCLUSIONS: Results indicate that lower and asymmetrical YBT scores have a significant relationship with future lower limb injuries in professional male footballers. The YBT offers a simple, reliable, and effective screening tool that can be used by practitioners in football to help identify players at a greater risk of injury before the season commences.

Effect of leg dominance on ipsilateral and contralateral limb training adaptation in middle-aged women after unilateral sensorimotor and resistance exercise training.

The aim was to examine the directionality of global training effects in middle-aged women after unilateral training.Thirty-nine middle-aged female volunteers (59.4 ± 5.4 years) were randomly assigned to one of three groups: 1. Unilateral Dominant Lower Limb Training (UDLT); 2. Unilateral Non-Dominant Lower Limb Training (UNDLT) or 3. Control group. Outcome measures assessing isometric strength, static and dynamic balance were recorded at baseline, and 1 week after 12 weeks (post-test) of training or no-intervention.The net cross education adaptation changes of the contralateral quadriceps isometric maximum voluntary (MVC) force (F2,34 = 4.33; p = 0.022), Stork balance score (F2,34 = 4.26; p = 0.023) and the Star Excursion Balance test score (F2,34 = 11.80; p = 0.001) were asymmetrical in the UNDLT group and on average, exceeded the UDLT group.The results demonstrated asymmetrical cross education training adaptations with unilateral training of non-dominant leg (UNDLT) to contralateral homologous and heterologous muscles, with the exception of knee flexor MVC. The results of this study provide a novel exercise or rehabilitation strategy that can be employed when one of the limbs is affected.

Does ipsilateral and bilateral knee strength status predict lower extremity injuries of elite judokas; a prospective cohort study.

The association of pre-participation knee muscle strength status with lower limb injury occurrence was investigated. Knee extensors and flexors muscle strength status including the traditional hamstrings/quadriceps (H/Q), Q/Q, H/H, and the non-dominant H/Q: dominant H/Q, HQ:HQ, ratios were recorded before the 10 month judo activity. Fifteen lower limb sport injuries were recorded for 53 judokas during the follow-up questionnaires. Significant accuracy of dominant H/Q ratio 60º/s (AUC 0.702, 95% CI 0.520 to .883, p = 0.023), as well as HQ:HQ ratios 300º/s (AUC .318, 95% CI 0.138 to 0.497, p = 0.040), and 60 º/s (AUC 0.311, 95% CI 0.130 to 0.491, p = .033) were revealed discriminating between injured and uninjured judokas. The optimum cut-off of dominant H/Q ratio associated with belonging to uninjured judokas group was 43.2% (sensitivity, 0.974; specificity, 0.533). Isokinetic knee muscle dynamometry is useful for predicting the likelihood of lower limb injuries in professional judokas during competitive activity.

Pre-participation testing of ipsilateral and bilateral knee extensors and flexors strength ratios can contribute to an injury prevention program for judokas.Ipsilateral and bilateral strength ratios should be monitored at lower and higher angular isokinetic velocities.

Parasympathetic reactivation in children: influence of two various modes of exercise.

PURPOSE: This study examined the effect of various modes of exercise on parasympathetic reactivation in children. METHODS: Twelve healthy boys volunteered for this study. Time domain measurement of heart rate variability in 5 and 10 min and heart rate recovery (HRR) in 1 (HRR1) and 2 min (HRR2) were measured during recovery after incremental exercise tests by a 12-lead ECG. Incremental exercise tests were performed using either upper (arm cranking) or lower body (cycling) ergometers. RESULTS: The amounts of increase in RMSSD and PNN50 in 5 and 10 min of recovery were higher in arm cranking compared to cycling. HRR1 and HRR2 were significantly higher after arm cranking compared to cycling. CONCLUSIONS: These results suggest that parasympathetic reactivation is likely greater following exercises that use smaller muscle mass (arm cranking) rather than larger muscle mass (cycling) in healthy boys.

Ipsilateral resistance exercise prevents exercise-induced central sensitization in the contralateral limb: a randomized controlled trial.

