scholarly journals Utilization of machine learning for identifying symptom severity military-related PTSD subtypes and their biological correlates

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Carole E. Siegel ◽  
Eugene M. Laska ◽  
Ziqiang Lin ◽  
Mu Xu ◽  
Duna Abu-Amara ◽  
...  
Keyword(s):  
Machine Learning ◽  
Symptom Severity ◽  
Principal Component ◽  
Micro Rna ◽  
Self Report ◽  
Discovery Sample ◽  
Partitioning Around Medoids ◽  
Military Trauma ◽  
Severity Scores ◽  
Intergroup Comparison

AbstractWe sought to find clinical subtypes of posttraumatic stress disorder (PTSD) in veterans 6–10 years post-trauma exposure based on current symptom assessments and to examine whether blood biomarkers could differentiate them. Samples were males deployed to Iraq and Afghanistan studied by the PTSD Systems Biology Consortium: a discovery sample of 74 PTSD cases and 71 healthy controls (HC), and a validation sample of 26 PTSD cases and 36 HC. A machine learning method, random forests (RF), in conjunction with a clustering method, partitioning around medoids, were used to identify subtypes derived from 16 self-report and clinician assessment scales, including the clinician-administered PTSD scale for DSM-IV (CAPS). Two subtypes were identified, designated S1 and S2, differing on mean current CAPS total scores: S2 = 75.6 (sd 14.6) and S1 = 54.3 (sd 6.6). S2 had greater symptom severity scores than both S1 and HC on all scale items. The mean first principal component score derived from clinical summary scales was three times higher in S2 than in S1. Distinct RFs were grown to classify S1 and S2 vs. HCs and vs. each other on multi-omic blood markers feature classes of current medical comorbidities, neurocognitive functioning, demographics, pre-military trauma, and psychiatric history. Among these classes, in each RF intergroup comparison of S1, S2, and HC, multi-omic biomarkers yielded the highest AUC-ROCs (0.819–0.922); other classes added little to further discrimination of the subtypes. Among the top five biomarkers in each of these RFs were methylation, micro RNA, and lactate markers, suggesting their biological role in symptom severity.

Classification of Observations through Combination of the Dimension Reduction and the Cluster Analysis

2017 ◽  
Vol 7 (8) ◽  
pp. 30
Author(s):  
Hyeuk Kim
Keyword(s):  
Machine Learning ◽  
Principal Component Analysis ◽  
Cluster Analysis ◽  
Unsupervised Learning ◽  
Principal Component ◽  
Component Analysis ◽  
Baseball Players ◽  
Partitioning Around Medoids ◽  
Different Characteristics

Unsupervised learning in machine learning divides data into several groups. The observations in the same group have similar characteristics and the observations in the different groups have the different characteristics. In the paper, we classify data by partitioning around medoids which have some advantages over the k-means clustering. We apply it to baseball players in Korea Baseball League. We also apply the principal component analysis to data and draw the graph using two components for axis. We interpret the meaning of the clustering graphically through the procedure. The combination of the partitioning around medoids and the principal component analysis can be used to any other data and the approach makes us to figure out the characteristics easily.

scholarly journals 2418 Post-traumatic stress symptoms in caregivers of pediatric hydrocephalus population

2018 ◽  
Vol 2 (S1) ◽  
pp. 86-86
Author(s):  
Kathrin Zimmerman ◽  
Alexandra Cutillo ◽  
Laura Dreer ◽  
Anastasia Arynchyna ◽  
Brandon G. Rocque
Keyword(s):  
Traumatic Stress ◽  
Symptom Severity ◽  
Traumatic Event ◽  
Self Report ◽  
Csf Shunt ◽  
Post Traumatic Stress ◽  
Pediatric Hydrocephalus ◽  
Stress Symptoms ◽  
Severity Scores ◽  
Post Traumatic

