scholarly journals A model to differentiate WAD patients and people with abnormal pain behaviour based on biomechanical and self-reported tests

2021 ◽  
Author(s):  
Merylin Monaro ◽  
Helios De Rosario ◽  
José María Baydal-Bertomeu ◽  
Marta Bernal-Lafuente ◽  
Stefano Masiero ◽  
...  
Keyword(s):  
Cross Validation ◽  
Area Under The Curve ◽  
Economic Loss ◽  
Self Report ◽  
Classification Model ◽  
Biomechanical Test ◽  
Linear Discriminant ◽  
Detection Model ◽  
Mechanical Approach ◽  
Malingering Detection

AbstractThe prevalence of malingering among individuals presenting whiplash-related symptoms is significant and leads to a huge economic loss due to fraudulent injury claims. Various strategies have been proposed to detect malingering and symptoms exaggeration. However, most of them have been not consistently validated and tested to determine their accuracy in detecting feigned whiplash. This study merges two different approaches to detect whiplash malingering (the mechanical approach and the qualitative analysis of the symptomatology) to obtain a malingering detection model based on a wider range of indices, both biomechanical and self-reported. A sample of 46 malingerers and 59 genuine clinical patients was tested using a kinematic test and a self-report questionnaire asking about the presence of rare and impossible symptoms. The collected measures were used to train and validate a linear discriminant analysis (LDA) classification model. Results showed that malingerers were discriminated from genuine clinical patients based on a greater proportion of rare symptoms vs. possible self-reported symptoms and slower but more repeatable neck motions in the biomechanical test. The fivefold cross-validation of the LDA model yielded an area under the curve (AUC) of 0.84, with a sensitivity of 77.8% and a specificity of 84.7%.

scholarly journals Using machine learning to predict COVID-19 infection and severity risk among 4,510 aged adults: a UK Biobank cohort study

2020 ◽  
Author(s):  
Auriel A. Willette ◽  
Sara A. Willette ◽  
Qian Wang ◽  
Colleen Pappas ◽  
Brandon S. Klinedinst ◽  
...  
Keyword(s):  
Area Under The Curve ◽  
Severe Infection ◽  
Host Immunity ◽  
Self Report ◽  
Biomedical Data ◽  
Uk Biobank ◽  
Linear Discriminant ◽  
Antibody Titers ◽  
Rare Infectious Diseases ◽  
Best Fit

AbstractBackgroundMany risk factors have emerged for novel 2019 coronavirus disease (COVID-19). It is relatively unknown how these factors collectively predict COVID-19 infection risk, as well as risk for a severe infection (i.e., hospitalization).MethodsAmong aged adults (69.3 ± 8.6 years) in UK Biobank, COVID-19 data was downloaded for 4,510 participants with 7,539 test cases. We downloaded baseline data from 10-14 years ago, including demographics, biochemistry, body mass, and other factors, as well as antibody titers for 20 common to rare infectious diseases. Permutation-based linear discriminant analysis was used to predict COVID-19 risk and hospitalization risk. Probability and threshold metrics included receiver operating characteristic curves to derive area under the curve (AUC), specificity, sensitivity, and quadratic mean.ResultsThe “best-fit” model for predicting COVID-19 risk achieved excellent discrimination (AUC=0.969, 95% CI=0.934-1.000). Factors included age, immune markers, lipids, and serology titers to common pathogens like human cytomegalovirus. The hospitalization “best-fit” model was more modest (AUC=0.803, 95% CI=0.663-0.943) and included only serology titers.ConclusionsAccurate risk profiles can be created using standard self-report and biomedical data collected in public health and medical settings. It is also worthwhile to further investigate if prior host immunity predicts current host immunity to COVID-19.

scholarly journals A multilayer multimodal detection and prediction model based on explainable artificial intelligence for Alzheimer’s disease

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Shaker El-Sappagh ◽  
Jose M. Alonso ◽  
S. M. Riazul Islam ◽  
Ahmad M. Sultan ◽  
Kyung Sup Kwak
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Cross Validation ◽  
Disease Risk ◽  
Binary Classification ◽  
Fuzzy Rule ◽  
Large Set ◽  
Detection Model ◽  
Multi Class Classification ◽  
Clinical Measures

