scholarly journals A multimodal AI system for out-of-distribution generalization of seizure detection

2021 ◽  
Author(s):  
Yikai Yang ◽  
Nhan Duy Truong ◽  
Jason K. Eshraghian ◽  
Christina Maher ◽  
Armin Nikpour ◽  
...  
Keyword(s):  
State Of The Art ◽  
Characteristic Curve ◽  
Cost Effective ◽  
Seizure Detection ◽  
University Hospital ◽  
Patient Specific ◽  
Brain Disorder ◽  
Unprovoked Seizure ◽  
Temple University ◽  
Scalp Electroencephalogram

Epilepsy is one of the most common severe neurological disorders worldwide. The International League Against Epilepsy (ILAE) define epilepsy as a brain disorder that generates (1) two unprovoked seizures more than 24 hrs apart, or (2) one unprovoked seizure with at least 60% risk of recurrence over the next ten years. Complete remission has been defined as ten years seizure free with the last five years medication free. This requires a cost-effective ambulatory ultra-long term out-patient monitoring solution. The common practice of self-reporting is inaccurate. Applying artificial intelligence (AI) to scalp electroencephalogram (EEG) interpretation is becoming increasingly common, but other data modalities such as electrocardiograms (ECGs) are simpler to collect and often recorded simultaneously with EEG. Both recordings contain biomarkers in the detection of seizures. Here, we propose a state-of-the-art performing AI system that combines EEG and ECG for seizure detection, tested on clinical data with early evidence demonstrating generalization across hospitals. The model was trained and validated on the publicly available Temple University Hospital (TUH) dataset. To evaluate performance in a clinical setting, we conducted non-patient-specific inference-only tests on three out-of-distribution datasets, including EPILEPSIAE (30 patients) and the Royal Prince Alfred Hospital (RPAH) in Sydney, Australia (31 patients shortlisted by neurologists and 30 randomly selected). Across all datasets, our multimodal approach improves the area under the receiver operating characteristic curve (AUC-ROC) by an average margin of 6.71% and 14.42% for prior state-of-the-art approaches using EEG and ECG alone, respectively. Our model's state-of-the-art performance and robustness to out-of-distribution datasets can improve the accuracy and efficiency of epilepsy diagnoses.

scholarly journals The Temple University Hospital Seizure Detection Corpus

2018 ◽  
Vol 12 ◽  
Author(s):  
Vinit Shah ◽  
Eva von Weltin ◽  
Silvia Lopez ◽  
James Riley McHugh ◽  
Lillian Veloso ◽  
...  
Keyword(s):  
Seizure Detection ◽  
University Hospital ◽  
Temple University ◽  
The Temple

scholarly journals Patient-Specific Early Seizure Detection From Scalp Electroencephalogram

2010 ◽  
Vol 27 (3) ◽  
pp. 163-178 ◽  
Author(s):  
Georgiy R. Minasyan ◽  
John B. Chatten ◽  
Martha J. Chatten ◽  
Richard N. Harner
Keyword(s):  
Seizure Detection ◽  
Patient Specific ◽  
Scalp Electroencephalogram ◽  
Early Seizure

scholarly journals Online EEG Seizure Detection and Localization

Algorithms ◽  
2019 ◽  
Vol 12 (9) ◽  
pp. 176
Author(s):  
Amirsalar Mansouri ◽  
Sanjay P. Singh ◽  
Khalid Sayood
Keyword(s):  
Significant Proportion ◽  
Cost Effective ◽  
Seizure Detection ◽  
Detection Algorithm ◽  
Patient Specific ◽  
Specific Method ◽  
Eeg Signals ◽  
Spectral Profiles ◽  
Detection And Localization ◽  
The Brain