OBJECTIVES/SPECIFIC AIMS: The goal of this study is to characterize traumatic events and post-traumatic stress symptom severity experienced by caregivers of children with hydrocephalus. Results will eventually be evaluated and compared with demographic and medical characteristics. This study is part of a larger research project that aims to (1) determine the prevalence and risk factors for post-traumatic stress symptoms in pediatric hydrocephalus patients and their caregivers; (2) develop a targeted intervention to mitigate its effects and pilot test the intervention. METHODS/STUDY POPULATION: Caregivers of children with hydrocephalus that have received surgical treatment (CSF shunt or ETV/CPC) were enrolled during routine follow up visit in a pediatric neurosurgery clinic. Caregivers completed the PTSD Checklist for DSM-5 (PCL-5), a 20-item self-report measure that assesses the presence and severity of post-traumatic stress disorder (PTSD) symptoms. RESULTS/ANTICIPATED RESULTS: Participant responses (n=56) revealed that 57.14% of caregivers indicated that their most traumatic event was directly related to their child’s medical condition. In total, 23.21% of caregivers did not specify their most traumatic event and 1.79% of caregivers indicated that they had never experienced a traumatic event. Median Total Symptom Severity Score was 11 (mean: 15.32±14.92), and scores ranged from 0 to 67; 32.14% of caregivers scored 19 or greater, and 16.07% of caregivers scored 33 or greater, a value suggestive of a provisional diagnosis of PTSD. Severity scores by DSM-V clusters were as follows: cluster B—intrusion symptoms (mean: 4.91±4.77, median: 4, range: 0–20), cluster C—avoidance symptoms (mean: 1.27±1.87, median: 0.5, range: 0–8), cluster D—negative alterations in cognition and mood (mean: 4.86±6.07, median: 2, range: 0–22), and cluster E—alterations in arousal and reactivity (mean: 4.29±4.07, median: 3, range: 0–17). DISCUSSION/SIGNIFICANCE OF IMPACT: Preliminary results from this study indicate that post-traumatic stress symptoms are prevalent among caregivers of children with hydrocephalus. These results suggest that psychosocial issues such as PTSS may be a significant problem in need of treatment, that is not traditionally addressed as part of routine care for families of children with hydrocephalus. Characterizing post-traumatic stress symptoms in this population sets the foundation for the development of screening and treatment protocols for post-traumatic stress symptoms in caregivers of children with hydrocephalus. This study is the first step towards fundamentally improving routine clinical care and quality of life for patients with hydrocephalus and their caregivers by understanding and addressing the effects of traumatic stress.

Analysis of the Bath Motion in the MM-SQC Dynamics Using Unsupervised Machine Learning Dimensionality Reduction Approaches: Principal Component Analysis

2020 ◽  
Author(s):  
Jiawei Peng ◽  
Yu Xie ◽  
Deping Hu ◽  
Zhenggang Lan
Keyword(s):  
Machine Learning ◽  
Principal Component Analysis ◽  
Collective Motion ◽  
Principal Component ◽  
Component Analysis ◽  
Nonadiabatic Dynamics ◽  
Trajectory Data ◽  
Unsupervised Machine Learning ◽  
Physical Knowledge ◽  
Vibronic Couplings

The system-plus-bath model is an important tool to understand nonadiabatic dynamics for large molecular systems. The understanding of the collective motion of a huge number of bath modes is essential to reveal their key roles in the overall dynamics. We apply the principal component analysis (PCA) to investigate the bath motion based on the massive data generated from the MM-SQC (symmetrical quasi-classical dynamics method based on the Meyer-Miller mapping Hamiltonian) nonadiabatic dynamics of the excited-state energy transfer dynamics of Frenkel-exciton model. The PCA method clearly clarifies that two types of bath modes, which either display the strong vibronic couplings or have the frequencies close to electronic transition, are very important to the nonadiabatic dynamics. These observations are fully consistent with the physical insights. This conclusion is obtained purely based on the PCA understanding of the trajectory data, without the large involvement of pre-defined physical knowledge. The results show that the PCA approach, one of the simplest unsupervised machine learning methods, is very powerful to analyze the complicated nonadiabatic dynamics in condensed phase involving many degrees of freedom.

Application of Machine Learning in Animal Disease Analysis and Prediction

2020 ◽  
Vol 15 ◽  
Author(s):  
Shuwen Zhang ◽  
Qiang Su ◽  
Qin Chen
Keyword(s):  
Machine Learning ◽  
Unsupervised Learning ◽  
Supervised Learning ◽  
Clustering Algorithm ◽  
Principal Component ◽  
Support Vector ◽  
Animal Disease ◽  
Human Beings ◽  
Animal Diseases ◽  
Disease Analysis

Abstract: Major animal diseases pose a great threat to animal husbandry and human beings. With the deepening of globalization and the abundance of data resources, the prediction and analysis of animal diseases by using big data are becoming more and more important. The focus of machine learning is to make computers learn how to learn from data and use the learned experience to analyze and predict. Firstly, this paper introduces the animal epidemic situation and machine learning. Then it briefly introduces the application of machine learning in animal disease analysis and prediction. Machine learning is mainly divided into supervised learning and unsupervised learning. Supervised learning includes support vector machines, naive bayes, decision trees, random forests, logistic regression, artificial neural networks, deep learning, and AdaBoost. Unsupervised learning has maximum expectation algorithm, principal component analysis hierarchical clustering algorithm and maxent. Through the discussion of this paper, people have a clearer concept of machine learning and understand its application prospect in animal diseases.

