Deep Learning-based Prediction of Cognitive Function Using Basic Blood Test Data and NIRS-measured Cerebral Hemodynamics

2021 ◽  
Author(s):  
Katsunori Oyama ◽  
Kaoru Sakatani
Keyword(s):  
Deep Learning ◽  
Cognitive Function ◽  
Test Data ◽  
Blood Test ◽  
Cerebral Hemodynamics

scholarly journals Deep Learning-Based Screening Test for Cognitive Impairment Using Basic Blood Test Data for Health Examination

2020 ◽  
Vol 11 ◽  
Author(s):  
Kaoru Sakatani ◽  
Katsunori Oyama ◽  
Lizhen Hu
Keyword(s):  
Deep Learning ◽  
Cognitive Impairment ◽  
Cognitive Function ◽  
Patient Group ◽  
Screening Test ◽  
Blood Test ◽  
Metabolic Disorders ◽  
Ground Truth ◽  
Health Examination ◽  
Healthy Group

Background: In order to develop a new screening test of cognitive impairment, we studied whether cognitive function can be estimated from basic blood test data by applying deep learning models. This model was constructed based on the effects of systemic metabolic disorders on cognitive function.Methods: We employed a deep neural network (DNN) to predict cognitive function based on subject's age and blood test items (23 items). We included 202 patients (73.48 ± 13.1 years) with various systemic metabolic disorders for training of the DNN model, and the following groups for validation of the model: (1) Patient group, 65 patients (73.6 ± 11.0 years) who were hospitalized for rehabilitation after stroke; (2) Healthy group, 37 subjects (62.0 ± 8.6 years); (3) Health examination group, 165 subjects (54.0 ± 8.6 years) admitted for a health examination. The subjects underwent the Mini-Mental State Examination (MMSE).Results: There were significant positive correlations between the predicted MMSE scores and ground truth scores in the Patient and Healthy groups (r = 0.66, p < 0.001). There were no significant differences between the predicted MMSE scores and ground truth scores in the Patient group (p > 0.05); however, in the Healthy group, the predicted MMSE scores were slightly, but significantly, lower than the ground truth scores (p < 0.05). In the Health examination group, the DNN model classified 94 subjects as normal (MMSE = 27–30), 67 subjects as having mild cognitive impairment (24–26), and four subjects as having dementia (≤ 23). In 37 subjects in the Health examination group, the predicted MMSE scores were slightly lower than the ground truth MMSE (p < 0.05). In contrast, in the subjects with neurological disorders, such as subarachnoid hemorrhage, the ground truth MMSE scores were lower than the predicted scores.Conclusions: The DNN model could predict cognitive function accurately. The predicted MMSE scores were significantly lower than the ground truth scores in the Healthy and Health examination groups, while there was no significant difference in the Patient group. We suggest that the difference between the predicted and ground truth MMSE scores was caused by changes in atherosclerosis with aging, and that applying the DNN model to younger subjects may predict future cognitive impairment after the onset of atherosclerosis.

Prediction of Recurrence in Patients with Stage III Colon Cancer Using Conventional Clinicopathological Factors and Peripheral Blood Test Data: A New Analysis with Artificial Intelligence

Oncology ◽  
2021 ◽  
Vol 99 (5) ◽  
pp. 318-326
Author(s):  
Yutaro Kamei ◽  
Tetsuro Takayama ◽  
Toshiyuki Suzuki ◽  
Kenichi Furihata ◽  
Megumi Otsuki ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Colon Cancer ◽  
Serum Albumin ◽  
Test Data ◽  
Predictive Factors ◽  
Blood Test ◽  
Stage Iii ◽  
Clinicopathological Factors ◽  
Stage Iii Colon Cancer ◽  
Staging Systems

