scholarly journals Unseen Artificial Intelligence—Deep Learning Paradigm for Segmentation of Low Atherosclerotic Plaque in Carotid Ultrasound: A Multicenter Cardiovascular Study

Diagnostics ◽  
2021 ◽  
Vol 11 (12) ◽  
pp. 2257
Author(s):  
Pankaj K. Jain ◽  
Neeraj Sharma ◽  
Luca Saba ◽  
Kosmas I. Paraskevas ◽  
Mandeep K. Kalra ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Ethnic Groups ◽  
Statistical Tests ◽  
Plaque Area ◽  
Close Proximity ◽  
Risk Patients ◽  
The Mean ◽  
Carotid Wall ◽  
Mixed Ethnicity

Background: The early detection of carotid wall plaque is recommended in the prevention of cardiovascular disease (CVD) in moderate-risk patients. Previous techniques for B-mode carotid atherosclerotic wall plaque segmentation used artificial intelligence (AI) methods on monoethnic databases, where training and testing are from the “same” ethnic group (“Seen AI”). Therefore, the versatility of the system is questionable. This is the first study of its kind that uses the “Unseen AI” paradigm where training and testing are from “different” ethnic groups. We hypothesized that deep learning (DL) models should perform in 10% proximity between “Unseen AI” and “Seen AI”. Methodology: Two cohorts from multi-ethnic groups (330 Japanese and 300 Hong Kong (HK)) were used for the validation of our hypothesis. We used a four-layered UNet architecture for the segmentation of the atherosclerotic wall with low plaque. “Unseen AI” (training: Japanese, testing: HK or vice versa) and “Seen AI” experiments (single ethnicity or mixed ethnicity) were performed. Evaluation was conducted by measuring the wall plaque area. Statistical tests were conducted for its stability and reliability. Results: When using the UNet DL architecture, the “Unseen AI” pair one (Training: 330 Japanese and Testing: 300 HK), the mean accuracy, dice-similarity, and correlation-coefficient were 98.55, 78.38, and 0.80 (p < 0.0001), respectively, while for “Unseen AI” pair two (Training: 300 HK and Testing: 330 Japanese), these were 98.67, 82.49, and 0.87 (p < 0.0001), respectively. Using “Seen AI”, the same parameters were 99.01, 86.89 and 0.92 (p < 0.0001), respectively. Conclusion: We demonstrated that “Unseen AI” was in close proximity (<10%) to “Seen AI”, validating our DL model for low atherosclerotic wall plaque segmentation. The online system runs < 1 s.

Outcomes and Cost of Outpatient or Inpatient Management of 712 Patients With Febrile Neutropenia

2008 ◽  
Vol 26 (4) ◽  
pp. 606-611 ◽  
Author(s):  
Linda S. Elting ◽  
Charles Lu ◽  
Carmelita P. Escalante ◽  
Sharon H. Giordano ◽  
Jonathan C. Trent ◽  
...  
Keyword(s):  
Febrile Neutropenia ◽  
Statistical Tests ◽  
Signs And Symptoms ◽  
Low Risk ◽  
Outpatient Management ◽  
Single Episode ◽  
Risk Patients ◽  
Inpatient Management ◽  
The Mean ◽  
Mean Cost

Purpose We retrospectively compared the outcomes and costs of outpatient and inpatient management of low-risk outpatients who presented to an emergency department with febrile neutropenia (FN). Patients and Methods A single episode of FN was randomly chosen from each of 712 consecutive, low-risk solid tumor outpatients who had been treated prospectively on a clinical pathway (1997-2003). Their medical records were reviewed retrospectively for overall success (resolution of all signs and symptoms of infection without modification of antibiotics, major medical complications, or intensive care unit admission) and nine secondary outcomes. Outcomes were assessed by physician investigators who were blinded to management strategy. Outcomes and costs (payer's perspective) in 529 low-risk outpatients were compared with 123 low-risk patients who were psychosocially ineligible for outpatient management (no access to caregiver, telephone, or transportation; residence > 30 minutes from treating center; poor compliance with previous outpatient therapy) using univariate statistical tests. Results Overall success was 80% among low-risk outpatients and 79% among low-risk inpatients. Response to initial antibiotics was 81% among outpatients and 80% among inpatients (P = .94); 21% of those initially treated as outpatients subsequently required hospitalization. All patients ultimately responded to antibiotics; there were no deaths. Serious complications were rare (1%) and equally frequent between the groups. The mean cost of therapy among inpatients was double that of outpatients ($15,231 v $7,772; P < .001). Conclusion Outpatient management of low-risk patients with FN is as safe and effective as inpatient management of low-risk patients and is significantly less costly.