PURPOSE: This study aimed to investigate the hypothesis that a repeated bout of eccentric exercise (ECC2) would result in smaller increase in the sensitivity of spinal nociceptive system, and smaller decrease in the local muscle blood oxygenation response in both the ipsilateral and the contralateral tibialis anterior muscle (TA) when compared with the initial bout (ECC1). It was hypothesized that the magnitude of the repeated bout effect (RBE) would be greater for the ipsilateral side than the contralateral side. METHODS: Twenty-six healthy young men performed two bouts of high-intensity eccentric exercise of TA separated by 2 weeks. Half of the participants used the same leg for both bouts (IPSI) and the other half used the contralateral leg for ECC2 (CONTRA). Nociceptive withdrawal reflex threshold (NWRT) and local muscle blood oxygenation were assessed for the exercised TA muscle before, immediately after, and one day after exercise. RESULTS: Significant decreases in NWRT and muscle oxygenation were observed after ECC1 (p < 0.05), but NWRT did not change after ECC2 in both groups. Smaller decreases in muscle oxygenation were observed after ECC2 than ECC1 in both groups with a similar magnitude of the difference between bouts, but an increase in muscle oxygen re-perfusion before ECC2 was only observed in the IPSI group. CONCLUSION: These results suggest that contralateral RBE was associated with spinal facilitation of the neuronal pathways situated at a homologous innervation level, and it is unlikely that oxygen re-perfusion improvement plays a major role in the contralateral RBE.

Adaptation of local muscle blood flow and surface electromyography to repeated bouts of eccentric exercise.

The aim of this randomized controlled crossover study was to investigate the effect of a bout of unaccustomed eccentric exercise (ECC) followed by a consecutive bout of the same intensity on local muscle blood flow, amplitude, and frequency of the electromyographic (EMG) signal from the exercised tibialis anterior muscle. Sixteen healthy male participants (age, 25.7 (0.6) years; body mass index 24.8 (1) kg·m(-2) participated in this study. Two identical bouts of high-intensity ECC were performed on the tibialis anterior muscle 7 days apart. Control sessions involving no exercise were performed 4 weeks either before or after the exercise sessions. Changes in local total blood flow [ΔtHb], EMG root mean square, and median power frequency were recorded during isometric maximum voluntary contraction of ankle dorsiflexion. Measurements were performed before, immediately after, and the day after both ECCs (ECC1 and ECC2). The participants rested quietly in a chair in the control session. Eccentric exercise 1 led to a significant decrease in [ΔtHb] on the day after (p ≤ 0.05), whereas ECC2 did not. Median power frequency decreased significantly in ECC2 compared with ECC1 (p < 0.01). Root mean square was unchanged in all the instants. The present study showed that adaptation is depicted in the local muscle blood flow and the frequency contents of the EMG after an unaccustomed ECC inducing muscle soreness. These alterations provide a potential mechanism for a rapid adaptation, which decreases susceptibility of the muscle to develop further soreness in the subsequent ECC bout.

Evaluation of the lower extremity functional test to predict lower limb injuries in professional male footballers.

The Lower Extremity Functional Test (LEFT) is a reliable and valid test for the measurement of athletic fitness, fatigue resistance, and speed performance. Contradictory results exist regarding the screening value of the LEFT in predicting lower limb injuries. The purpose of this study was to investigate the screening value of the LEFT in predicting lower limb injuries in professional male footballers. One hundred and twenty-one professional male football players participated in the study. LEFT was recorded pre-season and the lower-limb injuries were recorded during a 9-month season. Logistic regression analysis was used to determine the accuracy of the prognosis of LEFT. A total of twenty-five lower limb injuries were recorded. The model explained 53% of the variance in lower limb injury, showing that predictions by LEFT score is reliable, and correctly predicted 89.3% of cases, which is a large improvement. ROC analysis showed significant accuracy of the LEFT score (AUC 0.908, 95% CI 1.126-1.336, p = 0.001, OR = 1.227) in discriminating between injured and uninjured players. The optimum cut-off level of the LEFT score was 90.21 s; Our findings showed that the LEFT score was able to predict lower limb injuries in professional male footballers. The slower an athlete's LEFT scores, the more susceptible they are to future injury risk. Sports medicine specialists, football coaches and managers are suggested to use LEFT as a pre-season screening test to identify and prevent the weakness and functional imbalance of the athletes before the injury occurs by conducting this test.

Pain sensitivity is normalized after a repeated bout of eccentric exercise.