scholarly journals Correlates and Treatment Outcome of Risky Sexual Behaviour in Young Males with ADHD and Comorbid Alcohol Use Disorder: A Prospective Study

2019 ◽  
Vol 1 (1) ◽  
pp. 62-69
Author(s):  
Shankar Kumar ◽  
Yamini Devendran ◽  
Madhumitha N. S. ◽  
Javagal Amith Thejas
Keyword(s):  
Sexual Behavior ◽  
Alcohol Use ◽  
Perceived Stress ◽  
Risky Sexual Behavior ◽  
Alcohol Use Disorder ◽  
Self Report ◽  
Adult Males ◽  
Young Males ◽  
Severity Scores ◽  
Inattention And Hyperactivity

Background: Attention-deficit/hyperactivity disorder (ADHD) is associated with risky sexual behavior (RSB). Alcohol use and high perceived stress in young adulthood contributes to this association. Previous studies have not found methylphenidate to reduce RSB in ADHD, as the population had comorbidities such as mood disorders and antisocial personality disorder. We aimed to study (a) the association of RSB with ADHD and severity of alcohol use among adolescents and young adult males with ADHD who had comorbid alcohol use disorder and (b) the effect of treatment of ADHD using methylphenidate on RSB in this population at 3- and 6-month follow-ups. Methodology: The study had 31 participants who were selected by screening for RSBs using the sexual behavior section of the HIV Risk-taking Behavior Scale (HRBS) manual among a cohort of individuals with ADHD and early onset alcohol use. These individuals were also administered WHO ADHD self-report scale (ASRS), alcohol-use disorders identification test (AUDIT), perceived stress scale (PSS), and HRBS-sexual behavior section. They were then treated with methylphenidate and these assessments were repeated at 3 and 6 months. Results: Those having ADHD with RSB had higher total ADHD score ( P = .007) and inattention score ( p = .0001) than those without RSB. There was a significant correlation between the ADHD total score with alcohol-use severity ( r = 0.47), with RSB ( r = 0.34), and ADHD hyperactivity scores with alcohol-use severity ( r = 0.49) and with RSB ( r = 0.34). There was also a significant reduction of ADHD total, inattention and hyperactivity scores, alcohol-use severity scores, RSB and perceived stress scores with use of methylphenidate at 3- and 6-month follow-ups. Multiple logistic regression predicted reduction in ADHD total scores to reduce RSB (odds ratio [OR] = 1.26, P = .01). Conclusion: RSB was associated with severity of ADHD and alcohol use. Methylphenidate not only reduced ADHD severity but also alcohol-use severity and RSB, whose reduction was predicted by reduction in ADHD severity.

scholarly journals Transformer Oil Quality Assessment Using Random Forest with Feature Engineering

Energies ◽  
2021 ◽  
Vol 14 (7) ◽  
pp. 1809
Author(s):  
Mohammed El Amine Senoussaoui ◽  
Mostefa Brahami ◽  
Issouf Fofana
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Oil Quality ◽  
Principal Component ◽  
Condition Assessment ◽  
Classification Performance ◽  
Transformer Oil ◽  
Classification Model ◽  
Insulation Degradation ◽  
Transformer Oils

Machine learning is widely used as a panacea in many engineering applications including the condition assessment of power transformers. Most statistics attribute the main cause of transformer failure to insulation degradation. Thus, a new, simple, and effective machine-learning approach was proposed to monitor the condition of transformer oils based on some aging indicators. The proposed approach was used to compare the performance of two machine-learning classifiers: J48 decision tree and random forest. The service-aged transformer oils were classified into four groups: the oils that can be maintained in service, the oils that should be reconditioned or filtered, the oils that should be reclaimed, and the oils that must be discarded. From the two algorithms, random forest exhibited a better performance and high accuracy with only a small amount of data. Good performance was achieved through not only the application of the proposed algorithm but also the approach of data preprocessing. Before feeding the classification model, the available data were transformed using the simple k-means method. Subsequently, the obtained data were filtered through correlation-based feature selection (CFsSubset). The resulting features were again retransformed by conducting the principal component analysis and were passed through the CFsSubset filter. The transformation and filtration of the data improved the classification performance of the adopted algorithms, especially random forest. Another advantage of the proposed method is the decrease in the number of the datasets required for the condition assessment of transformer oils, which is valuable for transformer condition monitoring.

scholarly journals AEROBIC EXERCISE VOLUME, NOT PRESCRIPTION, INFLUENCES POST-CONCUSSION SYMPTOMS: A RANDOMIZED CLINICAL TRIAL