Background: Survival rate may be predicted by tumor-node-metastasis staging systems in colon cancer. In clinical practice, about 20 to 30 clinicopathological factors and blood test data have been used. Various predictive factors for recurrence have been advocated; however, the interactions are complex and remain to be established. We used artificial intelligence (AI) to examine predictive factors related to recurrence. Methods: The study group comprised 217 patients who underwent curative surgery for stage III colon cancer. Using a self-organizing map (SOM), an AI-based method, patients with only 23 clinicopathological factors, patients with 23 clinicopathological factors and 34 of preoperative blood test data (pre-data), and those with 23 clinicopathological factors and 31 of postoperative blood test data (post-data) were classified into several clusters with various rates of recurrence. Results: When only clinicopathological factors were used, the percentage of T4b disease, the percentage of N2 disease, and the number of metastatic lymph nodes were significantly higher in a cluster with a higher rate of recurrence. When clinicopathological factors and pre-data were used, three described pathological factors and the serum C-reactive protein (CRP) levels were significantly higher and the serum total protein (TP) levels, serum albumin levels, and the percentage of lymphocytes were significantly lower in a cluster with a higher rate of recurrence. When clinicopathological factors and post-data were used, three described pathological factors, serum CRP levels, and serum carcinoembryonic antigen levels were significantly higher and serum TP levels, serum albumin levels, and the percentage of lymphocytes were significantly lower in a cluster with a higher rate of recurrence. Conclusions: This AI-based analysis extracted several risk factors for recurrence from more than 50 pathological and blood test factors before and after surgery separately. This analysis may predict the risk of recurrence of a new patient by confirming which clusters this patient belongs to.

CancerEMC: frontline non-invasive cancer screening from circulating protein biomarkers and mutations in cell-free DNA

2021 ◽  
Author(s):  
Saifur Rahaman ◽  
Xiangtao Li ◽  
Jun Yu ◽  
Ka-Chun Wong
Keyword(s):  
Test Data ◽  
Cancer Detection ◽  
Blood Test ◽  
Class Imbalance ◽  
Cancer Type ◽  
Protein Biomarkers ◽  
Class Imbalance Problem ◽  
Multiple Cancer ◽  
Cell Free Dna ◽  
Free Dna

Abstract Motivation The early detection of cancer through accessible blood tests can foster early patient interventions. Although there are developments in cancer detection from cell-free DNA (cfDNA), its accuracy remains speculative. Given its central importance with broad impacts, we aspire to address the challenge. Methods A bagging Ensemble Meta Classifier (CancerEMC) is proposed for early cancer detection based on circulating protein biomarkers and mutations in cfDNA from the blood. CancerEMC is generally designed for both binary cancer detection and multi-class cancer type localization. It can address the class imbalance problem in multi-analyte blood test data based on robust oversampling and adaptive synthesis techniques. Results Based on the clinical blood test data, we observe that the proposed CancerEMC has outperformed other algorithms and state-of-the-arts studies (including CancerSEEK published in Science, 2018) for cancer detection. The results reveal that our proposed method (i.e., CancerEMC) can achieve the best performance result for both binary cancer classification with 99.1748% accuracy (AUC = 0.999) and localized multiple cancer detection with 74.1214% accuracy (AUC = 0.938). For addressing the data imbalance issue with oversampling techniques, the accuracy can be increased to 91.4966% (AUC = 0.992), where the state-of-the-art method can only be estimated at 69.64% (AUC = 0.921). Similar results can also be observed on independent and isolated testing data. Availability https://github.com/saifurcubd/Cancer-Detection

scholarly journals Deep Learning Using Multiple Degrees of Maximum-Intensity Projection for PET/CT Image Classification in Breast Cancer

Tomography ◽  
2022 ◽  
Vol 8 (1) ◽  
pp. 131-141
Author(s):  
Kanae Takahashi ◽  
Tomoyuki Fujioka ◽  
Jun Oyama ◽  
Mio Mori ◽  
Emi Yamaga ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Deep Learning ◽  
Image Classification ◽  
Test Data ◽  
Characteristic Curve ◽  
Maximum Intensity Projection ◽  
Maximum Intensity ◽  
Training Data ◽  
Ct Image ◽  
Pet Ct

Deep learning (DL) has become a remarkably powerful tool for image processing recently. However, the usefulness of DL in positron emission tomography (PET)/computed tomography (CT) for breast cancer (BC) has been insufficiently studied. This study investigated whether a DL model using images with multiple degrees of PET maximum-intensity projection (MIP) images contributes to increase diagnostic accuracy for PET/CT image classification in BC. We retrospectively gathered 400 images of 200 BC and 200 non-BC patients for training data. For each image, we obtained PET MIP images with four different degrees (0°, 30°, 60°, 90°) and made two DL models using Xception. One DL model diagnosed BC with only 0-degree MIP and the other used four different degrees. After training phases, our DL models analyzed test data including 50 BC and 50 non-BC patients. Five radiologists interpreted these test data. Sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were calculated. Our 4-degree model, 0-degree model, and radiologists had a sensitivity of 96%, 82%, and 80–98% and a specificity of 80%, 88%, and 76–92%, respectively. Our 4-degree model had equal or better diagnostic performance compared with that of the radiologists (AUC = 0.936 and 0.872–0.967, p = 0.036–0.405). A DL model similar to our 4-degree model may lead to help radiologists in their diagnostic work in the future.

