scholarly journals Predicting Customer Call Intent by Analyzing Phone Call Transcripts Based on CNN for Multi-Class Classification

2019 ◽  
Author(s):  
Junmei Zhong ◽  
William Li
Keyword(s):  
Phone Call ◽  
Multi Class Classification

Online Patient Consultation

2020 ◽  
Vol 158 (04) ◽  
pp. 345-350
Author(s):  
Christian Juhra ◽  
Jörg Ansorg ◽  
David Alexander Back ◽  
Dominik John ◽  
Andrea Kuckuck-Winkelmann ◽  
...  
Keyword(s):  
New Technologies ◽  
Communication Technologies ◽  
Phone Call ◽  
Insurance Companies ◽  
Personal Contact ◽  
Software Products ◽  
Patient Consent ◽  
Health Insurance Companies ◽  
Patient Consultation ◽  
Certified Software

AbstractNew communication technologies allow patients to communicate with their physicians from anywhere using computer or smartphone. Adding video to the mere phone call optimizes the personal contact between patient and physicians regardless of distance. Legal and reimbursements requirements must be taken into account, especially only certified software products must be used. In addition, patient consent is needed and confidentiality must be assured. The video patient consultation can be reimbursed by the health insurance companies. As with all new technologies, the introduction of these video consultations faced some challenges. Although patients and physicians have expressed great interest in this technology, it has been rarely used so far. The current COVID crisis increased the need for video consultations resulting in an increasing use of video patient consultation. It can be expected that this demand will still exists after the COVID crisis.

Squeak and rattle noise classification using radial basis function neural networks

2020 ◽  
Vol 68 (4) ◽  
pp. 283-293
Author(s):  
Oleksandr Pogorilyi ◽  
Mohammad Fard ◽  
John Davy ◽  
Mechanical and Automotive Engineering, School ◽  
Mechanical and Automotive Engineering, School ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
High Accuracy ◽  
Training Method ◽  
Vehicle Interior ◽  
Trained Classifier ◽  
Different Types ◽  
Noise Classification ◽  
Automatic Tool ◽  
Multi Class Classification

In this article, an artificial neural network is proposed to classify short audio sequences of squeak and rattle (S&R) noises. The aim of the classification is to see how accurately the trained classifier can recognize different types of S&R sounds. Having a high accuracy model that can recognize audible S&R noises could help to build an automatic tool able to identify unpleasant vehicle interior sounds in a matter of seconds from a short audio recording of the sounds. In this article, the training method of the classifier is proposed, and the results show that the trained model can identify various classes of S&R noises: simple (binary clas- sification) and complex ones (multi class classification).

A Study on Multi Class Classification from Breast Cancer Images using Ensemble Network and Transfer Learning

2020 ◽  
Vol 14 ◽  
Author(s):  
Lahari Tipirneni ◽  
Rizwan Patan
Keyword(s):  
Breast Cancer ◽  
Neural Network ◽  
Convolutional Neural Network ◽  
Binary Classification ◽  
Disease Diagnosis ◽  
Feature Descriptors ◽  
Histopathological Images ◽  
Viable Approach ◽  
Multi Class Classification

Abstract:: Millions of deaths all over the world are caused by breast cancer every year. It has become the most common type of cancer in women. Early detection will help in better prognosis and increases the chance of survival. Automating the classification using Computer-Aided Diagnosis (CAD) systems can make the diagnosis less prone to errors. Multi class classification and Binary classification of breast cancer is a challenging problem. Convolutional neural network architectures extract specific feature descriptors from images, which cannot represent different types of breast cancer. This leads to false positives in classification, which is undesirable in disease diagnosis. The current paper presents an ensemble Convolutional neural network for multi class classification and Binary classification of breast cancer. The feature descriptors from each network are combined to produce the final classification. In this paper, histopathological images are taken from publicly available BreakHis dataset and classified between 8 classes. The proposed ensemble model can perform better when compared to the methods proposed in the literature. The results showed that the proposed model could be a viable approach for breast cancer classification.

