Healthcare Detection Research Articles

Self-healing, anti-freezing, adhesive and remoldable hydrogel sensor with ion-liquid metal dual conductivity for biomimetic skin

Flexible wearable sensors assembled from conductive hydrogels have received great attention due to their wide application in human-machine interfaces, medical and healthcare detection. However, the traditional conductive gel needs to be attached to the application surface with external force, and only respond to the single strain stimulus. Moreover, due to the existence of water, ordinary hydrogels cannot work at below zero temperatures, which severely limits the application of hydrogel-based flexible electronic devices. The flexible wearable epidermal sensors assembled by ultra-sensitive polyvinyl alcohol-tannic acid-eutectic gallium-indium (PVA-TA-EGaIn) hydrogels with adhesiveness, rapid self-healing, high electrical conductivity and mechanical properties, and temperature sensitivity. The rigid conductive hydrogel prepared by freeze-thaw cycles shows outstanding tensile/compressive strength (1.13 MPa/4.59 MPa) and toughness (1.9 MJ/m3), and reveals excellent fatigue resistance. It also exhibited high conductivity (3.63 S m−1) and strain sensitivity (gauge factor = 2.59). In addition, the hydrogels maintained good flexibility and conductivity at −10 °C. Besides, the PVA-TA-EGaIn hydrogels shows remoldability, which greatly prolongs the service life of the gel. The composite hydrogels show the potential of building the next generation of multifunctional hydrogel-based flexible wearable sensors in human motion monitoring, voice recognition and medical diagnosis.

A new application of community detection for identifying the real specialty of physicians

BackgroundThere is an increasing trend in using network science methods and algorithms, including community detection methods, in different areas of healthcare. These areas include protein networks, drug prescriptions, healthcare fraud detection, and drug abuse. Counterfeit drugs, off-label marketing issues, and finding the healthcare community structures in a network of hospitals, are examples of using community detection in healthcare. ObjectiveThis paper attempts to find physicians’ real medical specialties based on their prescription history. As a novel application of community detection in the healthcare field, this knowledge can be used as an alternative for missing values of the healthcare databases. Therefore, it could help scientists and researchers to obtain more accurate and more reliable results. MethodsThis research is done through the community detection method and applying big data tools as well as interviews with the field experts. The big data, which is used in this paper, includes 32 million written medical prescriptions in the year 2014, provided by the Health Insurance Organization. The results are validated both qualitatively and quantitatively. ResultsThe findings reveal nine major communities of physicians, and labeling these communities by experts presents almost every specialty in the drug prescriptions field. Some of these communities are labeled as a single well-known specialty, and some others are consist of two or more specialties that have overlap with each other. ConclusionAfter receiving the prescription data and getting the experts’ opinions, it was revealed that some physicians might persistently prescribe drugs that are not in their fields of expertise. Regarding the accuracy of community detection and the use of existing data values, we proved this hypothesis.

Big Data-Driven Abnormal Behavior Detection in Healthcare Based on Association Rules

Healthcare insurance frauds are causing millions of dollars of public healthcare fund losses around the world in various ways, which makes it very important to strengthen the management of medical insurance in order to guarantee the steady operation of medical insurance funds. Healthcare fraud detection methods can reduce the losses of healthcare insurance funds and improve medical quality. Existing fraud detection studies mostly focus on finding normal behavior patterns and treat those violating normal behavior patterns as fraudsters. However, fraudsters can often disguise themselves with some normal behaviors, such as some consistent behaviors when they seek medical treatments. To address these issues, we combined a MapReduce distributed computing model and association rule mining to propose a medical cluster behavior detection algorithm based on frequent pattern mining. It can detect certain consistent behaviors of patients in medical treatment activities. By analyzing 1.5 million medical claim records, we have verified the effectiveness of the method. Experiments show that this method has better performance than several benchmark methods.

Sequence Mining and Prediction-Based Healthcare Fraud Detection Methodology

This article presents a novel methodology to detect insurance claim related frauds in the healthcare system using concepts of sequence mining and sequence prediction. Fraud detection in healthcare is a non-trivial task due to the heterogeneous nature of healthcare records. Fraudsters behave as normal patients and with the passage of time keep on changing their way of planting frauds; hence, there is a need to develop fraud detection models. The sequence generation is not the part of previous researches which mostly focus on amount based analysis or medication versus diseases sequential analysis. The proposed methodology is able to generate sequences of services availed or prescribed by each specialty and analyse via two cascaded checks for the detection of insurance claim related frauds. The methodology addresses these challenges and self learns from historical medical records. It is based on two modules namely “Sequence rule engine and Prediction based engine”. The sequence rule engine generates frequent sequences and probabilities of rare sequences for each specialty of the hospital. The comparison of such sequences with the actual patient sequences leads to the identification of anomalies as both sequences are not compliant to the sequences of the rule engine. The system performs further in detail analysis on all non-compliant sequences in the prediction based engine. The proposed methodology is validated by generating patient sequences from last five years transactional data of a local hospital and identifies patterns of service procedures administered to patients using Prefixspan algorithm and Compact prediction tree. Various experiments have been performed to validate the applicability of the developed methodology and the results demonstrate that the methodology is pertinent to detect healthcare frauds and provides on average 85% of accuracy. Thus can help in preventing fraudulent claims and provides better insight into how to improve patient management and treatment procedures.