2021 ◽  
Vol 9 (7_suppl3) ◽  
pp. 2325967121S0014
Author(s):  
David R. Howell ◽  
Danielle Hunt ◽  
Stacey E. Aaron ◽  
William P. Meehan ◽  
Can Ozan Tan
Keyword(s):  
Clinical Trial ◽  
Aerobic Exercise ◽  
Symptom Severity ◽  
Exercise Prescription ◽  
Standard Of Care ◽  
Care Group ◽  
Initial Symptom ◽  
Initial Visit ◽  
Severity Scores ◽  
Text Figure

Background: Current recommendations for sport-related concussion uniformly emphasize the importance of physical activity. However, specifics of this recommendation remain vague and do not account for an exercise dosage or compliance. Purposes: First, we examined if an 8-week individualized sub-symptom threshold aerobic exercise prescription, initiated within the first two weeks of concussion, alleviates symptom severity or affects the amount of exercise performed during the study. Second, we examined whether prescription adherence, rather than randomized group assignment, reflects the actual impact of aerobic exercise in post-concussion recovery. Methods: For this single-site prospective randomized clinical trial, participants completed an aerobic exercise test within 14 days of injury, and were randomized to an individualized aerobic exercise program or standard-of-care, and returned for assessments 1 month and 2 months after the initial visit (Table 1). The aerobic exercise group was instructed to exercise 5 days/week, 20 minutes/day, at a target heart rate based on an exercise test at the initial visit. Participants reported their symptom exercise volume each week over the 8-week study period, and reported symptoms at each study visit (initial, 1 month, 2 month). Results: Initial symptom severity was not different between randomized groups (Figure 1A), and no significant differences in symptom severity were found at the 4-week (Figure 1B) or 8-week (Figure 1C) assessment. In addition, there was no significant differences between groups for average weekly exercise volume during the first four weeks (Figure 2A) or second four weeks (Figure 2B) of the study. During the first four weeks of the study, 65% (n=11/17) of the exercise intervention participants were compliant with their exercise recommendation (≥100 min/week), compared to 45% (n=9/20) of the standard-of-care group (p=0.33). During the second four weeks of the study, 71% (n=12/17) of the exercise prescription group exercised ≥100 min/week, compared to 55% (n=11/20) of the standard-of-care group (p=0.50). When grouped by exercise volume, the group who exercised ≥100 minutes/week during the first month of the study reported significantly lower symptom severity scores than those who exercised <100 minutes/week (Figure 3B), despite similar initial symptom severity scores (Figure 3A). Conclusion: Participant randomization within 14 days of concussion did not lead to a significant reduction in symptoms, or greater exercise volume. Given that greater exercise volume was associated with lower symptoms after one month of the study, researchers and clinicians should pay particular attention to adherence to aerobic exercise programs for the treatment of concussion. [Table: see text][Figure: see text][Figure: see text][Figure: see text]

scholarly journals Comparison of Capability of SAR and Optical Data in Mapping Forest above Ground Biomass Based on Machine Learning

2020 ◽  
Vol 5 (1) ◽  
pp. 13
Author(s):  
Negar Tavasoli ◽  
Hossein Arefi
Keyword(s):  
Machine Learning ◽  
Carbon Stock ◽  
Vegetation Indices ◽  
Forest Biomass ◽  
Principal Component ◽  
Optical Data ◽  
Above Ground Biomass ◽  
Ground Biomass ◽  
Texture Characteristics ◽  
Sentinel 2

Assessment of forest above ground biomass (AGB) is critical for managing forest and understanding the role of forest as source of carbon fluxes. Recently, satellite remote sensing products offer the chance to map forest biomass and carbon stock. The present study focuses on comparing the potential use of combination of ALOSPALSAR and Sentinel-1 SAR data, with Sentinel-2 optical data to estimate above ground biomass and carbon stock using Genetic-Random forest machine learning (GA-RF) algorithm. Polarimetric decompositions, texture characteristics and backscatter coefficients of ALOSPALSAR and Sentinel-1, and vegetation indices, tasseled cap, texture parameters and principal component analysis (PCA) of Sentinel-2 based on measured AGB samples were used to estimate biomass. The overall coefficient (R2) of AGB modelling using combination of ALOSPALSAR and Sentinel-1 data, and Sentinel-2 data were respectively 0.70 and 0.62. The result showed that Combining ALOSPALSAR and Sentinel-1 data to predict AGB by using GA-RF model performed better than Sentinel-2 data.

scholarly journals A Strategy for Dimensionality Reduction and Data Analysis Applied to Microstructure–Property Relationships of Nanoporous Metals