scholarly journals Statistical Approaches Based on Deep Learning Regression for Verification of Normality of Blood Pressure Estimates

Sensors ◽  
2019 ◽  
Vol 19 (9) ◽  
pp. 2137 ◽  
Author(s):  
Soojeong Lee ◽  
Gangseong Lee ◽  
Gwanggil Jeon
Keyword(s):  
Blood Pressure ◽  
Deep Learning ◽  
Learning Algorithm ◽  
Statistical Tests ◽  
Single Point ◽  
Absolute Error ◽  
Standard Normal Distribution ◽  
Rank Test ◽  
The Mean ◽  
Statistical Approaches

Oscillometric blood pressure (BP) monitors currently estimate a single point but do not identify variations in response to physiological characteristics. In this paper, to analyze BP’s normality based on oscillometric measurements, we use statistical approaches including kurtosis, skewness, Kolmogorov-Smirnov, and correlation tests. Then, to mitigate uncertainties, we use a deep learning method to determine the confidence limits (CLs) of BP measurements based on their normality. The proposed deep learning regression model decreases the standard deviation of error (SDE) of the mean error and the mean absolute error and reduces the uncertainties of the CLs and SDEs of the proposed technique. We validate the normality of the distribution of the BP estimation which fits the standard normal distribution very well. We use a rank test in the deep learning technique to demonstrate the independence of the artificial systolic BP and diastolic BP estimations. We perform statistical tests to verify the normality of the BP measurements for individual subjects. The proposed methodology provides accurate BP estimations and reduces the uncertainties associated with the CLs and SDEs using the deep learning algorithm.

scholarly journals Accurate recognition of colorectal cancer with semi-supervised deep learning on pathological images

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Gang Yu ◽  
Kai Sun ◽  
Chao Xu ◽  
Xing-Hua Shi ◽  
Chong Wu ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Colorectal Cancer ◽  
Deep Learning ◽  
Supervised Learning ◽  
Area Under The Curve ◽  
Patient Level ◽  
Significant Difference ◽  
The Mean ◽  
Whole Slide Images ◽  
Better Than

AbstractMachine-assisted pathological recognition has been focused on supervised learning (SL) that suffers from a significant annotation bottleneck. We propose a semi-supervised learning (SSL) method based on the mean teacher architecture using 13,111 whole slide images of colorectal cancer from 8803 subjects from 13 independent centers. SSL (~3150 labeled, ~40,950 unlabeled; ~6300 labeled, ~37,800 unlabeled patches) performs significantly better than the SL. No significant difference is found between SSL (~6300 labeled, ~37,800 unlabeled) and SL (~44,100 labeled) at patch-level diagnoses (area under the curve (AUC): 0.980 ± 0.014 vs. 0.987 ± 0.008, P value = 0.134) and patient-level diagnoses (AUC: 0.974 ± 0.013 vs. 0.980 ± 0.010, P value = 0.117), which is close to human pathologists (average AUC: 0.969). The evaluation on 15,000 lung and 294,912 lymph node images also confirm SSL can achieve similar performance as that of SL with massive annotations. SSL dramatically reduces the annotations, which has great potential to effectively build expert-level pathological artificial intelligence platforms in practice.

scholarly journals Deep learning-based dental plaque detection on primary teeth: a comparison with clinical assessments

2020 ◽  
Author(s):  
Wenzhe You ◽  
Aimin Hao ◽  
Shuai Li ◽  
Yong Wang ◽  
Bin Xia
Keyword(s):  
Deep Learning ◽  
Dental Plaque ◽  
Primary Teeth ◽  
Digital Camera ◽  
Detection Accuracy ◽  
Plaque Area ◽  
Pediatric Dentist ◽  
Significant Difference ◽  
The Mean ◽  
First Time

