An explainable Artificial Intelligence approach to study MCI to AD conversion via HD-EEG processing

2021 ◽  
pp. 155005942110636
Author(s):  
Francesco Carlo Morabito ◽  
Cosimo Ieracitano ◽  
Nadia Mammone
Keyword(s):  
Artificial Intelligence ◽  
Frontal Lobe ◽  
Parietal Lobe ◽  
Classification Performance ◽  
Head Region ◽  
Left Frontal Lobe ◽  
Performance Accuracy ◽  
Power Spectral ◽  
Explainable Artificial Intelligence

An explainable Artificial Intelligence (xAI) approach is proposed to longitudinally monitor subjects affected by Mild Cognitive Impairment (MCI) by using high-density electroencephalography (HD-EEG). To this end, a group of MCI patients was enrolled at IRCCS Centro Neurolesi Bonino Pulejo of Messina (Italy) within a follow-up protocol that included two evaluations steps: T0 (first evaluation) and T1 (three months later). At T1, four MCI patients resulted converted to Alzheimer’s Disease (AD) and were included in the analysis as the goal of this work was to use xAI to detect individual changes in EEGs possibly related to the degeneration from MCI to AD. The proposed methodology consists in mapping segments of HD-EEG into channel-frequency maps by means of the power spectral density. Such maps are used as input to a Convolutional Neural Network (CNN), trained to label the maps as “T0” (MCI state) or “T1” (AD state). Experimental results reported high intra-subject classification performance (accuracy rate up to 98.97% (95% confidence interval: 98.68–99.26)). Subsequently, the explainability of the proposed CNN is explored via a Grad-CAM approach. The procedure allowed to detect which EEG-channels (i.e., head region) and range of frequencies (i.e., sub-bands) resulted more active in the progression to AD. The xAI analysis showed that the main information is included in the delta sub-band and that, limited to the analyzed dataset, the highest relevant areas are: the left-temporal and central-frontal lobe for Sb01, the parietal lobe for Sb02, the left-frontal lobe for Sb03 and the left-frontotemporal region for Sb04.

Post-Stimulation Effect of Electroacupuncture at Yintang (EX-HN3) and GV20 on cerebral functional regions in healthy volunteers: A resting functional MRI study

2012 ◽  
Vol 30 (4) ◽  
pp. 307-315 ◽  
Author(s):  
Yu Zheng ◽  
Shanshan Qu ◽  
Na Wang ◽  
Limin Liu ◽  
Guanzhong Zhang ◽  
...  
Keyword(s):  
Frontal Lobe ◽  
Temporal Lobe ◽  
Parietal Lobe ◽  
Occipital Lobe ◽  
Cingulate Gyrus ◽  
Left Frontal Lobe ◽  
Posterior Cingulate Gyrus ◽  
Functional Regions ◽  
Limbic Lobe ◽  
The Right

Objective The aim of the present work was to observe the activation/deactivation of cerebral functional regions after electroacupuncture (EA) at Yintang (EX-HN3) and GV20 by functional MRI (fMRI). Design A total of 12 healthy volunteers were stimulated by EA at Yintang and GV20 for 30 min. Resting-state fMRI scans were performed before EA, and at 5 and 15 min after needle removal. Statistical parametric mapping was used to preprocess initial data, and regional homogeneity (ReHo) and amplitude of low-frequency fluctuation (ALFF) were analysed. Results ReHo at 5 min post stimulation showed increases in the left temporal lobe and cerebellum and decreases in the left parietal lobe, occipital lobe and right precuneus. At 15 min post stimulation, ReHo showed increases in the left fusiform gyrus; lingual gyrus; middle temporal gyrus; postcentral gyrus; limbic lobe; cingulate gyrus; paracentral lobule; cerebellum, posterior lobe, declive; right cuneus and cerebellum, anterior lobe, culmen. It also showed decreases in the left frontal lobe, parietal lobe, right temporal lobe, frontal lobe, parietal lobe and right cingulate gyrus. ALFF at 5 min post stimulation showed increases in the right temporal lobe, but decreases in the right limbic lobe and posterior cingulate gyrus. At 15 min post stimulation ALFF showed increases in the left frontal lobe, parietal lobe, occipital lobe, right temporal lobe, parietal lobe, occipital lobe and cerebellum, but decreases in the left frontal lobe, anterior cingulate gyrus, right frontal lobe and posterior cingulate gyrus. Conclusions After EA stimulation at Yintang and GV20, which are associated with psychiatric disorder treatments, changes were localised in the frontal lobe, cingulate gyrus and cerebellum. Changes were higher in number and intensity at 15 min than at 5 min after needle removal, demonstrating lasting and strong after-effects of EA on cerebral functional regions.