Post-Hospital Syndrome (PHS) and Potentially Preventable Hospitalizations(PPH) in Adults. MonashWatch adult cohort patient telehealth journeys (Preprint)

2018 ◽  
Author(s):  
Associate Professor Martin ◽  
Narelle Hinckley ◽  
Keith Stockman ◽  
Donadl Campbell
Keyword(s):  
Adverse Outcomes ◽  
Phone Call ◽  
Post Discharge ◽  
Patient Journey ◽  
Preventable Hospitalizations ◽  
Acute Admission ◽  
Avoidable Hospitalizations ◽  
Self Rated Health ◽  
Phone Calls ◽  
Potentially Preventable Hospitalizations

BACKGROUND Monash Watch (MW) aims to reduce avoidable hospitalizations in a cohort above a risk ‘threshold’ identified by HealthLinks Chronic Care (HLCC) algorithms using personal, diagnostic, and service data, excluding surgical and psychiatric admissions. MW conducted regular patient monitoring through outbound phone calls using the Patient Journey Record System (PaJR). PaJR alerts are intended to act as a self-reported barometer of health perceptions with more alerts per call indicating greater risk of Potentially Preventable Hospitalizations (PPH) and Post Hospital Syndrome (PHS). Most knowledge of PPH and PHS occurs at a macro-level with little understanding of fine-grained dynamics. OBJECTIVE To describe patterns of self-reported concerns and self-rated health 10 days before and after acute hospital admission in the telehealth intervention cohort of MonashWatch in the context of addressing PPH and PHS. METHODS Participants: 173 who had an acute admission of the of the 232 HLCC cohort with predicted 3+ admissions/year, in MW service arm for >40 days. Measures: Self-reported health and health care status in 764 MW phone call records which were classified into Total Alerts (all concerns - self-reported) and Red Alerts (concerns judged to be higher risk of adverse outcomes/admissions -acute medical and illness symptoms). Acute (non-surgical) admissions from Victorian Admitted Episode database. Analysis: Descriptive Timeseries homogeneity metrics using XLSTAT. RESULTS Self-reported problems (Total Alerts) statistically shifted to a higher level 3 days before an acute admission and stayed at a high level for the 10 days post discharge; reported acute medical and illness symptoms (Red Alerts) increased 1 day prior to admission and but remained at a higher level than before admission. Symptoms of concern did not change before admission or after discharge. Self-rated health and feeling depressed were reported to worsen 5 days post discharge. Patients reported more medication changes up to 2 days before acute admission. CONCLUSIONS These descriptive findings in a cohort of high risk individuals suggest a prehospital phase of what is termed PHS, which persisted on discharge and possibly worsened 5 days after discharge with worse self-rated health and depressive symptoms. Further research is needed. The role and place of community and hospital in such a cohort needs further investigation and research into PPH and PHS.

"Taming the Monster aka Uncontrolled Diabetes: A Viewpoint" (Preprint)

2020 ◽  
Author(s):  
Swati Anand ◽  
Amardeep Kalsi ◽  
Jonathan Figueroa ◽  
Parag Mehta
Keyword(s):  
Blood Glucose ◽  
Diabetes Management ◽  
Positive Impact ◽  
The United States ◽  
Phone Call ◽  
Diabetic Patients ◽  
Dietary Compliance ◽  
Glucose Levels ◽  
Uncontrolled Diabetes ◽  
Number Of Patients

BACKGROUND HbA1c between 6% and 6.9% is associated with the lowest incidence of all‐cause and CVD mortality, with a stepwise increase in all‐cause and cardiovascular mortality in those with an HbA1c >7%. • There are 30 million individuals in the United States (9.4% of the population) currently living with Diabetes Mellitus. OBJECTIVE Improving HbA1C levels in patients with uncontrolled Diabetes with a focused and collaborative effort. METHODS Our baseline data for Diabetic patients attending the outpatient department from July 2018 to July 2019 in a University-affiliated hospital showed a total of 217 patients for one physician. • Of 217 patients, 17 had HbA1C 9 and above. We contacted these patients and discussed the need for tight control of their blood glucose levels. We intended to ensure them that we care and encourage them to participate in our efforts to improve their outcome. • We referred 13 patients that agreed to participate to the Diabetic educator who would schedule an appointment with the patients, discuss their diet, exercise, how to take medications, self-monitoring, and psychosocial factors. • If needed, she would refer them to the Nutritionist based on patients’ dietary compliance. • The patients were followed up in the next two weeks via telemedicine or a phone call by the PCP to confirm and reinforce the education provided by the diabetes educator. RESULTS Number of patients that showed an improvement in HbA1C values: 11 Cumulative decrease in HbA1C values for 13 patients: 25.3 The average reduction in HbA1C: 1.94 CONCLUSIONS Our initiative to exclusively target the blood glucose level with our multidisciplinary approach has made a positive impact, which is reflected in the outcome. • It leads to an improvement in patient compliance and facilitates diabetes management to reduce the risk for complications CLINICALTRIAL NA