Abstract Background: The objectives are to design an artificial intelligence (AI) model based on deep learning to detect dental plaque on primary teeth and evaluate the diagnostic accuracy of the AI model. Methods : A conventional neural network (CNN) framework was adopted, and a total of 886 photos of primary teeth taken by an intraoral camera(1280×960 pixels; TPC Ligang, Shenzhen, China) were used to train the AI model. To validate the clinical feasibility, 98 photos of primary teeth taken by the intraoral camera were assessed by the AI model. Additionally, tooth photos were acquired using a digital camera (3216×2136 pixels, Canon EOS 60D, Japan). One experienced pediatric dentist looked at these photos and marked the regions the photos containing dental plaque. After a week, the dentist drew the dental plaque area on the 98 photos taken by the digital camera a second time. In another round of comparison, 102 photos of primary teeth taken by the same intraoral camera to evaluate the diagnostic ability of each approach based on photos with lower-resolution (fewer pixels). The mean intersection-over-union (MIoU) metric was employed to indicate the detection accuracy. Results : The MIoU for the detection of dental plaque on the tested tooth photos was 0.726 ± 0.165.The MIoU of the dentist when diagnosing the 98 photos taken by the digital camera for the first time was 0.695 ± 0.269, while after one week, the MIoU of the dentist was 0.689 ± 0.253. Compared to the dentist, the AI model demonstrated a higher MIoU (0.736 ± 0.174), and the results did not change after a week. When both the dentist and the AI model assessed the 102 photos taken by the intraoral camera. the MIoU of the pediatric dentist was 0.652 ± 0.195, and the MIoU of the AI model was 0.724 ±0.159. The results of a paired t-test found no significant difference between the AI model and human specialist (P > .05) in diagnosing dental plaque on primary teeth. Conclusions : The AI model showed clinically acceptable performance in detecting dental plaque on primary teeth compared with an experienced pediatric dentist.

A cluster-controlled clinical trial of two prophylactic silicone sacral dressings to prevent sacral pressure injuries in critically ill patients

2019 ◽  
pp. 21-26 ◽  
Author(s):  
Monica Stankiewicz ◽  
Jodie Gordon ◽  
Joel Dulhunty ◽  
Wendy Brown ◽  
Hamish Pollock ◽  
...  
Keyword(s):  
Clinical Trial ◽  
Intensive Care ◽  
Similar Efficacy ◽  
Care Patient ◽  
Controlled Clinical Trial ◽  
Cost Difference ◽  
Increased Risk ◽  
Pressure Injury ◽  
Risk Patients ◽  
The Mean

Objective Patients in the intensive care unit (ICU) have increased risk of pressure injury (PI) development due to critical illness. This study compared two silicone dressings used in the Australian ICU setting for sacral PI prevention. Design A cluster-controlled clinical trial of two sacral dressings with four alternating periods of three months' duration. Setting A 10-bed general adult ICU in outer-metropolitan Brisbane, Queensland, Australia. Participants Adult participants who did not have a sacral PI present on ICU admission and were able to have a dressing applied for more than 24 hours without repeated dislodgement or soiling in a 24-hour period (>3 times). Interventions Dressing 1 (Allevyn Gentle Border Sacrum™, Smith & Nephew) and Dressing 2 (Mepilex Border Sacrum™, Mölnlycke). Main outcomes measures The primary outcome was the incidence of a new sacral PI (stage 1 or greater) per 100 dressing days in the ICU. Secondary outcomes were the mean number of dressings per patient, the cost difference of dressings to prevent a sacral PI and product integrity. Results There was no difference in the incidence of a new sacral PI (0.44 per 100 dressing days for both products, p = 1.00), the mean number of dressings per patient per day (0.50 for both products, p = 0.51) and product integrity (85% for Dressing 1 and 84% for Dressing 2, p = 0.69). There was a dressing cost difference per patient (A$10.29 for Dressing 1 and A$28.84 for Dressing 2, p < 0.001). Conclusions Similar efficacy, product use and product integrity, but differential cost, were observed for two prophylactic silicone dressings in the prevention of PIs in the intensive care patient. We recommend the use of sacral prophylactic dressings for at-risk patients, with the choice of product based on ease of application, clinician preference and overall cost-effectiveness of the dressing.