PURPOSE: The purpose of this study was to investigate the effect of repeated bouts of eccentric exercise on the nociceptive withdrawal reflex (NWR) threshold, a measure of sensitivity in the spinal nociceptive system. METHODS: Sixteen healthy students (age 25.7 ± 0.6 years, BMI 24.8 ± 1 kg m(-2)) participated in this randomized, controlled, crossover study. Two identical bouts of high-intensity eccentric exercises were performed on the tibialis anterior muscle 7 days apart. Control sessions involving no exercise were performed 4 weeks apart the exercise sessions. Pressure pain thresholds (PPT) and the NWR threshold were recorded before, immediately after, and 1 day after both bouts of exercise. RESULTS: Pressure pain thresholds decreased significantly at two of the muscle belly sites on the day after initial bout compared with baseline. NWR threshold decreased by 25 ± 4 % immediately after initial bout and by 30 ± 5 % the next day (p < 0.05) as an indication of generalized pain hypersensitivity. On the contrary, no changes were found in both pain thresholds after second bout of eccentric exercise indicating that both localized and generalized pain sensitivity were normalized. CONCLUSION: In conclusion, this study for the first time documented that an initial bout of unaccustomed high-intensity eccentric exercise, which results in muscle soreness can induce central sensitization. A repeated bout of exercise, however, facilitates inherent protective spinal mechanisms against the development of muscle soreness.

The effect of patient-led goal setting approach combined with pain neuroscience education or manual therapy in patients with chronic low back pain: protocol for a parallel-group randomized controlled trial.

BACKGROUND: Low back pain (LBP) is a multifactorial disorder associated with a high range of physical and psychological burden on the society. Patient-led goal-setting approach has shown potential effects for improving chronic LBP. However, there are few studies investigating its benefits when combined with a supplementary intervention. This paper, therefore, presents a protocol for a randomized control trial (RCT) to study the effect of a patient-led goal-setting approach combined with pain neuroscience education (PNE) or manual therapy (MT) among patients with chronic LBP. METHODS: A total of 105 patients suffering from chronic LBP will be recruited via flyers displayed in hospitals and universities, and those meeting the study's criteria will randomly be allocated into a patient-led goal-setting approach with the PNE group, and/or with the MT program group, and/or a control group. The primary outcomes will be the pain intensity and disability. Secondary outcomes include quality of life, depression, anxiety and stress, fear avoidance beliefs, kinesophobia, pain self-efficacy, catastrophic pain, neurophysiology of pain, and central sensitivity. All the outcomes will be recorded at 2 months after receiving the treatment as post-test sessions and after 4 and 12 months as follow-up sessions. The Ethics Committee in Research at Sport Sciences Research Institute of Iran approved the protocol of this trial (IR.SSRC.REC.1400.084). Written, informed consent to participate will be obtained from all participants. All methods will be conducted in accordance with the ethical standards of the Declaration of Helsinki and in accordance with relevant guidelines and regulations. We will disseminate the findings through peer-reviewed publications and conference presentations and send them to the participants. DISCUSSION: This trial will demonstrate which supplementary intervention can better improve the impact of a patient-led goal-setting approach to treat LBP. If successful, the results will potentially have implications for athletic trainers, physiotherapists, and health care practitioners. TRIAL REGISTRATION: IRCT Iranian Registry of Clinical Trials IRCT20210927052616N1. Registered on November 03, 2021.

Investigating the value of balance and proprioception scores to predict lower limb injuries in professional judokas.

We investigated the ability of balance and proprioception screening tests to predict lower limb injuries in professional male judokas. Fifty-three male judokas of the national teams (Mean ± SD, age 18.68 ± 3.08 years, weight 75.34 ± 11.62 kg, height 175.28 ± 7.24 cm) participated in this study. Limits of stability (LOS), single leg stability (SLS), and knee joint position sense (JPS) was recorded as the screening tests before starting the 10 month follow up. Lower limb injury was recorded all through the follow up. Fifteen lower limb sport injuries were recorded for 53 judokas during the follow-up recordings. Significant accuracy of SLS, overall bilateral ratio (AUC 0.646, 95% CI 0.452-0.839, p = 0.046), as well as JPS 60° bilateral ratio (AUC 0.657, 95% CI 0.480-0.834, p = 0.044), and LOS overall (AUC 0.696, 95% CI 0.551-0.840, p = 0.031) were revealed discriminating between injured and uninjured judokas. The optimum cut-off of SLS, overall bilateral ratio, JPS 60° bilateral ratio, and LOS overall associated with belonging to uninjured judokas group was ≤ 1.15%, ≤ 1.09%, and ≤ 1.09 respectively (sensitivity, 0.763, 0.711, 0.789 respectively; specificity, 0.600). Although the absolute unilateral balance and proprioception scores were almost the same between injured and non-injured judokas, the bilateral ratio of both these indices were different between the two groups. Lower limbs bilateral balance and proprioception asymmetries is a more important risk factor than the absolute unilateral balance and proprioception scores for sustaining lower limb injuries in professional male judokas. Medical professionals and coaches are suggested to use these findings as pre-participation screening tools identify injury-prone athletes.

