scholarly journals Machine Learning for Subtyping Concussion Using a Clustering Approach

2021 ◽  
Vol 15 ◽  
Author(s):  
Cirelle K. Rosenblatt ◽  
Alexandra Harriss ◽  
Aliya-Nur Babul ◽  
Samuel A. Rosenblatt
Keyword(s):  
Machine Learning ◽  
Clustering Algorithm ◽  
Pain Catastrophizing ◽  
Optimal Number ◽  
Cognitive Testing ◽  
Measurement Information ◽  
Learning Approach ◽  
Agglomerative Clustering ◽  
Patient Reported ◽  
Machine Learning Approach

Background: Concussion subtypes are typically organized into commonly affected symptom areas or a combination of affected systems, an approach that may be flawed by bias in conceptualization or the inherent limitations of interdisciplinary expertise.Objective: The purpose of this study was to determine whether a bottom-up, unsupervised, machine learning approach, could more accurately support concussion subtyping.Methods: Initial patient intake data as well as objective outcome measures including, the Patient-Reported Outcomes Measurement Information System (PROMIS), Dizziness Handicap Inventory (DHI), Pain Catastrophizing Scale (PCS), and Immediate Post-Concussion Assessment and Cognitive Testing Tool (ImPACT) were retrospectively extracted from the Advance Concussion Clinic's database. A correlation matrix and principal component analysis (PCA) were used to reduce the dimensionality of the dataset. Sklearn's agglomerative clustering algorithm was then applied, and the optimal number of clusters within the patient database were generated. Between-group comparisons among the formed clusters were performed using a Mann-Whitney U test.Results: Two hundred seventy-five patients within the clinics database were analyzed. Five distinct clusters emerged from the data when maximizing the Silhouette score (0.36) and minimizing the Davies-Bouldin score (0.83). Concussion subtypes derived demonstrated clinically distinct profiles, with statistically significant differences (p < 0.05) between all five clusters.Conclusion: This machine learning approach enabled the identification and characterization of five distinct concussion subtypes, which were best understood according to levels of complexity, ranging from Extremely Complex to Minimally Complex. Understanding concussion in terms of Complexity with the utilization of artificial intelligence, could provide a more accurate concussion classification or subtype approach; one that better reflects the true heterogeneity and complex system disruptions associated with mild traumatic brain injury.

scholarly journals Control Oriented Prediction of Driver Brake Intention and Intensity Using a Composite Machine Learning Approach

Energies ◽  
2019 ◽  
Vol 12 (13) ◽  
pp. 2483 ◽  
Author(s):  
Jianhao ◽  
Jing ◽  
Longqiang ◽  
Yi ◽  
Hanzhang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Clustering Algorithm ◽  
External Input ◽  
Feature Subset Selection ◽  
Learning Approach ◽  
Area Network ◽  
Feature Subset ◽  
Sensor Failure ◽  
Machine Learning Approach ◽  
And Control

Driver perception, decision, and control behaviors are easily affected by traffic conditions and driving style, showing the tendency of randomness and personalization. Brake intention and intensity are integrated and control-oriented parameters that are crucial to the development of an intelligent braking system. In this paper, a composite machine learning approach was proposed to predict driver brake intention and intensity with a proper prediction horizon. Various driving data were collected from Controller Area Network (CAN) bus under a real driving condition, which mainly contained urban and rural road types. ReliefF and RReliefF (they don’t have abbreviations) algorithms were employed as feature subset selection methods and applied in a prepossessing step before the training. The rank importance of selected predictors exhibited different trends or even negative trends when predicting brake intention and intensity. A soft clustering algorithm, Fuzzy C-means, was adopted to label the brake intention into categories, namely slight, medium, intensive, and emergency braking. Data sets with misplaced labels were used for training of an ensemble machine learning method, random forest. It was validated that brake intention could be accurately predicted 0.5 s ahead. An open-loop nonlinear autoregressive with external input (NARX) network was capable of learning the long-term dependencies in comparison to the static neural network and was suggested for online recognition and prediction of brake intensity 1 s in advance. As system redundancy and fault tolerance, a close-loop NARX network could be adopted for brake intensity prediction in the case of possible sensor failure and loss of CAN message.

scholarly journals Predicting Clinically Relevant Patient-Reported Symptom Improvement After Carpal Tunnel Release: A Machine Learning Approach