Buildout of Methodology for Meticulous Diagnosis of K-Complex in EEG for Aiding the Detection of Alzheimer’s by Artificial Intelligence

Application of artificial intelligence (AI) in health-care detection is a domain of exceptional research and interest in today’s world. And hence among this domain, a considerable inclination is toward creating a smart system that is AI for aiding identification of brain-related disease—Alzheimer’s—using electroencephalogram (EEG). Certain AI-based techniques as well as systems have been created for EEG examination and interpretation, but they have a common drawback that is lack of shrewdness and acuteness. Therefore, to overcome these drawbacks, a different methodology or technique is suggested in this paper which is able to mold the AI technique for better EEG Cz strip K-complex identification. This suggested method and structure of AI detection system is relied on quantitative scrutinization of Cz strip and embedding-established EEG explication principles for detection of K-complex and Alzheimer’s. This technique unconditionally relied on facts and information of neuroscience that are applied by expert in health care such as neurologist to create a detailed review of sick person’s EEG. The suggested technique also allots a potential of learning on its own to the AI so that it can apply the events in future examinations.

Violencia obstétrica en mujeres asistidas por aborto espontáneo en Guadalajara, México: expresiones

Objectives To expose the violence exerted by institutions when they fail to fulfill their obligation to enforce the rights of citizens. Materials and methods This research is based, on the one hand, on the analysis of the concepts of structural or institutional violence and cultural or symbolic violence as developed by several authors and, on the other hand, on the revision of some of its sociological, legal and ethical manifestations, such as impunity, moral damage and its detection in healthcare. Development Considerations on the violence suffered by women in the judicial system (in relation to impunity and the low recognition of moral damages) and in the field of healthcare. This type of violence is invisible and protected by certain institutional and symbolic structures. Conclusions A proposal of research and social actions to expose and eradicate the institutional and symbolic bases of certain types of violence.

A parameter based growing ensemble of self-organizing maps for outlier detection in healthcare

Outlier detection is critical for many applications such as healthcare, health insurance, medical diagnosis, predictive analytics, pattern recognition, intrusion detection, anomaly or defect detection, video surveillance, credit card fraud detection and text mining. Outlier detection techniques could be statistics, distance- or model based. Techniques, which are based on a single method for outlier detection usually have weaknesses and strengths and are mostly unstable. Outlier detection ensembles harness the strengths of individual detectors and result in stable performance. This paper presents a new parameter based growing self-organizing maps ensemble (GSOME) for outlier detection in multivariate patterns. For outlier detection, the proposed GSOME transforms non-linear relationships between high dimensional patterns into a simple 1D geometric relationship. Whatever the pattern dimensionality is, it is mapped to a single point of a line. The dispersion of mapped points will be used to locate the outliers and measure the degree of outlyingness. Several experiments on both real and synthetic data sets show the promising performance of the proposed GSOME.

Investigation of Ingaas-Based Pin Photodiode for High Quantum Efficiency

Photodetectors are key components in every photonic sensors like photonics, bio-signal detection in health care and internet of things, etc.1-3To serve as the converter from the optical to the electrical signal, the photodetector should offer high responsivity and sensitivity. Avalanche photodiodes are widely used as opto-electronic converter for highly-sensitive optical receivers. For covering the spectral range from 800 nm to 1600 nm wavelength, the avalanche photodiodes are needed sophisticated layer structures and supply voltage values in excess of 20 V. Particularly, the avalanche photodiodes are not appropriate to apply in comfortable applications like wearable devices and smart phones. In addition, the operation of the photodetector should be facilitated by a compact size, a low power supply voltage and temperature insensitivity. To overcome this problem, InGaAs-baed PIN photodiodes are investigated to obtain a high quantum efficiency and low leakage current. Figure 1

Development of a trigger tool to identify adverse events and harm in Emergency Medical Services

BackgroundAdverse event(AE) detection in healthcare has traditionally relied upon several methods including: patient care documentation review, mortality and morbidity review, voluntary reporting, direct observation and complaint systems. A novel sampling...

Validation of the Alcohol, Smoking and Substance Involvement Screening Test in a low- and middle-income country cross-sectional emergency centre study.