Fusion-based tensor radiomics using reproducible features: Application to survival prediction in head and neck cancer.

BACKGROUND: Numerous features are commonly generated in radiomics applications as applied to medical imaging, and identification of robust radiomics features (RFs) can be an important step to derivation of reliable, reproducible solutions. In this work, we utilize a tensor radiomics (TR) framework, where numerous fusions are explored, to generate different flavours of RFs, and we aimed to identify RFs that are robust to fusion techniques in head and neck cancer. Overall, we aimed to predict progression-free survival (PFS) using Hybrid Machine Learning Systems (HMLS) and reproducible RFs. METHODS: The study was performed on 408 patients with head and neck cancer from The Cancer Imaging Archive. After image preprocessing, 15 fusion techniques were employed to combine Positron Emission Tomography (PET) and Computed Tomography (CT) images. Subsequently, 215 RFs were extracted through a standardized radiomics software, with 17 'flavours' generated using PET-only, CT-only, and 15 fused PET&CT images. The variability of RFs across flavours was studied using the Intraclass Correlation Coefficient (ICC). Furthermore, the features were categorized into seven reliability groups, 106 reproducible RFs with ICC>0.75 were selected, highly correlated flavours were removed, Principal Component Analysis was used to convert 17 flavours to 1 attribute, the polynomial function was utilized to increase RFs, and Analysis of variance (ANOVA) was used to select the relevant attributes. Finally, 3 classifiers including Random Forest (RFC), Logistic regression (LR), and Multi-layer perceptron were applied to the preselected relevant attributes to predict binary PFS. In 5-fold cross-validation, 80% of 4 divisions were utilized to train the model, and the remaining 20% was utilized to evaluate the model. Further, the remaining fold was used for external nested testing. RESULTS: Reliability analysis indicated that most morphological features belong to the high-reliability category. By contrast, local intensity and statistical features extracted from images belong to the low-reliability category. In the tensor framework, the highest 5-fold cross-validation accuracy of 76.7%±3.3% with an external nested testing of 70.6%±6.7% resulted from the reproducible TR+polynomial function+ANOVA+LR algorithm while the accuracy of 70.0%±4.2% with the external nested testing of 67.7%±4.9% was achieved through the PCA fusion+RFC (non-tensor paradigm). CONCLUSIONS: This study demonstrated that using reproducible RFs as utilized within a tensor fusion radiomics framework, linked with ANOVA and LR, added value to prediction of progression-free survival outcome in head and neck cancer patients.

Rehabilitative exercise scheduling: Effects on balance, functional movement performance, and pain perception in middle-aged women with knee pain: A randomized controlled trial.

BACKGROUND: The scheduling of clinical rehabilitative exercise should combine best possible delivery of exercise with the most efficient use of time, facilities, equipment, and personnel. However, it is not clear whether distribution of a fixed amount of exercise volume is more efficient over a longer time period in a week (distributed manner) than over a shorter time period in a week (massed manner). OBJECTIVE: To evaluate the effects of distributed versus massed within- and between-session exercise scheduling on balance, exercise performance, and pain perception in middle-aged women with knee pain. PARTICIPANTS: Thirty-four middle-aged female volunteers (mean age ± SD, 56.0 ± 5.2 years old; mean weight ± SD, 66.9 ± 7.6 kg; mean body mass index [BMI] ± SD, 27.7 ± 2.8 kg/m2 ) were randomly assigned to one of the three groups consisting of Rehabilitative Massed Scheduling (RMS); Rehabilitative Distributed Scheduling (RDS); or Control group (CG). MAIN OUTCOME MEASURES: Isometric strength, balance, functional movement performance, and pain perception were assessed at baseline (pre), at week 8 (mid), and 1 week after the full 12 weeks (post) of exercise training or no intervention (CG). RESULTS: Significant improvements in balance, functional movement performance, and pain perception were found after both RDS and RMS after 8 and 12 weeks compared to the control group (p Ë‚ .05). Examination of the net changes (% ∆) between RDS and RMS showed a statistically significant difference only in the right 30-second arm curl records of individuals in the RDS group, which were significantly higher than the RMS group at the post-test (p Ë‚ .05). CONCLUSION: Rehabilitative training providers are advised to distribute the drills of rehabilitative exercise training within and between the sessions of exercise per week only when a positive Bottom-Up Rise Strength Transfer effect (BURST) effect of exercise training is needed. Otherwise, if the whole amount of rehabilitative exercise work is identical the benefit of going five versus three times per week to the rehabilitation centers would be similar.