AbstractAlzheimer’s disease (AD) is the most common type of dementia. Its diagnosis and progression detection have been intensively studied. Nevertheless, research studies often have little effect on clinical practice mainly due to the following reasons: (1) Most studies depend mainly on a single modality, especially neuroimaging; (2) diagnosis and progression detection are usually studied separately as two independent problems; and (3) current studies concentrate mainly on optimizing the performance of complex machine learning models, while disregarding their explainability. As a result, physicians struggle to interpret these models, and feel it is hard to trust them. In this paper, we carefully develop an accurate and interpretable AD diagnosis and progression detection model. This model provides physicians with accurate decisions along with a set of explanations for every decision. Specifically, the model integrates 11 modalities of 1048 subjects from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) real-world dataset: 294 cognitively normal, 254 stable mild cognitive impairment (MCI), 232 progressive MCI, and 268 AD. It is actually a two-layer model with random forest (RF) as classifier algorithm. In the first layer, the model carries out a multi-class classification for the early diagnosis of AD patients. In the second layer, the model applies binary classification to detect possible MCI-to-AD progression within three years from a baseline diagnosis. The performance of the model is optimized with key markers selected from a large set of biological and clinical measures. Regarding explainability, we provide, for each layer, global and instance-based explanations of the RF classifier by using the SHapley Additive exPlanations (SHAP) feature attribution framework. In addition, we implement 22 explainers based on decision trees and fuzzy rule-based systems to provide complementary justifications for every RF decision in each layer. Furthermore, these explanations are represented in natural language form to help physicians understand the predictions. The designed model achieves a cross-validation accuracy of 93.95% and an F1-score of 93.94% in the first layer, while it achieves a cross-validation accuracy of 87.08% and an F1-Score of 87.09% in the second layer. The resulting system is not only accurate, but also trustworthy, accountable, and medically applicable, thanks to the provided explanations which are broadly consistent with each other and with the AD medical literature. The proposed system can help to enhance the clinical understanding of AD diagnosis and progression processes by providing detailed insights into the effect of different modalities on the disease risk.

Patient self-reporting of tolerability using PRO-CTCAE: A randomized double-blind placebo controlled phase II trial comparing gemcitabine in combination with adavosertib or placebo in women with platinum resistant epithelial ovarian cancer.

2021 ◽  
Vol 39 (15_suppl) ◽  
pp. 5541-5541
Author(s):  
Ainhoa Madariaga ◽  
Sandra A. Mitchell ◽  
Tyler Pittman ◽  
Lisa Wang ◽  
Valerie Bowering ◽  
...  
Keyword(s):  
Ovarian Cancer ◽  
Abdominal Pain ◽  
Objective Assessment ◽  
Area Under The Curve ◽  
Recurrent Ovarian Cancer ◽  
Median Number ◽  
Self Report ◽  
Double Blind ◽  
Patient Reported ◽  
Fatigue Severity

5541 Background: A 4 month improvement in OS was demonstrated when Wee1 inhibitor adavosertib (Ad) and gemcitabine (G; arm A) was compared to G and placebo (P; arm B) in a phase 2 trial in recurrent ovarian cancer (NCT02151292). The patient reported outcome version of the CTCAE (PRO-CTCAE) was used to capture self-report of the frequency, severity and/or interference (scored 0-4; higher scores indicating worse symptomatic adverse events [syAEs]). Methods: Ad/P was given orally on D1-2, D8-9, D15-16 with G D1, D8, D15 in a 28-day cycle. English speaking pts in 2 centres completed PRO-CTCAE items electronically in clinic at baseline, D1 and D15 of each cycle and off treatment. An exploratory objective was to characterize syAEs in the first 3 months of therapy. We calculated 12-week area under the curve (AUC12w) as a measure of syAE over time and incremental AUC12w (iAUC12w) for adjustment to baseline syAEs and compared arms A and B using an independent samples t-test. We assessed proportion of scores 3-4 at 6 time-points and compared them using Fisher’s Exact Test at each survey. Results: 51 pts were enrolled and completed ≥1 survey, 47 were evaluable for primary outcome (arm A: 28, B: 19). ECOG status was ≤1 in 44/47 pts. Median number of cycles of therapy were 5 (1-16) in arm A, and 2 (1-16) in B. Survey completion rates were high (arm A 93%, B 95%). Mean AUC12w fatigue severity (A 152 [standard error 9] vs B 112 [10]; p = 0.005) and interference (A 144 [11] vs 98 [15]; p = 0.018), diarrhea frequency (A 70 [12] vs B 33 [9]; p = 0.014), mucositis (A 23 [6] vs B 6 [3]; p = 0.012) and difficulty swallowing severity (A 10 [3] vs B 2 [2]; p = 0.023) were higher in arm A (any grade). There were no statistically significant between-arm differences in abdominal pain, bloating, nausea, vomiting and anxiety. The iAUC12w was significantly higher in arm A vs B for difficulty swallowing severity (A 10.1 [3] vs B -2.7 [4.7]; p = 0.02), mucositis severity (A 19.9 [6.6] vs B -3.1 [6.9]; p = 0.02) and fatigue severity (A 35.2 [8.2] vs B -3.1 [9.8]; p = 0.005). Proportions with high scores (3-4) were only significantly higher at C1D15 for fatigue severity in arm A (A 55% vs B 19%, p = 0.044). No significant differences were seen in other 3-4 scores per survey time. Conclusions: This is the first study evaluating pts self-reported toxicity with adavosertib in a randomized setting, allowing pts self-evaluation of toxicity in the context of improved PFS and OS. Greater fatigue, diarrhea, mucositis and difficulty swallowing were experienced by pts receiving adavosertib and gemcitabine, but score 3-4 reached significance on C1D15 fatigue only. No significant differences were detected in syAE profile for nausea, vomiting, abdominal pain, bloating and anxiety. This approach allows objective assessment of pts perception of toxicity with complex therapy. Clinical trial information: NCT02151292.