scholarly journals Case Report: Unusual Clinical Presentation of a Rare Cardiac Inflammatory Myofibroblastic Tumor in Children: The Differential Diagnosis With Pediatric Emergencies

2021 ◽  
Vol 9 ◽  
Author(s):  
Clio Bilotta ◽  
Giulio Perrone ◽  
Emiliano Maresi ◽  
Giovanni De Lisi ◽  
Pietro Di Pasquale ◽  
...  
Keyword(s):  
Differential Diagnosis ◽  
Frontal Lobe ◽  
Inflammatory Myofibroblastic Tumor ◽  
Parietal Lobe ◽  
Treatment Protocol ◽  
Immunohistochemical Analysis ◽  
Scientific Data ◽  
Left Frontal Lobe ◽  
Rare Type ◽  
Motor Delay

Introduction: There are still no guidelines about pediatric cardiac cancers. The purpose of this work is to provide new scientific data facilitating the differential diagnosis of a rare cardiac tumor with an unusual presentation, such as the cardiac inflammatory myofibroblastic tumor (IMT).Case Presentation: A 3-year-old male child presented with several symptoms including unconsciousness, vomiting, and drowsiness. A clinical and neurological examination revealed a unilateral (right) motor delay and positive unilateral Babinski sign. Electrocardiogram (ECG) was normal.Diagnostic Assessment: The total body computed tomography (CT) scans showed hypodensity in the left temporal–parietal lobe, a large hypodense area in the right frontal lobe, and a second area in the left frontal lobe were found with head CT. A magnetic resonance (MR) also noted cerebral areas of hypointensity. The echocardiographic images revealed an ovoid mass, adherent to the anterolateral papillary muscle. The histological exams, performed with hematoxylin–eosin, Masson's trichrome, Alcian blue PAS, Weigert and Van-Gieson stain, allowed observing the microscopic structure of the neoplastic mass. The immunohistochemical analysis was performed through subsequent antibodies: anti-vimentin, anti-actina, anti-ALK, anti-CD8, anti-CD3, anti-CD20, anti-kappa and lambda chains, and anti CD68 antibodies. The healthcare professionals diagnosed a cardiac IMT with brain embolism.Differential Diagnosis: The ventricular localization, observed through radiological exams, required a differential diagnosis with fibroma and rhabdomyoma, the presence of brain embolism with sarcoma, and its morphology with fibroma. Neurological symptoms might be attributed to encephalitis, primitive cerebral cancer, such as astrocytoma or neuroblastoma, cerebral metastases due to any malignancy, or embolic stroke.Conclusion: New studies are encouraged to better define IMT behavior and draw up guidelines confirming the crucial role of multidisciplinary approach and treatment protocol selected on the basis of the characteristics of the tumors, in the case of this rare type of cancer.

scholarly journals Clinicoradiological Features and Treatment Outcome of Supratentorial Intraparenchymal Epidermoid Cyst: A Report of Five Cases and Literature Review

2021 ◽  
Author(s):  
Ashutosh Kumar ◽  
Ved Prakash Maurya ◽  
Soumen Kanjilal ◽  
Kamlesh Singh Bhaisora ◽  
Jayesh Sardhara ◽  
...  
Keyword(s):  
Frontal Lobe ◽  
Parietal Lobe ◽  
Case Reports ◽  
Neurological Deficits ◽  
Seizure Freedom ◽  
Complete Excision ◽  
Epidermoid Cysts ◽  
Complete Surgical Excision ◽  
Intracranial Epidermoid