Epilepsy is one of the three most prevalent neurological disorders. A significant proportion of patients suffering from epilepsy can be effectively treated if their seizures are detected in a timely manner. However, detection of most seizures requires the attention of trained neurologists—a scarce resource. Therefore, there is a need for an automatic seizure detection capability. A tunable non-patient-specific, non-seizure-specific method is proposed to detect the presence and locality of a seizure using electroencephalography (EEG) signals. This multifaceted computational approach is based on a network model of the brain and a distance metric based on the spectral profiles of EEG signals. This computationally time-efficient and cost-effective automated epileptic seizure detection algorithm has a median latency of 8 s, a median sensitivity of 83%, and a median false alarm rate of 2.9%. Hence, it is capable of being used in portable EEG devices to aid in the process of detecting and monitoring epileptic patients.

scholarly journals Development of a prediction model for 30-day acute readmissions among older medical patients: the influence of social factors along with other patient-specific and organisational factors

2019 ◽  
Vol 8 (2) ◽  
pp. e000544 ◽  
Author(s):  
Sara Fokdal Lehn ◽  
Ann-Dorthe Zwisler ◽  
Solvejg Gram Henneberg Pedersen ◽  
Thomas Gjørup ◽  
Lau Caspar Thygesen
Keyword(s):  
Social Factors ◽  
Educational Level ◽  
Characteristic Curve ◽  
University Hospital ◽  
Patient Specific ◽  
Charlson Comorbidity Index Score ◽  
Medical Patients ◽  
Related Factors ◽  
Internal Validation ◽  
Health Related

BackgroundReadmission rate is one way to measure quality of care for older patients. Knowledge is sparse on how different social factors can contribute to predict readmission. We aimed to develop and internally validate a comprehensive model for prediction of acute 30-day readmission among older medical patients using various social factors along with demographic, organisational and health-related factors.MethodsWe performed an observational prospective study based on a group of 770 medical patients aged 65 years or older, who were consecutively screened for readmission risk factors at an acute care university hospital during the period from February to September 2012. Data on outcome and candidate predictors were obtained from clinical screening and administrative registers. We used multiple logistic regression analyses with backward selection of predictors. Measures of model performance and performed internal validation were calculated.ResultsTwenty percent of patients were readmitted within 30 days from index discharge. The final model showed that low educational level, along with male gender, contact with emergency doctor, specific diagnosis, higher Charlson Comorbidity Index score, longer hospital stay, cognitive problems, and medical treatment for thyroid disease, acid-related disorders, and glaucoma, predicted acute 30-day readmission. Area under the receiver operating characteristic curve (0.70) indicated acceptable discriminative ability of the model. Calibration slope was 0.98 and calibration intercept was 0.01. In internal validation analysis, both discrimination and calibration measures were stable.ConclusionsWe developed a model for prediction of readmission among older medical patients. The model showed that social factors in the form of educational level along with demographic, organisational and health-related factors contributed to prediction of acute 30-day readmissions among older medical patients.

scholarly journals Haemoconcentration as a predictor of severity in acute pancreatitis

2016 ◽  
Vol 4 (1) ◽  
pp. 3-7
Author(s):  
Tanka Prasad Bohara ◽  
Dimindra Karki ◽  
Anuj Parajuli ◽  
Shail Rupakheti ◽  
Mukund Raj Joshi
Keyword(s):  
Acute Pancreatitis ◽  
Pearson Correlation ◽  
Characteristic Curve ◽  
Scoring Systems ◽  
Cost Effective ◽  
Receiver Operator Characteristic Curve ◽  
First Episode ◽  
P Value ◽  
Receiver Operator Characteristic ◽  
Chi Square