scholarly journals Excessive Crossed Disparity Detection by Visual Evoked Potentials to Reduce Visual Discomfort in 3D Viewing

2018 ◽  
Vol 2018 ◽  
pp. 1-8
Author(s):  
Xiao Wang ◽  
Liuye Yao ◽  
Zhiyu Qian ◽  
Lidong Xing ◽  
Weitao Li ◽  
...  
Keyword(s):  
Evoked Potentials ◽  
Visual Evoked Potentials ◽  
Experimental System ◽  
Occipital Lobe ◽  
Cost Effective ◽  
Subjective Assessment ◽  
Classification Model ◽  
Visual Discomfort ◽  
Linear Discriminant ◽  
Visual Evoked

As excessive crossed disparity is known to cause visual discomfort, this study aims to establish a classification model to discriminate excessive crossed disparity in stereoscopic viewing in combination with subjective assessment of visual discomfort. A stereo-visual evoked potentials (VEPs) experimental system was built up to obtain the VEPs evoked by stereoscopic stimulus with different disparities. Ten volunteers participated in this experiment, and forty VEP datasets in total were extracted when the viewers were under comfortable viewing conditions. Six features of VEPs from three electrodes at the occipital lobe were chosen, and the classification was established using the Fisher’s linear discriminant (FLD). Based on FLD results, the correct rate for determining the excessive crossed disparity was 70%, and it reached 80% for other stimuli. The study demonstrated cost-effective discriminant classification modelling to distinguish the stimulus with excessive crossed disparity which inclines to cause visual discomfort.

scholarly journals Multiple biomarker panel to screen for severe aortic stenosis: results from the CASABLANCA study

Open Heart ◽  
2018 ◽  
Vol 5 (2) ◽  
pp. e000916 ◽  
Author(s):  
Sammy Elmariah ◽  
Cian McCarthy ◽  
Nasrien Ibrahim ◽  
Deborah Furman ◽  
Renata Mukai ◽  
...  
Keyword(s):  
Aortic Valve ◽  
Predictive Value ◽  
Cross Validation ◽  
Severe Aortic Stenosis ◽  
Area Under The Curve ◽  
Diagnostic Model ◽  
Aortic Valve Area ◽  
Academic Medical Centre ◽  
Diagnostic Score ◽  
Biomarker Panel

ObjectiveSevere aortic valve stenosis (AS) develops via insidious processes and can be challenging to correctly diagnose. We sought to develop a circulating biomarker panel to identify patients with severe AS.MethodsWe enrolled study participants undergoing coronary or peripheral angiography for a variety of cardiovascular diseases at a single academic medical centre. A panel of 109 proteins were measured in blood obtained at the time of the procedure. Statistical learning methods were used to identify biomarkers and clinical parameters that associate with severe AS. A diagnostic model incorporating clinical and biomarker results was developed and evaluated using Monte Carlo cross-validation.ResultsOf 1244 subjects (age 66.4±11.5  years, 28.7% female), 80 (6.4%) had severe AS (defined as aortic valve area (AVA) <1.0  cm2). A final model included age, N-terminal pro-B-type natriuretic peptide, von Willebrand factor and fetuin-A. The model had good discrimination for severe AS (OR=5.9, 95% CI 3.5 to 10.1, p<0.001) with an area under the curve of 0.76 insample and 0.74 with cross-validation. A diagnostic score was generated. Higher prevalence of severe AS was noted in those with higher scores, such that 1.6% of those with a score of 1 had severe AS compared with 15.3% with a score of 5 (p<0.001), and score values were inversely correlated with AVA (r=−0.35; p<0.001). At optimal model cut-off, we found 76% sensitivity, 65% specificity, 13% positive predictive value and 98% negative predictive value.ConclusionsWe describe a novel, multiple biomarker approach for diagnostic evaluation of severe AS.Trial registration numberNCT00842868.