Abstract Objectives Intraparenchymal epidermoid cysts (IECs) are rare lesions. They represent less than 1% of the intracranial epidermoid cysts. The supratentorial IEC is a clinically and prognostically distinct subset. Given the rarity, most of the articles are case reports. We present a series of five cases of supratentorial IEC to characterize their clinical presentation and outcome, with emphasis on the surgical features. Materials and Methods We searched our database for all cases of intracranial epidermoid cysts operated between January 2005 and January 2020. Five patients were identified having IEC from the hospital information system and the neurosurgical operation record book. Standard craniotomy and decompression of the lesion were performed in all these patients. Standard postoperative care includes computed tomography scan of head on the day of surgery and magnetic resonance imaging of brain after 6 weeks to look for the residual lesion, if any. Subsequent follow-up visits in outpatient department to look for resolution of the presurgical symptoms. Results The mean age of the patients in our series was 28.8 years (range: 28–40 years.). All the five patients were male. Four patients had IEC involving frontal lobe and one in parietal lobe with a small occipital lobe extension. Seizure was the most common presenting complaint followed by headache. Complete excision was achieved in all the cases. All the three patients with seizure attained seizure freedom postlesionectomy. Focal neurological deficits resolved gradually in postoperative period. There was no recurrence of lesion during follow-up. Conclusion Supratentorial IEC most commonly affects young males, involve frontal lobe and present clinically with seizure. Complete surgical excision offers best outcome in the form of remission of seizure disorder.

XHAC

2022 ◽  
pp. 146-164
Author(s):  
Duygu Bagci Das ◽  
Derya Birant
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Internet Of Things ◽  
Window Size ◽  
Classification Performance ◽  
Black Box ◽  
Data Exploration ◽  
Learning Models ◽  
Explainable Artificial Intelligence ◽  
Machine Learning Models

Explainable artificial intelligence (XAI) is a concept that has emerged and become popular in recent years. Even interpretation in machine learning models has been drawing attention. Human activity classification (HAC) systems still lack interpretable approaches. In this study, an approach, called eXplainable HAC (XHAC), was proposed in which the data exploration, model structure explanation, and prediction explanation of the ML classifiers for HAR were examined to improve the explainability of the HAR models' components such as sensor types and their locations. For this purpose, various internet of things (IoT) sensors were considered individually, including accelerometer, gyroscope, and magnetometer. The location of these sensors (i.e., ankle, arm, and chest) was also taken into account. The important features were explored. In addition, the effect of the window size on the classification performance was investigated. According to the obtained results, the proposed approach makes the HAC processes more explainable compared to the black-box ML techniques.

scholarly journals Explainable artificial intelligence for predicting remission in patients with rheumatoid arthritis treated with biologics

2021 ◽  
Author(s):  
Bon San Koo ◽  
Seongho Eun ◽  
Kichul Shin ◽  
Hyemin Yoon ◽  
Chaelin Hong ◽  
...  
Keyword(s):  
Rheumatoid Arthritis ◽  
Artificial Intelligence ◽  
Machine Learning ◽  
Clinical Features ◽  
Clinical Information ◽  
Learning Model ◽  
Support Vector ◽  
Machine Learning Model ◽  
Explainable Artificial Intelligence

Abstract Background: We developed a model to predict remissions in patients treated with biologic disease-modifying anti-rheumatic drugs (bDMARDs) and to identify important clinical features associated with remission using explainable artificial intelligence (XAI).Methods: We gathered the follow-up data of 1204 patients treated with bDMARDs (etanercept, adalimumab, golimumab, infliximab, abatacept, and tocilizumab) from the Korean College of Rheumatology Biologics and Targeted Therapy Registry. Remission was predicted at one-year follow-up using baseline clinical data obtained at the time of enrollment. Machine learning methods (e.g., lasso, ridge, support vector machine, random forest, and XGBoost) were used for the predictions. The Shapley additive explanation (SHAP) value was used for interpretability of the predictions.Results: The ranges for accuracy and area under the receiver operating characteristic of the newly developed machine learning model for predicting remission were 52.8%–72.9% and 0.511–0.694, respectively. The Shapley plot in XAI showed that the impacts of the variables on predicting remission differed for each bDMARD. The most important features were age for adalimumab, rheumatoid factor for etanercept, erythrocyte sedimentation rate for infliximab and golimumab, disease duration for abatacept, and C-reactive protein for tocilizumab, with mean SHAP values of -0.250, -0.234, -0.514, -0.227, -0.804, and 0.135, respectively.Conclusions: Our proposed machine learning model successfully identified clinical features that were predictive of remission in each of the bDMARDs. This approach may be useful for improving treatment outcomes by identifying clinical information related to remissions in patients with rheumatoid arthritis.