Effect of the Fungus Isaria japonica from the Silkworm on Cognitive Function in Older Adults with Mild Cognitive Decline: A Pilot Study

2021 ◽  
Vol 19 (4) ◽  
pp. 383-387
Author(s):  
Daisuke Furushima ◽  
Yuri Takashima ◽  
Toshiji Miyagawa ◽  
Hiroshi Fujita ◽  
Yuzuki Nomura ◽  
...  
Keyword(s):  
Older Adults ◽  
Cognitive Function ◽  
Cognitive Decline ◽  
Blood Test ◽  
Mmse Score ◽  
Protective Role ◽  
In Vivo Studies ◽  
Serious Adverse Events ◽  
Silkworm Pupae

Several in vivo studies report that the fungus Isaria japonica grown on silkworm pupae, classified as a Cordycipitaceae, plays a role in preventing memory deficits and may have a protective role against cognitive impairment. The present study investigated the cognitive effects and safety of I. japonica in older adults with mild cognitive decline. Intervention trial was conducted in subjects over 60 years of age with mild cognitive decline (Mini-Mental State Examination [MMSE] score: 20-27). The subjects consumed the I. japonica supplements twice per day for 12 weeks. The outcome measures included the MMSE score and blood test values before and after the intervention. A total of 25 subjects (aged 64-94 years) were eligible for the study. After the intervention, the MMSE score (mean ± standard deviation) significantly increased from 25.5 ± 1.6 to 27.1 ± 2.4 (P < 0.0001). The blood test revealed no change in any of the hematological and biochemical parameters evaluated. Also, no serious adverse events were reported. Despite several limitations in the study design, the findings of the present study suggest that the fungus I. japonica is safe to consume and it may improve cognitive function in older adults with mild cognitive decline.

scholarly journals Neural network activation similarity: a new measure to assist decision making in chemical toxicology

2020 ◽  
Vol 11 (28) ◽  
pp. 7335-7348 ◽  
Author(s):  
Timothy E. H. Allen ◽  
Andrew J. Wedlake ◽  
Elena Gelžinytė ◽  
Charles Gong ◽  
Jonathan M. Goodman ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Decision Making ◽  
Deep Learning ◽  
Test Data ◽  
High Performance ◽  
Chemical Binding ◽  
Biological Targets ◽  
Network Activation ◽  
Chemical Toxicology

Deep learning neural networks, constructed for the prediction of chemical binding at 79 pharmacologically important human biological targets, show extremely high performance on test data (accuracy 92.2 ± 4.2%, MCC 0.814 ± 0.093, ROC-AUC 0.96 ± 0.04).

scholarly journals A Framework Based on Nesting of Convolutional Neural Networks to Classify Secondary Roads in High Resolution Aerial Orthoimages

2020 ◽  
Vol 12 (5) ◽  
pp. 765 ◽  
Author(s):  
Calimanut-Ionut Cira ◽  
Ramon Alcarria ◽  
Miguel-Ángel Manso-Callejo ◽  
Francisco Serradilla
Keyword(s):  
Remote Sensing ◽  
Neural Networks ◽  
Deep Learning ◽  
High Resolution ◽  
Learning Strategies ◽  
Convolutional Neural Networks ◽  
Test Data ◽  
Road Network ◽  
Ideal Solution ◽  
The Road

Remote sensing imagery combined with deep learning strategies is often regarded as an ideal solution for interpreting scenes and monitoring infrastructures with remarkable performance levels. In addition, the road network plays an important part in transportation, and currently one of the main related challenges is detecting and monitoring the occurring changes in order to update the existent cartography. This task is challenging due to the nature of the object (continuous and often with no clearly defined borders) and the nature of remotely sensed images (noise, obstructions). In this paper, we propose a novel framework based on convolutional neural networks (CNNs) to classify secondary roads in high-resolution aerial orthoimages divided in tiles of 256 × 256 pixels. We will evaluate the framework’s performance on unseen test data and compare the results with those obtained by other popular CNNs trained from scratch.

scholarly journals An Augmented Model with Inferred Blood Features for the Self-diagnosis of Metabolic Syndrome

2020 ◽  
Vol 59 (01) ◽  
pp. 018-030
Author(s):  
Tianshu Zhou ◽  
Ying Zhang ◽  
Chengkai Wu ◽  
Chao Shen ◽  
Jingsong Li ◽  
...  
Keyword(s):  
Metabolic Syndrome ◽  
Test Data ◽  
Classification Accuracy ◽  
Blood Test ◽  
Health Management ◽  
Fasting Blood Glucose ◽  
Density Lipoprotein ◽  
Developed Countries ◽  
The Third ◽  
Health Checks