Deep versus Handcrafted Tensor Radiomics Features: Prediction of Survival in Head and Neck Cancer Using Machine Learning and Fusion Techniques.

BACKGROUND: Although handcrafted radiomics features (RF) are commonly extracted via radiomics software, employing deep features (DF) extracted from deep learning (DL) algorithms merits significant investigation. Moreover, a "tensor'' radiomics paradigm where various flavours of a given feature are generated and explored can provide added value. We aimed to employ conventional and tensor DFs, and compare their outcome prediction performance to conventional and tensor RFs. METHODS: 408 patients with head and neck cancer were selected from TCIA. PET images were first registered to CT, enhanced, normalized, and cropped. We employed 15 image-level fusion techniques (e.g., dual tree complex wavelet transform (DTCWT)) to combine PET and CT images. Subsequently, 215 RFs were extracted from each tumor in 17 images (or flavours) including CT only, PET only, and 15 fused PET-CT images through the standardized-SERA radiomics software. Furthermore, a 3 dimensional autoencoder was used to extract DFs. To predict the binary progression-free-survival-outcome, first, an end-to-end CNN algorithm was employed. Subsequently, we applied conventional and tensor DFs vs. RFs as extracted from each image to three sole classifiers, namely multilayer perceptron (MLP), random-forest, and logistic regression (LR), linked with dimension reduction algorithms. RESULTS: DTCWT fusion linked with CNN resulted in accuracies of 75.6 ± 7.0% and 63.4 ± 6.7% in five-fold cross-validation and external-nested-testing, respectively. For the tensor RF-framework, polynomial transform algorithms + analysis of variance feature selector (ANOVA) + LR enabled 76.67 ± 3.3% and 70.6 ± 6.7% in the mentioned tests. For the tensor DF framework, PCA + ANOVA + MLP arrived at 87.0 ± 3.5% and 85.3 ± 5.2% in both tests. CONCLUSIONS: This study showed that tensor DF combined with proper machine learning approaches enhanced survival prediction performance compared to conventional DF, tensor and conventional RF, and end-to-end CNN frameworks.

Comparing kinematic asymmetry and lateral step-down test scores in healthy, chronic ankle instability, and patellofemoral pain syndrome female basketball players: a cross-sectional study.

We aimed to understand whether ankle dorsiflexion range of motion (ROM) and dynamic knee valgus (DKV) kinematic inter-limb asymmetries would be associated with the Lateral Step-Down Test (LSD) in basketball players with chronic ankle instability (CAI), patellofemoral pain (PFP) and healthy controls (HC). An observational cross-sectional study with a between-subject design was employed. Female basketball athletes with CAI (n = 20), PFP (n = 20) and HC (n = 20) were recruited. Ankle dorsiflexion-ROM, DKV angle during a single-limb squat, and LSD quality were measured bilaterally. The Asymmetry index (ASI) was calculated to identify between-limb percentage imbalances. The correlation matrix between the tasks was calculated. Ankle dorsiflexion-ROM was less in the CAI and PFP than in the HC group regardless of limb (p < 0.001). DKV angle was greater in the CAI and PFP than in the HC group bilaterally (p < 0.001). LSDs were similar between the PFP and CAI groups (p = 0.698) but worse than the HC group (p = 0.001). The ASI showed asymmetry across all tasks (p < 0.001), with the greatest asymmetry for the DKV angle. The correlation matrix between tasks on both limbs was significant (p < 0.05). Our findings suggest significant asymmetries in ankle dorsiflexion-ROM and frontal plane knee control are present in female basketball athletes with CAI and PFP, and thus, highlights need to evaluate and reduce limb asymmetries in these populations.