Background: Acute pancreatitis is usually a mild and self-limiting disease. About 25 % of patients have severe episode with mortality up to 30%. Early identification of these patients has potential advantages of aggressive treatment at intensive care unit or transfer to higher centre. Several scoring systems are available to predict severity of acute pancreatitis but are cumbersome, take 24 to 48 hours and are dependent on tests that are not universally available. Haematocrit has been used as a predictor of severity of acute pancreatitis but some have doubted its role.Objectives: To study the significance of haematocrit in prediction of severity of acute pancreatitis.Methods: Patients admitted with first episode of acute pancreatitis from February 2014 to July 2014 were included. Haematocrit at admission and 24 hours of admission were compared with severity of acute pancreatitis. Mean, analysis of variance, chi square, pearson correlation and receiver operator characteristic curve were used for statistical analysis.Results: Thirty one patients were included in the study with 16 (51.61%) male and 15 (48.4%) female. Haematocrit at 24 hours of admission was higher in severe acute pancreatitis (P value 0.003). Both haematocrit at admission and at 24 hours had positive correlation with severity of acute pancreatitis (r: 0.387; P value 0.031 and r: 0.584; P value 0.001) respectively.Area under receiver operator characteristic curve for haematocrit at admission and 24 hours were 0.713 (P value 0.175, 95% CI 0.536 - 0.889) and 0.917 (P value 0.008, 95% CI 0.813 – 1.00) respectively.Conclusion: Haematocrit is a simple, cost effective and widely available test and can predict severity of acute pancreatitis.Journal of Kathmandu Medical College, Vol. 4(1) 2015, 3-7

scholarly journals Cost Effectiveness of Transbronchial Needle Aspiration

1999 ◽  
Vol 6 (4) ◽  
pp. 332-335 ◽  
Author(s):  
Jennifer A Crocket ◽  
Eric YL Wong ◽  
Dale C Lien ◽  
Khanh Gia Nguyen ◽  
Michelle R Chaput ◽  
...  
Keyword(s):  
Cost Effectiveness ◽  
Cost Effective ◽  
Diagnostic Procedures ◽  
Needle Aspiration ◽  
Benign Disease ◽  
University Hospital ◽  
High Yield ◽  
Transbronchial Needle Aspiration ◽  
Computed Tomographic ◽  
The Cost

OBJECTIVE: To evaluate the yield and cost effectiveness of transbronchial needle aspiration (TBNA) in the assessment of mediastinal and/or hilar lymphadenopathy.DESIGN: Retrospective study.SETTING: A university hospital.POPULATION STUDIED: Ninety-six patients referred for bronchoscopy with computed tomographic evidence of significant mediastinal or hilar adenopathy.RESULTS: Ninety-nine patient records were reviewed. Three patients had two separate bronchoscopy procedures. TBNA was positive in 42 patients (44%) and negative in 54 patients. Of the 42 patients with a positive aspirate, 40 had malignant cytology and two had cells consistent with benign disease. The positive TBNA result altered management in 22 of 40 patients with malignant disease and one of two patients with benign disease, thereby avoiding further diagnostic procedures. The cost of these subsequent procedures was estimated at $27,335. No complications related to TBNA were documented.CONCLUSIONS: TBNA is a high-yield, safe and cost effective procedure for the diagnosis and staging of bronchogenic cancer.

An evaluation of a shoulder rehabilitation class in a UK hospital following evidence-based modifications

2021 ◽  
pp. 1-8
Author(s):  
Emily Kell ◽  
John A. Hammond ◽  
Sophie Andrews ◽  
Christina Germeni ◽  
Helen Hingston ◽  
...  
Keyword(s):  
Patient Satisfaction ◽  
Shoulder Pain ◽  
Management Strategies ◽  
Cost Effective ◽  
Rehabilitation Programme ◽  
Patient Specific ◽  
Satisfaction Survey ◽  
Evidence Based ◽  
Patient Satisfaction Survey ◽  
Significant Difference