Abstract Background and Objectives The penetration rate of physical examinations in China is substantially lower than that in developed countries. Therefore, an auxiliary approach that does not depend on hospital health checks for the diagnosis of metabolic syndrome (MetS) is needed. Methods In this study, we proposed an augmented method with inferred blood features that uses self-care inputs available at home for the auxiliary diagnosis of MetS. The dataset used for modeling contained data on 91,420 individuals who had at least 2 consecutive years of health checks. We trained three separate models using a regularized gradient-boosted decision tree. The first model used only home-based features; additional blood test data (including triglyceride [TG] data, fasting blood glucose data, and high-density lipoprotein cholesterol [HDL-C] data) were included in the second model. However, in the augmented approach, the blood test data were manipulated using multivariate imputation by chained equations prior to inclusion in the third model. The performance of the three models for MetS auxiliary diagnosis was then quantitatively compared. Results The results showed that the third model exhibited the highest classification accuracy for MetS in comparison with the other two models (area under the curve [AUC]: 3rd vs. 2nd vs. 1st = 0.971 vs. 0.950 vs. 0.905, p < 0.001). We further revealed that with full sets of the three measurements from earlier blood test data, the classification accuracy of MetS can be further improved (AUC: without vs. with = 0.971 vs. 0.993). However, the magnitude of improvement was not statistically significant at the 1% level of significance (p = 0.014). Conclusion Our findings demonstrate the feasibility of the third model for MetS homecare applications and lend novel insights into innovative research on the health management of MetS. Further validation and implementation of our proposed model might improve quality of life and ultimately benefit the general population.

Diagnostic assessment of a deep learning system for detecting atrial fibrillation in pulse waveforms

Heart ◽  
2018 ◽  
Vol 104 (23) ◽  
pp. 1921-1928 ◽  
Author(s):  
Ming-Zher Poh ◽  
Yukkee Cheung Poh ◽  
Pak-Hei Chan ◽  
Chun-Ka Wong ◽  
Louise Pun ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Deep Learning ◽  
Test Data ◽  
Predictive Value ◽  
Characteristic Curve ◽  
Performance Comparison ◽  
Learning System ◽  
Training Data ◽  
Validation Data ◽  
Data Set

ObjectiveTo evaluate the diagnostic performance of a deep learning system for automated detection of atrial fibrillation (AF) in photoplethysmographic (PPG) pulse waveforms.MethodsWe trained a deep convolutional neural network (DCNN) to detect AF in 17 s PPG waveforms using a training data set of 149 048 PPG waveforms constructed from several publicly available PPG databases. The DCNN was validated using an independent test data set of 3039 smartphone-acquired PPG waveforms from adults at high risk of AF at a general outpatient clinic against ECG tracings reviewed by two cardiologists. Six established AF detectors based on handcrafted features were evaluated on the same test data set for performance comparison.ResultsIn the validation data set (3039 PPG waveforms) consisting of three sequential PPG waveforms from 1013 participants (mean (SD) age, 68.4 (12.2) years; 46.8% men), the prevalence of AF was 2.8%. The area under the receiver operating characteristic curve (AUC) of the DCNN for AF detection was 0.997 (95% CI 0.996 to 0.999) and was significantly higher than all the other AF detectors (AUC range: 0.924–0.985). The sensitivity of the DCNN was 95.2% (95% CI 88.3% to 98.7%), specificity was 99.0% (95% CI 98.6% to 99.3%), positive predictive value (PPV) was 72.7% (95% CI 65.1% to 79.3%) and negative predictive value (NPV) was 99.9% (95% CI 99.7% to 100%) using a single 17 s PPG waveform. Using the three sequential PPG waveforms in combination (<1 min in total), the sensitivity was 100.0% (95% CI 87.7% to 100%), specificity was 99.6% (95% CI 99.0% to 99.9%), PPV was 87.5% (95% CI 72.5% to 94.9%) and NPV was 100% (95% CI 99.4% to 100%).ConclusionsIn this evaluation of PPG waveforms from adults screened for AF in a real-world primary care setting, the DCNN had high sensitivity, specificity, PPV and NPV for detecting AF, outperforming other state-of-the-art methods based on handcrafted features.

Sign in / Sign up

Export Citation Format

Share Document