scholarly journals Komparasi Metode Klasifikasi untuk Deteksi Ekspresi Wajah Dengan Fitur Facial Landmark

2021 ◽  
Vol 8 (5) ◽  
pp. 949
Author(s):  
Fitra A. Bachtiar ◽  
Muhammad Wafi
Keyword(s):  
Facial Expression ◽  
Facial Expressions ◽  
Cross Validation ◽  
Classification Model ◽  
Expression Recognition ◽  
Classification Methods ◽  
Human Machine Interaction ◽  
Facial Landmark ◽  
Total Data ◽  
Machine Interaction

<p><em>Human machine interaction</em>, khususnya pada <em>facial</em> <em>behavior</em> mulai banyak diperhatikan untuk dapat digunakan sebagai salah satu cara untuk personalisasi pengguna. Kombinasi ekstraksi fitur dengan metode klasifikasi dapat digunakan agar sebuah mesin dapat mengenali ekspresi wajah. Akan tetapi belum diketahui basis metode klasifikasi apa yang tepat untuk digunakan. Penelitian ini membandingkan tiga metode klasifikasi untuk melakukan klasifikasi ekspresi wajah. Dataset ekspresi wajah yang digunakan pada penelitian ini adalah JAFFE dataset dengan total 213 citra wajah yang menunjukkan 7 (tujuh) ekspresi wajah. Ekspresi wajah pada dataset tersebut yaitu <em>anger</em>, <em>disgust</em>, <em>fear</em>, <em>happy</em>, <em>neutral</em>, <em>sadness</em>, dan <em>surprised</em>. Facial Landmark digunakan sebagai ekstraksi fitur wajah. Model klasifikasi yang digunakan pada penelitian ini adalah ELM, SVM, dan <em>k</em>-NN. Masing masing model klasifikasi akan dicari nilai parameter terbaik dengan menggunakan 80% dari total data. 5- <em>fold</em> <em>cross-validation</em> digunakan untuk mencari parameter terbaik. Pengujian model dilakukan dengan 20% data dengan metode evaluasi akurasi, F1 Score, dan waktu komputasi. Nilai parameter terbaik pada ELM adalah menggunakan 40 hidden neuron, SVM dengan nilai  = 10<sup>5</sup> dan 200 iterasi, sedangkan untuk <em>k</em>-NN menggunakan 3 <em>k</em> tetangga. Hasil uji menggunakan parameter tersebut menunjukkan ELM merupakan algoritme terbaik diantara ketiga model klasifikasi tersebut. Akurasi dan F1 Score untuk klasifikasi ekspresi wajah untuk ELM mendapatkan nilai akurasi sebesar 0.76 dan F1 Score 0.76, sedangkan untuk waktu komputasi membutuhkan waktu 6.97´10<sup>-3</sup> detik.   </p><p> </p><p><em><strong>Abstract</strong></em></p><p class="Abstract">H<em>uman-machine interaction, especially facial behavior is considered to be use in user personalization. Feature extraction and classification model combinations can be used for a machine to understand the human facial expression. However, which classification base method should be used is not yet known. This study compares three classification methods for facial expression recognition. JAFFE dataset is used in this study with a total of 213 facial images which shows seven facial expressions. The seven facial expressions are anger, disgust, fear, happy, neutral, sadness, dan surprised. Facial Landmark is used as a facial component features. The classification model used in this study is ELM, SVM, and k-NN. The hyperparameter of each model is searched using 80% of the total data. 5-fold cross-validation is used to find the hyperparameter. The testing is done using 20% of the data and evaluated using accuracy, F1 Score, and computation time. The hyperparameter for ELM is 40 hidden neurons, SVM with  = 105 and 200 iteration, while k-NN used 3 k neighbors. The experiment results show that ELM outperforms other classification methods. The accuracy and F1 Score achieved by ELM is 0.76 and 0.76, respectively. Meanwhile, time computation takes 6.97 10<sup>-3</sup> seconds.      </em></p>

scholarly journals Urinary MicroRNA Biomarkers for Detecting The Presence of Esophageal Cancer