The association of artificial intelligence-enabled electrocardiogram-derived age (physiologic age) with atherosclerotic cardiovascular events in the community

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
J Medina-Inojosa ◽  
A Ladejobi ◽  
Z Attia ◽  
M Shelly-Cohen ◽  
B Gersh ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Bypass Graft ◽  
P Value ◽  
Funding Source ◽  
Atherosclerotic Cardiovascular Disease ◽  
Age Gap ◽  
Predicted Risk ◽  
Age And Sex

Abstract Background We have demonstrated that artificial intelligence interpretation of ECGs (AI-ECG) can estimate an individual's physiologic age and that the gap between AI-ECG and chronologic age (Age-Gap) is associated with increased mortality. We hypothesized that Age-Gap would predict long-term atherosclerotic cardiovascular disease (ASCVD) and that Age-Gap would refine the ACC/AHA Pooled Cohort Equations' (PCE) predictive abilities. Methods Using the Rochester Epidemiology Project (REP) we evaluated a community-based cohort of consecutive patients seeking primary care between 1998–2000 and followed through March 2016. Inclusion criteria were age 40–79 and complete data to calculate PCE. We excluded those with known ASCVD, AF, HF or an event within 30 days of baseline.A neural network, trained, validated, and tested in an independent cohort of ∼ 500,000 independent patients, using 10-second digital samples of raw, 12 lead ECGs. PCE was categorized as low<5%, intermediate 5–9.9%, high 10–19.9%, and very high≥20%. The primary endpoint was ASCVD and included fatal and non-fatal myocardial infarction and ischemic stroke; the secondary endpoint also included coronary revascularization [Percutaneous Coronary Intervention (PCI) or Coronary Artery Bypass Graft (CABG)], TIA and Cardiovascular mortality. Events were validated in duplicate. Follow-up was truncated at 10 years for PCE analysis. The association between Age-Gap with ASCVD and expanded ASCVD was assessed with cox proportional hazard models that adjusted for chronological age, sex and risk factors. Models were stratified by PCE risk categories to evaluate the effect of PCE predicted risk. Results We included 24,793 patients (54% women, 95% Caucasian) with mean follow up of 12.6±5.1 years. 2,366 (9.5%) developed ASCVD events and 3,401 (13.7%) the expanded ASCVD. Mean chronologic age was 53.6±11.6 years and the AI-ECG age was 54.5±10.9 years, R2=0.7865, p<0.0001. The mean Age-Gap was 0.87±7.38 years. After adjusting for age and sex, those considered older by ECG, compared to their chronologic age had a higher risk for ASCVD when compared to those with <−2 SD age gap (considered younger by ECG). (Figure 1A), with similar results when using the expanded definition of ASCVD (data not shown). Furthermore, Age-Gap enhanced predicted capabilities of the PCE among those with low 10-year predicted risk (<5%): Age and sex adjusted HR 4.73, 95% CI 1.42–15.74, p-value=0.01 and among those with high predicted risk (>20%) age and sex adjusted HR 6.90, 95% CI 1.98–24.08, p-value=0.0006, when comparing those older to younger by ECG respectively (Figure 1B). Conclusion The difference between physiologic AI-ECG age and chronologic age is associated with long-term ASCVD, and enhances current risk calculators (PCE) ability to identify high and low risk individuals. This may help identify individuals who should or should not be treated with newer, expensive risk-reducing therapies. Funding Acknowledgement Type of funding source: Foundation. Main funding source(s): Mayo Clinic

Sign in / Sign up

Export Citation Format

Share Document