Category: Statistics

Comput Biol Chem. 2021 Oct 16;95:107593. doi: 10.1016/j.compbiolchem.2021.107593. Online ahead of print.

ABSTRACT

With the growth of high throughput sequencing techniques, the generation of protein sequences has become fast and cheap, leading to a huge increase in the number of known proteins. However, it is challenging to identify the functions being performed by these newly discovered proteins. Machine learning techniques have improved traditional methods’ efficiency by suggesting relevant functions but fails to perform well when the number of functions to be predicted becomes large. In this work, we propose a machine learning-based approach to predict huge set of protein functions that use the inter-relationships between functions to improve the model’s predictability. These inter-relationships of functions is used to reduce the redundancy caused by highly correlated functions. The proposed model is trained on the reduced set of non-redundant functions hindering the ambiguity caused due to inter-related functions. Here, we use two statistical approaches 1) Pearson’s correlation coefficient 2) Jaccard similarity coefficient, as a measure of correlation to remove redundant functions. To have a fair evaluation of the proposed model, we recreate our original function set by inverse transforming the reduced set using the two proposed approaches: Direct mapping and Ensemble approach. The model is tested using different feature sets and function sets of biological processes and molecular functions to get promising results on DeepGO and CAFA3 dataset. The proposed model is able to predict specific functions for the test data which were unpredictable by other compared methods. The experimental models, code and other relevant data are available at https://github.com/richadhanuka/PFP-using-Functional-interrelationship.

PMID:34736126 | DOI:10.1016/j.compbiolchem.2021.107593

J Neurol Sci. 2021 Oct 28;431:120045. doi: 10.1016/j.jns.2021.120045. Online ahead of print.

ABSTRACT

The majority of neurological disorders exist in low- and middle-income countries, but these nations have the fewest neurologists and neurological training opportunities worldwide. The objective of this study was to assess the effectiveness, relevance, and feasibility of a five-day neurocritical care course delivered online to African healthcare workers and to understand participants’ prior neurological and neurocritical care training experiences. We offered the Neurocritical Care Society’s Emergency Neurological Life Support (ENLS) course covering 14 neurocritical conditions via Zoom to 403 African healthcare workers over a 4-day period. An additional day was devoted to management of neurological emergencies in resource-limited settings. Participants completed pre- and post-course surveys to assess the effectiveness, relevance, and feasibility of the overall course to their settings. 318 participants (46% female; 56% residents; 24% neurologists; 9.0 ± 6.7 years practicing medicine) from 11 African countries completed the pre-course self-assessment, and 232 completed the post-course self-assessment. 97% reported prior experience caring for patients with neurological emergencies but only 35% reported prior neurology training and 9% prior neurocritical care training. Pre-course and post-course comfort levels showed statistically significant improvements (p < 0.001) across all fourteen neurocritical topics. 95% of participants found the course relevant to their current practice setting, 94% agreed the Zoom online platform was easy to use, and 93% reported it facilitated their learning. Suggestions for course improvement included addition of non-critical neurological conditions and inclusion of locally available diagnostics and treatment modalities. Study results suggest virtual platforms may offer a way to improve neurology training in areas with reduced neurological workforce.

PMID:34736123 | DOI:10.1016/j.jns.2021.120045

Appl Radiat Isot. 2021 Oct 29;179:109949. doi: 10.1016/j.apradiso.2021.109949. Online ahead of print.

ABSTRACT

Considering the difficulties of the low signal-to-noise ratio in weak radioactive source detections, this study proposes an abandon Gaussian tails method based on the analysis of the characteristic information denoted by the full-energy peak of the gamma spectrum of a gamma-emitting radioactive source. Based on the study of the signal-to-background ratio and the statistical fluctuations in the signal of the weak radioactive source, a factor ζ, incorporating the statistical fluctuations of signal and background and the signal-to-background ratio, is suggested to characterize the sensitivity of a radioactive source detection. When ζ reaches its maximum value, the optimal counting window around the centroid of the full-energy peak can be obtained. To evaluate the effectiveness of the proposed approach, comparisons between the proposed abandon Gaussian tails, the conventional full-energy counting, and other experiential methods were performed. The results show that the sensitivity can be significantly improved. Further, experiments with different intensity of radiation sources and duplicated experiments were conducted to examine the stability of the proposed method.

PMID:34736109 | DOI:10.1016/j.apradiso.2021.109949

J Biomech. 2021 Oct 17;129:110818. doi: 10.1016/j.jbiomech.2021.110818. Online ahead of print.

ABSTRACT

In this study, using vertical ground reaction force (VGRF) data and focusing on the stance phase of the gait cycle, the effect of Parkinson’s disease (PD) on gait was investigated. The used dataset consisted of 93 PD and 72 healthy individuals. Multiple comparisons correction ANOVA test and student t-test were used for statistical analyses. Results showed that a longer stance duration with a larger VGRF peak value (p < 0.05) was observed for PD patients during the stance phase. In addition, the VGRF peak value was delayed and blunted in PD cases compared with healthy individuals. These results indicated more time and effort for PD patients for posture stabilization during the stance phase. The time delay for different locations of the foot sole to contact the ground during the stance phase indicated that PD patients might use a different strategy for maintaining their body stability compared with healthy individuals. Although the VGRF time-domain pattern during the stance phase in PD was similar to healthy conditions, its local characteristics like duration and peak value differed significantly. The classification analysis based on the VGRF time-domain extracted features during the stance phase obtained PD recognition with accuracy, sensitivity and specificity of 90.82%, 88.63% and 82.56%, respectively.