Application of novel hybrid machine learning systems and radiomics features for non-motor outcome prediction in Parkinson's disease.

Objectives.Parkinson's disease (PD) is a complex neurodegenerative disorder, affecting 2%-3% of the elderly population. Montreal Cognitive Assessment (MoCA), a rapid nonmotor screening test, assesses different cognitive dysfunctionality aspects. Early MoCA prediction may facilitate better temporal therapy and disease control. Radiomics features (RF), in addition to clinical features (CF), are indicated to increase clinical diagnoses, etc, bridging between medical imaging procedures and personalized medicine. We investigate the effect of RFs, CFs, and conventional imaging features (CIF) to enhance prediction performance using hybrid machine learning systems (HMLS).Methods.We selected 210 patients with 981 features (CFs, CIFs, and RFs) from the Parkinson's Progression-Markers-Initiative database. We generated 4 datasets, namely using (i), (ii) year-0 (D1) or year-1 (D2) features, (iii) longitudinal data (D3, putting datasets in years 0 and 1 longitudinally next to each other), and (iv) timeless data (D4, effectively doubling dataset size by listing both datasets from years 0 and 1 separately). First, we directly applied 23 predictor algorithms (PA) to the datasets to predict year-4 MoCA, which PD patients this year have a higher dementia risk. Subsequently, HMLSs, including 14 attribute extraction and 10 feature selection algorithms followed by PAs were employed to enhance prediction performances. 80% of all datapoints were utilized to select the best model based on minimum mean absolute error (MAE) resulting from 5-fold cross-validation. Subsequently, the remaining 20% was used for hold-out testing of the selected models.Results.When applying PAs without ASAs/FEAs to datasets (MoCA outcome range: [11,30]), Adaboost achieved an MAE of 1.74 ± 0.29 on D4 with a hold-out testing performance of 1.71. When employing HMLSs, D4 + Minimum_Redundancy_Maximum_Relevance (MRMR)+K_Nearest_Neighbor Regressor achieved the highest performance of 1.05 ± 0.25 with a hold-out testing performance of 0.57.Conclusion.Our study shows the importance of using larger datasets (timeless), and utilizing optimized HMLSs, for significantly improved prediction of MoCA in PD patients.

Prediction of Cognitive Decline in Parkinson's Disease Using Clinical and DAT SPECT Imaging Features, and Hybrid Machine Learning Systems.

BACKGROUND: We aimed to predict Montreal Cognitive Assessment (MoCA) scores in Parkinson's disease patients at year 4 using handcrafted radiomics (RF), deep (DF), and clinical (CF) features at year 0 (baseline) applied to hybrid machine learning systems (HMLSs). METHODS: 297 patients were selected from the Parkinson's Progressive Marker Initiative (PPMI) database. The standardized SERA radiomics software and a 3D encoder were employed to extract RFs and DFs from single-photon emission computed tomography (DAT-SPECT) images, respectively. The patients with MoCA scores over 26 were indicated as normal; otherwise, scores under 26 were indicated as abnormal. Moreover, we applied different combinations of feature sets to HMLSs, including the Analysis of Variance (ANOVA) feature selection, which was linked with eight classifiers, including Multi-Layer Perceptron (MLP), K-Neighbors Classifier (KNN), Extra Trees Classifier (ETC), and others. We employed 80% of the patients to select the best model in a 5-fold cross-validation process, and the remaining 20% were employed for hold-out testing. RESULTS: For the sole usage of RFs and DFs, ANOVA and MLP resulted in averaged accuracies of 59 ± 3% and 65 ± 4% for 5-fold cross-validation, respectively, with hold-out testing accuracies of 59 ± 1% and 56 ± 2%, respectively. For sole CFs, a higher performance of 77 ± 8% for 5-fold cross-validation and a hold-out testing performance of 82 + 2% were obtained from ANOVA and ETC. RF+DF obtained a performance of 64 ± 7%, with a hold-out testing performance of 59 ± 2% through ANOVA and XGBC. Usage of CF+RF, CF+DF, and RF+DF+CF enabled the highest averaged accuracies of 78 ± 7%, 78 ± 9%, and 76 ± 8% for 5-fold cross-validation, and hold-out testing accuracies of 81 ± 2%, 82 ± 2%, and 83 ± 4%, respectively. CONCLUSIONS: We demonstrated that CFs vitally contribute to predictive performance, and combining them with appropriate imaging features and HMLSs can result in the best prediction performance.