Neurosurgery ◽  
2021 ◽  
Vol 90 (1) ◽  
pp. 106-113 ◽  
Author(s):  
Lisa Hoogendam ◽  
Jeanne A. C. Bakx ◽  
J. Sebastiaan Souer ◽  
Harm P. Slijper ◽  
Eleni-Rosalina Andrinopoulou ◽  
...  
Keyword(s):  
Machine Learning ◽  
Carpal Tunnel ◽  
Carpal Tunnel Release ◽  
Symptom Improvement ◽  
Learning Approach ◽  
Patient Reported ◽  
Machine Learning Approach

EMPLOYING FUZZY C-MEANS FOR DNA TRANSCRIPTION FACTOR BINDING SITE IDENTIFICATION

2010 ◽  
Vol 19 (01) ◽  
pp. 15-30 ◽  
Author(s):  
TURGAY İBRİKCİ ◽  
MUSTAFA KARABULUT
Keyword(s):  
Machine Learning ◽  
Dna Sequences ◽  
Motif Discovery ◽  
Clustering Algorithm ◽  
Motif Finding ◽  
Synthesis Process ◽  
Learning Approach ◽  
Fuzzy C Means ◽  
Dna Motif ◽  
Machine Learning Approach

DNA motif discovery is an important task since it helps to better understand the regulation of the transcription in the protein synthesis process. This paper introduces a novel method for the task of DNA motif finding where the proposed method adopts machine-learning approach by the use of a well-known clustering algorithm, Fuzzy C-Means. The method is explained in detail and tested against DNA sequences extracted from the genome of Saccharomyces cerevisiae and Escherichia coli organisms. Experimental results suggest that the algorithm is efficient in finding statistically interesting features existing in the DNA sequences. The comparison of the algorithm with the well-known motif finding tools, MEME and MDScan, which are built on statistical and word-enumerative models, shows the advantages of the proposed method over the existing tools and the promising direction of the machine-learning approach.

scholarly journals Estimate of the HOMA-IR Cut-off Value Identifying Subjects at Risk of Insulin Resistance using a Machine Learning Approach

2021 ◽  
Author(s):  
Abdelhamid Abdessalem ◽  
Hamza Zidoum ◽  
Fahd Zadjali ◽  
Rachid Hedjam ◽  
Aliya Al-Ansari ◽  
...  
Keyword(s):  
Machine Learning ◽  
Insulin Resistance ◽  
At Risk ◽  
Clinical Data ◽  
Clustering Algorithm ◽  
Early Stage ◽  
Strong Relationship ◽  
Learning Approach ◽  
Machine Learning Approach ◽  
Research Findings

Objective: This paper describes an unsupervised Machine Learning approach to estimate the HOMA-IR cut-off identifying subjects at risk of insulin resistance in a given ethnic group, based on the clinical data of a representative sample. Methods: We apply the approach to clinical data of individuals of Arab ancestors obtained from a family study conducted in the city of Nizwa between January 2000 and December 2004. First, we identify HOMA-IR-correlated variables to which we apply our own clustering algorithm. Two clusters having the smallest overlap in their HOMA-IR values are returned. These clusters represent samples of two populations: insulin sensitive subjects and individuals at risk of insulin resistance. The cut-off value is estimated from intersections of the Gaussian functions modelling the HOMA-IR distributions of these populations. Results: We identified a HOMA-IR cut-off value of 1.62+/-0.06. We demonstrated the validity of this cut-off by 1) Showing that clinical characteristics of the identified groups match well published research findings about insulin resistance. 2) Showing a strong relationship between the segmentations resulting from the proposed cut-off and that resulting from the 2-hours glucose cut-off recommended by WHO for detecting prediabetes. Finally, we showed that the method is also able to identify cut-off values for similar problems (e.g. fasting sugar cut-off for prediabetes). Conclusion: The proposed method defines a HOMA-IR cut-off value for detecting individuals at risk of insulin resistance. Such method can identify high risk individuals at early stage which may prevent or at least delay the onset of chronic diseases like type 2 diabetes. Keywords: Machine Learning; Feature Selection; K-mean++ Clustering; Insulin Resistance; HOMA-IR; T2DM.

Sign in / Sign up

Export Citation Format

Share Document