PMID:34736084 | DOI:10.1016/j.jbiomech.2021.110818

J Biomech. 2021 Oct 23;129:110810. doi: 10.1016/j.jbiomech.2021.110810. Online ahead of print.

ABSTRACT

The symmetrical center of rotation estimation (SCoRE) is probably one of the most used functional method for estimating the hip join center (HJC). However, it requires of complex multi-plane movements to find accurate estimations of HJC. Thus, using SCoRE for people with limited hip range of motion will lead to poor HJC estimation. In this work, we propose an anisotropic regularized version of the SCoRE formulation (RSCoRE), which is able to estimate the HJC location by using only standard gait trials, avoiding the need of recording complex multi-plane movements. RSCoRE is evaluated in both accuracy and repeatability of the estimation as compared to functional and predictive methods on a self-recorded cohort of fifteen young healthy adults with no hip joint pathologies or other disorders that could affect their gait. Given that, no medical images were available for this study, to quantify the global error of HJC the SCoRE residual was used. RSCoRE presents a global error of about 12 mm, similarly to the best performance of SCoRE. The comparison of the coordinate’s errors at each coordinate indicates that HJC estimations from SCoRE with complex multi-plane movements and RSCoRE are not statistical significantly different. Finally, we show that the repeatability of RSCoRE is similar to the rest of the tested methods, yielding to repeatability values between 0.72 and 0.79. In conclusion, not only the RSCoRE yields similar estimation performance than SCoRE, but it also avoids the need of complex multi-plane movements to be performed by the subject of analysis. For this reason, RSCoRE has the potential to be a valuable approach for estimating the HJC location in people with limited hip ROM.

PMID:34736083 | DOI:10.1016/j.jbiomech.2021.110810

J Healthc Qual. 2021 Nov-Dec 01;43(6):365-373. doi: 10.1097/JHQ.0000000000000291.

ABSTRACT

BACKGROUND: Effective communication among healthcare teams is essential for ensuring handoff-related safety and quality care outcomes.

PURPOSE: The aim of this project was to improve patient safety through the reduction of communication-related errors on an acute hemodialysis unit (AHU) in an academic medical center. A target was set to reduce by 50 percent the communication-related errors using strategies to improve teamwork and communication.

METHODS: Acute hemodialysis unit team members attended Clinical Team Training (CTT) informational sessions on teamwork and communication. A structured handoff tool was implemented in the AHU to improve nurse communication and reduce communication-related patient safety events. Descriptive statistics and comparison of means were conducted to assess the differences between preimplementation and postimplementation audit and safety event data.

RESULTS: There was a statistically significant difference between the preintervention and postintervention groups of handoff tool usage and completion as well as a consistent decrease in handoff-related safety events after implementation.

CONCLUSIONS/IMPLICATIONS: Findings suggest that CTT and a structured handoff tool used to guide nurse-to-nurse care transitions lead to a reduction in communication-related safety events during handoffs in an AHU.

PMID:34734920 | DOI:10.1097/JHQ.0000000000000291

Stud Health Technol Inform. 2021 Oct 27;285:100-105. doi: 10.3233/SHTI210580.

ABSTRACT

The relevance of this study lies in improvement of machine learning models understanding. We present a method for interpreting clustering results and apply it to the case of clinical pathways modeling. This method is based on statistical inference and allows to get the description of the clusters, determining the influence of a particular feature on the difference between them. Based on the proposed approach, it is possible to determine the characteristic features for each cluster. Finally, we compare the method with the Bayesian inference explanation and with the interpretation of medical experts [1].

PMID:34734858 | DOI:10.3233/SHTI210580

Neurologist. 2021 Nov 4;26(6):271-273. doi: 10.1097/NRL.0000000000000355.

ABSTRACT

INTRODUCTION: Wake-up strokes are challenging to manage due to unknown time of onset. Recently, the wake-up trial demonstrated that recombinant tissue plasminogen activator (rtPA) could be administered based on the magnetic resonance imaging (MRI)- diffusion weighted imaging/fluid attenuated inversion recovery mismatch. Many still doubt the safety results due to the higher rate of hemorrhagic conversion reported. Although it was statistically insignificant, the study was terminated early. Furthermore, Corona virus disease-19 is associated with coagulopathy and a higher risk of hemorrhagic conversion.