Prediction of Parkinson's disease pathogenic variants using hybrid Machine learning systems and radiomic features.

PURPOSE: In Parkinson's disease (PD), 5-10% of cases are of genetic origin with mutations identified in several genes such as leucine-rich repeat kinase 2 (LRRK2) and glucocerebrosidase (GBA). We aim to predict these two gene mutations using hybrid machine learning systems (HMLS), via imaging and non-imaging data, with the long-term goal to predict conversion to active disease. METHODS: We studied 264 and 129 patients with known LRRK2 and GBA mutations status from PPMI database. Each dataset includes 513 features such as clinical features (CFs), conventional imaging features (CIFs) and radiomic features (RFs) extracted from DAT-SPECT images. Features, normalized by Z-score, were univariately analyzed for statistical significance by the t-test and chi-square test, adjusted by Benjamini-Hochberg correction. Multiple HMLSs, including 11 features extraction (FEA) or 10 features selection algorithms (FSA) linked with 21 classifiers were utilized. We also employed Ensemble Voting (EV) to classify the genes. RESULTS: For prediction of LRRK2 mutation status, a number of HMLSs resulted in accuracies of 0.98 ± 0.02 and 1.00 in 5-fold cross-validation (80% out of total data points) and external testing (remaining 20%), respectively. For predicting GBA mutation status, multiple HMLSs resulted in high accuracies of 0.90 ± 0.08 and 0.96 in 5-fold cross-validation and external testing, respectively. We additionally showed that SPECT-based RFs added value to the specific prediction of of GBA mutation status. CONCLUSION: We demonstrated that combining medical information with SPECT-based imaging features, and optimal utilization of HMLS can produce excellent prediction of the mutations status in PD patients.

Composite functional movement screen score predicts injuries in youth volleyball players: a prospective cohort study.

We aimed to investigate whether composite Functional Movement Screen (FMS) test scores can predict musculoskeletal injuries (MSI) in youth volleyball players. 131 national young volleyball players (Males: n = 100, age = 16.5 years, height = 1.787 m, mass = 68.32 kg; Females: n = 31, age = 13.83 years, height = 1.684 m, mass = 65.12 kg) participated in this prospective cohort study. The FMS screen was performed before starting the season. MSI and exposure data were collected during the season via each team's certified athletic trainer. The mean FMS score and standard deviation for all volleyball players was 15.85 ± 3.31. A score of ≤ 14 was positive to predict MSI with specificity of 0.60 and sensitivity of 0.93. The odds ratio for (≤ 14/˃14) was 0.048. The relative risk for being injured was 3.46. Positive likelihood ratio was 2.34, and negative likelihood ratio was 0.11. The findings of this study demonstrated that an FMS score of ≤ 14 is an identifiable risk factor for injury in young volleyball players. The FMS can be used as a pre-season screening test to identify volleyball players who may be predisposed to sustaining MSI during the season ahead.

Exercise training and antioxidants: effects on rat heart tissue exposed to lead acetate.

We have investigated the cardioprotective effects of exercise training and/or curcumin on lead acetate-induced myocardial damage. Forty rats were randomly divided into 5 groups: (1) lead acetate, (2) curcumin, (3) endurance training, (4) training + curcumin, (5) sham groups. The rats in groups 3 and 4 experienced the treadmill running of 15 to 22 m/min for 25 to 64 minutes, 5 times a week for 8 weeks. Groups 1 to 4 received lead acetate (20 mg/kg), the sham group received curcumin solvent (ethyl oleat), and the curcumin and training + curcumin groups received curcumin solution (30 mg/kg) intraperitoneally. Lead administration resulted in significant increases in high-sensitivity C-reactive protein (hs-CRP), creatine kinase-MB (CK-MB), malondialdehyde (MDA), and low-density lipoprotein (LDL), and significantly decreased glutathione peroxidase (GPx), Total Antioxidant Capacity (TAC), and high-density lipoprotein (HDL) levels. Treadmill running and\or curcumin supplementation resulted in a significant decrease in hs-CRP, CK-MB, MDA, and LDL levels and significantly increased GPx, TAC, and HDL levels. These results suggest a lifestyle-induced cardioprotective potential in ameliorating lead-induced cardiotoxicity.