Given the high prevalence and detrimental consequences of alcohol or other drug (AOD) use in low- and middle-income countries, a screening tool for early detection in health care, including emergency care, is critical. We set out to validate the Alcohol, Smoking and Substance Involvement Screening Test (ASSIST) for the South African context. We interviewed emergency centre patients (n = 200) in Cape Town for this cross-sectional study conducted from January to March 2013 utilising a questionnaire battery, including the ASSIST and Mini International Neuropsychiatric Interview. Internal consistency (Cronbach's alpha) and screening properties of the ASSIST (receiver operating characteristic analysis) were examined utilising the Mini International Neuropsychiatric Interview AOD use modules as the gold standard. Cronbach's alpha for alcohol and illicit drugs ranged from 0.81 to 0.95 indicating good internal consistency. ASSIST cut-off scores show a good sensitivity and specificity for discrimination particularly when distinguishing between substance use and abuse, rather than dependence. For alcohol, the area under the curve was 0.94 for distinguishing between use and abuse, and this dropped to 0.68 for distinguishing between abuse and dependence, while the statistic remained high for both use/abuse and abuse/dependence for illicit drugs: 0.95 and 0.96. AOD abuse was associated with cut-off scores below the World Health Organization recommended levels, in keeping with various international studies suggesting that individuals with lower scores be offered interventions. The ASSIST was found to be useful for South African health care and holds promise for cost-effective task-shifting approaches in lower resourced settings. [van der Westhuizen C, Wyatt G, Williams JK, Stein DJ, Sorsdahl K. Validation of the Alcohol, Smoking and Substance Involvement Screening Test in a low- and middle-income country cross-sectional emergency centre study. Drug Alcohol Rev 2016;35:702-709].

Improving electrochemical biosensor performance by understanding the influence of target DNA length on assay sensitivity

Electrochemical DNA hybridisation assays allow the measurement of probe-target binding in a label free fashion for biosensor and healthcare detection, particularly when using electrochemical impedance spectroscopy (EIS). Typically in EIS assay development a short artificial oligonucleotide is used to test sensor performance and consideration is not given to binding real world samples which can contain DNA fragments of varying length. This paper investigates the effect of solution side DNA overhangs on the EIS signal. Firstly, by using a surface tethered 15 nucleotides (nt) PNA probe and a series of artificial DNA targets with increasingly long overhangs it was possible to measure differences in the EIS signal brought about by target length. It was found that an overhang of 1515nt nt gave the most effective enhancement of signal. This enhancement was attributed to the overhang reducing the access of the redox couple to the electrode surface. Overhangs of 45 and 8515nt nt caused a smaller enhancement of signal which can be attributed to the reduced hybridisation efficiency of longer strands. Secondly, EIS responses from fragmented Methicillin resistant Staphylococcus aureus (MRSA) bacterial genomic DNA (gDNA) were measured and it was found that in the case of the MRSA gDNA, progressive fragmentation of long DNA sequences (>1000bp) to less than 100bp coincided with enhancement of the EIS signal. From the results obtained with oligonucleotides it is inferred that the creation of shorter solution side overhangs in real world MRSA samples boosts the electrochemical signal observed upon DNA binding.

Anomaly Detection in Healthcare: Detecting Erroneous Treatment Plans in Time Series Radiotherapy Data

Adverse events in healthcare and medical errors result in thousands of accidental deaths and over one million excess injuries each year. Anomaly detection in medicine is an important task, especially in the area of radiation oncology where errors are very rare, but can be extremely dangerous, and even deadly. To avoid medical errors in radiation cancer treatment, careful attention needs to be made to ensure accurate implementation of the intended treatment plan. In this paper, we describe the work that resulted in a valuable predictive analytics tool for automatic detection of catastrophic errors in cancer radiotherapy, adding an important safeguard for patient safety. We designed a method for Dynamic Modeling and Prediction of Radiotherapy Treatment Deviations from Intended Plans (SmartTool) to automatically detect and highlight potential errors in a radiotherapy treatment plan, based on the data from several thousand prostate cancer treatments that were used to build the model. SmartTool determines if the treatment parameters are valid, against a previously built Predictive Model of a Medical Error (PMME). SmartTool communicates with a radiotherapy treatment management system, checking all the treatment parameters in the background prior to execution, and after the human expert QA is completed. Any anomalous treatment parameters are detected using an innovative intelligent algorithm in a completely automatic and unsupervised manner, and it flags the operator by highlighting the suspect parameter(s) for human intervention. Furthermore, the system is self-learning and constantly evolving, and the model is dynamically updated with the new treatment data.

Energy Saving in Forward Fall Detection using Mobile Accelerometer

Fall injury is one of the biggest risks to health and well-being of the elderly especially in independent living because falling accidents may cause instant death. There are many research interests aimed to detect fall incidents. Fall detection is envisioned critical on ICT-assisted healthcare future. In addition, mobile battery is currently another serious problem in which performance feasibility is considered as a standard to verify an effective method. In this paper, the authors study forward fall detection method from mobile phone perspective using accelerometer only without sacrificing accuracy to save energy. Using peak threshold algorithm in axes of mobile accelerometer, transition from activity of daily living (ADL) to forward fall event is recognized. In collected templates, Dynamic Time Warping (DTW) was applied to compute difference among them with new unlabeled samples. Results implemented on mobile phone easily show the feasibility of the method hence contribute significantly to fall detection in healthcare.