CASE REPORT: A 46-year-old fully functioning male presented with a wake-up right hemiparesis, right facial droop, and expressive aphasia. His National Institute of Health Stroke Scale was 4 upon arrival. Last known well state was >4.5 hours. He tested positive for SARS-CoV-2 viral infection. He had left distal-M2 occlusion. He was deemed not a candidate for rtPA. Hyperacute-MRI protocol showed diffusion weighted imaging/fluid attenuated inversion recovery mismatch. The patient received rtPA at 6.5 hours from the last knwn well state. Follow-up MRI-susceptibility weighted imaging revealed fragmented clot. The stroke burden was less than that shown on the initial computed tomography-perfusion scans implying saved penumbra. There was no hemorrhagic conversion despite low fibrinogen levels.

CONCLUSION: The hyperacute-MRI protocol for wake-up COVID-19 associated strokes might be a safe option.

PMID:34734906 | DOI:10.1097/NRL.0000000000000355

Anatol J Cardiol. 2021 Nov;25(11):803-810. doi: 10.5152/AnatolJCardiol.2021.13611.

ABSTRACT

OBJECTIVE: In this study, we aimed to investigate the prognostic accuracy of the presence of fragmented QRS (fQRS) on baseline electrocardiogram on the adverse outcome in critical patients with coronavirus disease 2019 (COVID-19) with cardiovascular disease (CVD).

METHODS: The current study was retrospective designed and included 169 patients who were critically ill with COVID-19 and CVD (mean age of 62±15 years). The patients were grouped into those who died (non-survivor group) and those who survived (survivor group).

RESULTS: The non-survivors were older and more often had CVD (p=0.009), hypertension (p=0.046), diabetes (p=0.048), cancer (p=0.023), and chronic renal failure (p=0.001). Although the presence of fQRS on the basal electrocardiogram was more common in patients who died, this was not statistically significant (p=0.059). Furthermore, non-survivors had more frequent the coexistence of CVD and fQRS (p=0.029). In Model 1 multivariate regression analysis, CVD alone was not a predictor of mortality (p=0.078), whereas coexistence of CVD and fQRS was found to be an independent predictor of mortality in Model 2 analysis [hazard ratio (HR): 2.243; p=0.003]. Furthermore, older age (HR: 1.022; p=0.006 and HR: 1.023; p=0.005), cancer (HR: 1.912; p=0.021 and HR: 1.858; p=0.031), high SOFA score (HR: 1.177; p=0.003 and HR: 1.215; p<0.001), and increased CRP level (HR: 1.003; p=0.039 and HR: 1.003; p=0.027) independently predicted the mortality in both multivariate analysis models, respectively.

CONCLUSION: fQRS may be a useful and handy risk-stratification tool for clinical outcomes by identifying high-risk individuals, especially among those with CVD.

PMID:34734814 | DOI:10.5152/AnatolJCardiol.2021.13611

J Med Internet Res. 2021 Nov 4;23(11):e27282. doi: 10.2196/27282.

ABSTRACT

BACKGROUND: Behavioral habits are often initiated by contextual cues that occur at approximately the same time each day; so, it may be possible to identify a reflexive habit based on the temporal similarity of repeated daily behavior. Mobile health tools provide the detailed, longitudinal data necessary for constructing such an indicator of reflexive habits, which can improve our understanding of habit formation and help design more effective mobile health interventions for promoting healthier habits.

OBJECTIVE: This study aims to use behavioral data from a commercial mindfulness meditation mobile phone app to construct an indicator of reflexive meditation habits based on temporal similarity and estimate the association between temporal similarity and meditation app users’ perceived health benefits.

METHODS: App-use data from June 2019 to June 2020 were analyzed for 2771 paying subscribers of a meditation mobile phone app, of whom 86.06% (2359/2771) were female, 72.61% (2012/2771) were college educated, 86.29% (2391/2771) were White, and 60.71% (1664/2771) were employed full-time. Participants volunteered to complete a survey assessing their perceived changes in physical and mental health from using the app. Receiver operating characteristic curve analysis was used to evaluate the ability of the temporal similarity measure to predict future behavior, and variable importance statistics from random forest models were used to corroborate these findings. Logistic regression was used to estimate the association between temporal similarity and self-reported physical and mental health benefits.

RESULTS: The temporal similarity of users’ daily app use before completing the survey, as measured by the dynamic time warping (DTW) distance between app use on consecutive days, significantly predicted app use at 28 days and at 6 months after the survey, even after controlling for users’ demographic and socioeconomic characteristics, total app sessions, duration of app use, and number of days with any app use. In addition, the temporal similarity measure significantly increased in the area under the receiver operating characteristic curve (AUC) for models predicting any future app use in 28 days (AUC=0.868 with DTW and 0.850 without DTW; P<.001) and for models predicting any app use in 6 months (AUC=0.821 with DTW and 0.802 without DTW; P<.001). Finally, a 1% increase in the temporal similarity of users’ daily meditation practice with the app over 6 weeks before the survey was associated with increased odds of reporting mental health improvements, with an odds ratio of 2.94 (95% CI 1.832-6.369).

CONCLUSIONS: The temporal similarity of the meditation app use was a significant predictor of future behavior, which suggests that this measure can identify reflexive meditation habits. In addition, temporal similarity was associated with greater perceived mental health benefits, which demonstrates that additional mental health benefits may be derived from forming reflexive meditation habits.

PMID:34734826 | DOI:10.2196/27282