2020 ◽  
Author(s):  
Yusuke Okuda ◽  
Takaya Shimura ◽  
Hiroyasu Iwasaki ◽  
Shigeki Fukusada ◽  
Ruriko Nishigaki ◽  
...  
Keyword(s):  
Esophageal Cancer ◽  
Poor Prognosis ◽  
Cross Validation ◽  
Area Under The Curve ◽  
Pcr Analysis ◽  
Discovery Cohort ◽  
Qrt Pcr ◽  
Urinary Levels ◽  
Noninvasive Biomarker ◽  
Test Sets

Abstract Background: Esophageal cancer (EC) including esophageal squamous cell carcinoma (ESCC) and adenocarcinoma (EAC) generally exhibits poor prognosis; hence, a noninvasive biomarker enabling early detection is necessary. Methods: Age- and sex-matched 150 healthy controls (HCs) and 43 patients with ESCC were randomly divided into two groups: 9 patients in the discovery cohort for microarray analysis and 184 patients in the training/test cohort with cross-validation for qRT-PCR analysis. Using 152 urine samples (144 HCs and 8 EACs), we validated the urinary miRNA biomarkers for EAC diagnosis.Results: Among eight miRNAs selected in the discovery cohort, urinary levels of five miRNAs (miR-1273f, miR-619-5p, miR-150-3p, miR-4327, and miR-3135b) were significantly higher in the ESCC group than in the HC group, in the training/test cohort. Consistently, these five urinary miRNAs were significantly different between HC and ESCC in both training and test sets. Especially, urinary miR-1273f and miR-619-5p showed excellent values of area under the curve (AUC) ≥ 0.80 for diagnosing stage I ESCC. Similarly, the EAC group had significantly higher urinary levels of these five miRNAs than the HC group, with AUC values of approximately 0.80.Conclusion: The present study established novel urinary miRNA biomarkers that can early detect ESCC and EAC.

scholarly journals CT-Based Radiomics Analysis for Preoperative Diagnosis of Pancreatic Mucinous Cystic Neoplasm and Atypical Serous Cystadenomas

2021 ◽  
Vol 11 ◽  
Author(s):  
Tiansong Xie ◽  
Xuanyi Wang ◽  
Zehua Zhang ◽  
Zhengrong Zhou
Keyword(s):  
Predictive Value ◽  
Cross Validation ◽  
Clinical Decision Making ◽  
Area Under The Curve ◽  
Clinical Decision ◽  
Cystic Neoplasm ◽  
Cystic Neoplasms ◽  
Serous Cystadenomas ◽  
Radiological Model ◽  
Fold Cross Validation

ObjectivesTo investigate the value of CT-based radiomics analysis in preoperatively discriminating pancreatic mucinous cystic neoplasms (MCN) and atypical serous cystadenomas (ASCN).MethodsA total of 103 MCN and 113 ASCN patients who underwent surgery were retrospectively enrolled. A total of 764 radiomics features were extracted from preoperative CT images. The optimal features were selected by Mann-Whitney U test and minimum redundancy and maximum relevance method. The radiomics score (Rad-score) was then built using random forest algorithm. Radiological/clinical features were also assessed for each patient. Multivariable logistic regression was used to construct a radiological model. The performance of the Rad-score and the radiological model was evaluated using 10-fold cross-validation for area under the curve (AUC), sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and accuracy.ResultsTen screened optimal features were identified and the Rad-score was then built based on them. The radiological model was built based on four radiological/clinical factors. In the 10-fold cross-validation, the Rad-score was proved to be robust and reliable (average AUC: 0.784, sensitivity: 0.847, specificity: 0.745, PPV: 0.767, NPV: 0.849, accuracy: 0.793). The radiological model performed slightly less well in classification (average AUC: average AUC: 0.734 sensitivity: 0.748, specificity: 0.705, PPV: 0.732, NPV: 0.798, accuracy: 0.728.ConclusionsThe CT-based radiomics analysis provided promising performance for preoperatively discriminating MCN from ASCN and showed good potential in improving diagnostic power, which may serve as a novel tool for guiding clinical decision-making for these patients.

Sign in / Sign up

Export Citation Format

Share Document