Materials ◽  
2021 ◽  
Vol 14 (8) ◽  
pp. 1822
Author(s):  
Norbert Huber
Keyword(s):  
Machine Learning ◽  
Dimensionality Reduction ◽  
Work Hardening ◽  
Large Range ◽  
Scaling Law ◽  
Principal Component ◽  
Underlying Structure ◽  
Structure Property ◽  
Work Hardening Rate ◽  
Nanoporous Metals

Nanoporous metals, with their complex microstructure, represent an ideal candidate for the development of methods that combine physics, data, and machine learning. The preparation of nanporous metals via dealloying allows for tuning of the microstructure and macroscopic mechanical properties within a large design space, dependent on the chosen dealloying conditions. Specifically, it is possible to define the solid fraction, ligament size, and connectivity density within a large range. These microstructural parameters have a large impact on the macroscopic mechanical behavior. This makes this class of materials an ideal science case for the development of strategies for dimensionality reduction, supporting the analysis and visualization of the underlying structure–property relationships. Efficient finite element beam modeling techniques were used to generate ~200 data sets for macroscopic compression and nanoindentation of open pore nanofoams. A strategy consisting of dimensional analysis, principal component analysis, and machine learning allowed for data mining of the microstructure–property relationships. It turned out that the scaling law of the work hardening rate has the same exponent as the Young’s modulus. Simple linear relationships are derived for the normalized work hardening rate and hardness. The hardness to yield stress ratio is not limited to 1, as commonly assumed for foams, but spreads over a large range of values from 0.5 to 3.

Brompheniramine Maleate: A Double-Blind, Placebo-Controlled Comparison with Terfenadine for Symptoms of Allergic Rhinitis

1998 ◽  
Vol 12 (4) ◽  
pp. 293-300 ◽  
Author(s):  
William R. Thoden ◽  
Howard M. Druce ◽  
Sandy A. Furey ◽  
Earle A. Lockhart ◽  
Paul Ratner ◽  
...  
Keyword(s):  
Allergic Rhinitis ◽  
Symptom Severity ◽  
Extended Release ◽  
Nasal Symptom ◽  
Double Blind ◽  
Release Formulation ◽  
Extended Release Formulation ◽  
Adverse Experiences ◽  
Severity Scores ◽  
Brompheniramine Maleate

This was a double-blind, randomized, placebo-controlled, multicenter, parallel study comparing the effectiveness, at recommended doses, of an extended-release formulation of brompheniramine maleate and terfenadine in the treatment of allergic rhinitis. Subjects with symptoms of seasonal and/or perennial allergic rhinitis received brompheniramine 12 mg (n = 106), 8 mg (n = 105), terfenadine 60 mg (n = 106), or placebo (n = 53) twice daily for 14 days. On treatment days 3, 7, and 14, symptom severity ratings (i.e., rhinorrhea, sneezing, nasal congestion, itchy nose, eyes or throat, excessive tearing, postnasal drip) were completed by the physician; subjects and physicians each completed a global efficacy evaluation. Brompheniramine 12 mg and 8 mg and terfenadine were more effective than placebo (p ≤ 0.05) on the physicians’ global; brompheniramine 12 mg was more effective than terfenadine (p ≤ 0.05) on days 7 and 14 and brompheniramine 8 mg on day 3. On the subjects’ global evaluation, brompheniramine 12 mg and 8 mg and terfenadine were more effective than placebo (p ≤ 0.05); brompheniramine 12 mg was more effective than terfenadine (p ≤ 0.05) on days 7 and 14 and brompheniramine 8 mg on day 3. In general, brompheniramine 8 mg was comparable to terfenadine. On days 3 and 7, the total symptom and total nasal symptom severity scores for subjects receiving brompheniramine 12 mg were significantly more improved than for placebo (p < 0.05); terfenadine was not different from placebo; brompheniramine 12 mg was significantly better than terfenadine on day 7 (p < 0.05) for reducing total symptom severity and on days 3, 7, and 14 for reducing total nasal symptom severity. Adverse experiences were reported by 155 (41.9%) of the 370 subjects enrolled in the study. The overall rate of adverse experiences in the brompheniramine 12 mg treatment group (57.5%) was significantly greater (p < 0.05) than for brompheniramine 8 mg (38.1%), terfenadine (31.1%), and placebo (39.6%). In conclusion, an extended-release formulation of brompheniramine 12 mg or 8 mg bid alleviates allergic rhinitis symptoms and brompheniramine 12 mg provides significantly better relief of these symptoms than terfenadine 60 mg bid.

Sign in / Sign up

Export Citation Format

Share Document