OBJECTIVES: Shoulder pain is a common musculoskeletal disorder, which carries a high cost to healthcare systems. Exercise is a common conservative management strategy for a range of shoulder conditions and can reduce shoulder pain and improve function. Exercise classes that integrate education and self-management strategies have been shown to be cost-effective, offer psycho-social benefits and promote self-efficacy. This study aimed to examine the effectiveness of an 8-week educational and exercise-based shoulder rehabilitation programme following the introduction of evidence-based modifications. METHODS: A retrospective evaluation of a shoulder rehabilitation programme at X Trust was conducted, comparing existing anonymised Shoulder Pain and Disability Index (SPADI) and Patient-Specific Functional Scale (PSFS) scores from two cohorts of class participants from 2017-18 and 2018-19 that were previously collected by the physiotherapy team. Data from the two cohorts were analysed separately, and in comparison, to assess class efficacy. Descriptive data were also analysed from a patient satisfaction survey from the 2018-19 cohort. RESULTS: A total of 47 patients completed the 8-week shoulder rehabilitation programme during the period of data collection (2018-2019). The 2018-19 cohort showed significant improvements in SPADI (p 0.001) and PSFS scores (p 0.001). No significant difference was found between the improvements seen in the 2017-18 cohort and the 2018-19 cohort. 96% of the 31 respondents who completed the patient satisfaction survey felt the class helped to achieve their goals. CONCLUSION: A group-based shoulder rehabilitation class, which included loaded exercises and patient education, led to improvements in pain, disability and function for patients with rotator cuff related shoulder pain (RCRSP) in this outpatient setting, but anticipated additional benefits based on evidence were not observed.

Estimating the area under a receiver operating characteristic curve using partially ordered sets

2020 ◽  
Vol 0 (0) ◽  
Author(s):  
Ehsan Zamanzade ◽  
Xinlei Wang
Keyword(s):  
Roc Curve ◽  
Characteristic Curve ◽  
Partially Ordered Sets ◽  
Sampling Technique ◽  
Real Data ◽  
Cost Effective ◽  
Ordered Sets ◽  
Operating Characteristics ◽  
Partially Ordered ◽  
Receiver Operating

AbstractRanked set sampling (RSS), known as a cost-effective sampling technique, requires that the ranker gives a complete ranking of the units in each set. Frey (2012) proposed a modification of RSS based on partially ordered sets, referred to as RSS-t in this paper, to allow the ranker to declare ties as much as he/she wishes. We consider the problem of estimating the area under a receiver operating characteristics (ROC) curve using RSS-t samples. The area under the ROC curve (AUC) is commonly used as a measure for the effectiveness of diagnostic markers. We develop six nonparametric estimators of the AUC with/without utilizing tie information based on different approaches. We then compare the estimators using a Monte Carlo simulation and an empirical study with real data from the National Health and Nutrition Examination Survey. The results show that utilizing tie information increases the efficiency of estimating the AUC. Suggestions about when to choose which estimator are also made available to practitioners.

scholarly journals An Innovative and Cost-Advantage CAD Solution for Cubitus Varus Surgical Planning in Children

2021 ◽  
Vol 11 (9) ◽  
pp. 4057
Author(s):  
Leonardo Frizziero ◽  
Gian Maria Santi ◽  
Christian Leon-Cardenas ◽  
Giampiero Donnici ◽  
Alfredo Liverani ◽  
...  
Keyword(s):  
Computer Aided Design ◽  
Low Cost ◽  
Cost Effective ◽  
Varus Deformity ◽  
Patient Specific ◽  
Cubitus Varus ◽  
Surgical Guide ◽  
Traditional Procedure ◽  
Custom Made ◽  
Patient Specific Instruments

The study of CAD (computer aided design) modeling, design and manufacturing techniques has undergone a rapid growth over the past decades. In medicine, this development mainly concerned the dental and maxillofacial sectors. Significant progress has also been made in orthopedics with pre-operative CAD simulations, printing of bone models and production of patient-specific instruments. However, the traditional procedure that formulates the surgical plan based exclusively on two-dimensional images and interventions performed without the aid of specific instruments for the patient and is currently the most used surgical technique. The production of custom-made tools for the patient, in fact, is often expensive and its use is limited to a few hospitals. The purpose of this study is to show an innovative and cost-effective procedure aimed at prototyping a custom-made surgical guide for address the cubitus varus deformity on a pediatric patient. The cutting guides were obtained through an additive manufacturing process that starts from the 3D digital model of the patient’s bone and allows to design specific models using Creo Parametric. The result is a tool that adheres perfectly to the patient’s bone and guides the surgeon during the osteotomy procedure. The low cost of the methodology described makes it worth noticing by any health institution.

Sign in / Sign up

Export Citation Format

Share Document