Tracing or Tracking? A Preliminary Analysis of COVID-19 Outbreak Tracker Apps on Android and User Privacy (Preprint)

2020 ◽  
Author(s):  
Alex Akinbi ◽  
Ehizojie Ojie
Keyword(s):  
Preliminary Analysis ◽  
Service Providers ◽  
User Participation ◽  
Memory Storage ◽  
Phone Call ◽  
Contact Tracing ◽  
Privacy Rights ◽  
User Privacy ◽  
Android Apps ◽  
User Data

BACKGROUND Technology using digital contact tracing apps has the potential to slow the spread of COVID-19 outbreaks by recording proximity events between individuals and alerting people who have been exposed. However, there are concerns about the abuse of user privacy rights as such apps can be repurposed to collect private user data by service providers and governments who like to gather their citizens’ private data. OBJECTIVE The objective of our study was to conduct a preliminary analysis of 34 COVID-19 trackers Android apps used in 29 individual countries to track COVID-19 symptoms, cases, and provide public health information. METHODS We identified each app’s AndroidManifest.xml resource file and examined the dangerous permissions requested by each app. RESULTS The results in this study show 70.5% of the apps request access to user location data, 47% request access to phone activities including the phone number, cellular network information, and the status of any ongoing calls. 44% of the apps request access to read from external memory storage and 2.9% request permission to download files without notification. 17.6% of the apps initiate a phone call without giving the user option to confirm the call. CONCLUSIONS The contributions of this study include a description of these dangerous permissions requested by each app and its effects on user privacy. We discuss principles that must be adopted in the development of future tracking and contact tracing apps to preserve the privacy of users and show transparency which in turn will encourage user participation.

Recognizing a Crisis

2018 ◽  
Author(s):  
Joshua M. Sharfstein
Keyword(s):  
Crisis Management ◽  
Daily Activity ◽  
Wishful Thinking ◽  
Phone Call ◽  
First Order ◽  
Lasting Change

The first order of business in crisis management is figuring out that there is a crisis. Once a brewing crisis is recognized, health officials can organize a coherent response, limit its impact, and even make an early pivot to achieve long-lasting change. Unfortunately, spotting a crisis early is far easier said than done. It’s the rare crisis that announces itself with a phone call 12 hours in advance. Most crises go unnoticed even as clues emerge, lost in the stream of the daily activity of an agency or hidden by biases, assumptions, and wishful thinking. To be successful, officials and their agencies should pursue a proactive strategy to identify crises early. There are three elements of effective crisis detection: spotting signals, pulling in data and assessing the situation, and developing a space and culture to put the pieces of the puzzle together.

Patient Education and Sacubitril/Valsartan: A Randomized Comparative Trial

2021 ◽  
pp. 001857872199980
Author(s):  
Christopher Giuliano ◽  
Bradley St. Pierre ◽  
Jamie George
Keyword(s):  
Controlled Trial ◽  
Comparative Trial ◽  
Text Messages ◽  
Phone Call ◽  
Secondary Outcome ◽  
Short Term ◽  
Phone Calls ◽  
Video Education ◽  
Pharmacist Education

Objective: To compare video to pharmacist education for patients taking sacubitril/valsartan. Methods: We conducted a randomized controlled trial comparing video to pharmacist education with a second randomized intervention of education delivered through text or phone call at 14 days. The primary outcome compared the change in short term knowledge between groups and the secondary outcome was long term knowledge at 1 month. Results: Forty-three patients were included. Scores improved significantly ( P < .05) in the pharmacist group from 54.1% to 85.9% and from 64.3% to 86.1% in the video education group, although there was no difference between groups (31.8% vs 22.9%, P = .13). At 30 days, scores were significantly higher than baseline (difference 16.5%, P < .05) although did decrease from the posttest (difference 7.4%, P < .05). There was no difference at 30 days between those that received text messages versus phone calls (−10% vs −5.5%, respectively; P = .36). Conclusion: We saw improvements in both short term and long term knowledge for patients receiving education through pharmacist or video education. Neither approach was more effective than the other. Clinicians can use either approach based on patient preference.

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.

Sign in / Sign up

Export Citation Format

Share Document