Developing an Artificial Intelligence Project in your Radiology Department

2020 ◽  
Vol 2 ◽  
pp. 58-61 ◽  
Author(s):  
Syed Junaid ◽  
Asad Saeed ◽  
Zeili Yang ◽  
Thomas Micic ◽  
Rajesh Botchu
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Health Care ◽  
Deep Learning ◽  
Learning Algorithms ◽  
Radiology Department ◽  
Short Article ◽  
Computing Power ◽  
Road Map ◽  
Key Concepts

The advances in deep learning algorithms, exponential computing power, and availability of digital patient data like never before have led to the wave of interest and investment in artificial intelligence in health care. No radiology conference is complete without a substantial dedication to AI. Many radiology departments are keen to get involved but are unsure of where and how to begin. This short article provides a simple road map to aid departments to get involved with the technology, demystify key concepts, and pique an interest in the field. We have broken down the journey into seven steps; problem, team, data, kit, neural network, validation, and governance.

Virtual Screening Meets Deep Learning

2018 ◽  
Vol 15 (1) ◽  
pp. 6-28 ◽  
Author(s):  
Javier Pérez-Sianes ◽  
Horacio Pérez-Sánchez ◽  
Fernando Díaz
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Deep Learning ◽  
Virtual Screening ◽  
Great Increase ◽  
New Drugs ◽  
Learning Approach ◽  
Screening Strategies ◽  
Computer Aided ◽  
Recent Developments

Background: Automated compound testing is currently the de facto standard method for drug screening, but it has not brought the great increase in the number of new drugs that was expected. Computer- aided compounds search, known as Virtual Screening, has shown the benefits to this field as a complement or even alternative to the robotic drug discovery. There are different methods and approaches to address this problem and most of them are often included in one of the main screening strategies. Machine learning, however, has established itself as a virtual screening methodology in its own right and it may grow in popularity with the new trends on artificial intelligence. Objective: This paper will attempt to provide a comprehensive and structured review that collects the most important proposals made so far in this area of research. Particular attention is given to some recent developments carried out in the machine learning field: the deep learning approach, which is pointed out as a future key player in the virtual screening landscape.

Rice tablet (Aluminum Phosphide) poisoning

2016 ◽  
Vol 5 (11) ◽  
pp. 5041
Author(s):  
Farkhondeh Jamshidi ◽  
Ahmad Ghorbani ◽  
Sina Darvishi*
Keyword(s):  
Medical Records ◽  
Statistical Tests ◽  
Patient Records ◽  
Demographic Information ◽  
Aluminum Phosphide ◽  
Men And Women ◽  
Significant Difference ◽  
The Mean ◽  
Aluminum Phosphide Poisoning ◽  
Commit Suicide

The abuse of some pesticides especially to suicide is one of the current problems of pesticides. Aluminum phosphide induced poisoning usually happens to suicide and sometimes it is due to accidental occupational exposure and in a few cases it has some criminal intensions. This study is conducted to evaluate patients poisoned with aluminum phosphide. In the present study the medical records of cases of poisoning with rice tablets (aluminum phosphide) hospitalized in Ahvaz Razi hospital is studied. Accordingly, a checklist is prepared that included demographic information of patients (age, gender) and information on patient records (information on poisoning) are completed using the patients’ medical records. The analysis of data is done by SPSS V22. 18 patients poisoned with rice tablet (aluminum phosphide) are studied. Results of the study show that 11 patients are male and seven are female. The mean patient age is 27.06 ±8.04 years that is 28 ±9 and 25 ±6.02 in men and women respectively. Statistical tests show no statistically significant difference in mean age in both genders (P> 0.05). Among patients, 11 subjects took aluminum phosphide to attempt suicide and 3 cases took it unintentionally and of course the reason is not mentioned in four cases. Among the patients who tried to commit suicide by taking aluminum phosphide, 6 cases are male and 5 cases are female that no statistically significant difference is observed between the genders in this respect (P> 0.05). In addition to the study of the complications caused by this poisoning and its mortality, it is recommended to responsible authorities to provide the necessary educations and treatments to prevent this type of poisoning.

Sign in / Sign up

Export Citation Format

Share Document