Clinical Health Care Applications Research Articles

Microwave humidity sensor based on carbon dots-decorated MOF-derived porous Co3O4 for breath monitoring and finger moisture detection

This research investigates a microwave transduction-based humidity sensor that is a promising candidate for real-time clinical healthcare applications and green miniaturized wearable electronic devices. Optimization of sensing material, sensing platform, and device fabrication techniques produces a carbon dots (CDs)-decorated metal organic framework (MOF)-derived porous Co3O4 (CDs-Co3O4) microwave resonator-based sensor with excellent real-time humidity detection. Inspired by the water absorption component polyacrylamide in baby diapers, the acrylamide is adopted to synthesize CDs for microwave humidity sensor. Combining CDs with MOF-derived porous Co3O4 enhances humidity sensitivity under microwave excitation, with a frequency shift of 3.40 MHz/% RH and a loss variation of 0.15 dB/% RH between 5% and 99% RH. These values are 49.7% (for frequency shift) and 20.5% (for return loss) higher than Co3O4 sensor. Moreover, CDs-Co3O4 exhibits high selectivity towards water vapor against other volatile organic compounds, and the response or recovery time are both less than 5 s. Fabricated by an integrated passive device technology, the sensing platform is miniaturized at 0.98 × 0.80 × 0.22 mm3 with superb device stability and reliability. The CDs-Co3O4 sensor remarkably monitors respiratory patterns of breathing or apnea, as well as subtle changes in the humidity levels of an approaching finger. A charge transfer process and microwave interactions are the mechanisms for improved humidity sensitivity.

A priority-aware lightweight secure sensing model for body area networks with clinical healthcare applications in Internet of Things

In this study, a priority-aware lightweight secure sensing model for body area networks with clinical healthcare applications in internet of things is proposed. In this model, patients’ data is labeled according to the proposed prioritizing mechanism. This provides a prioritized and delay-less service in the server side for the patients with critical conditions. In the proposed model, the sensed data is monitored in a real time way to calculate its sparsity level. Then, the ,calculated sparsity level is used to determine the number of required measurements for data sampling. This allows to sample the data with the number of measurements proportional to the sparsity level and information content of the data. Moreover, the particular design of the measurement matrix causes the aggregated data to be encrypted and its security be guaranteed. Simulation results show that compared to its counterpart schemes, the proposed sensing model not only provides security but also reduces the average energy consumption of the sensor nodes and the average packet delivery delay. This improvement originates from the reduction of the number of required bits for transferring the sensed data and is due to the consideration of the information content and sparsity level variation in the sensed data.

Highly conformable stretchable dry electrodes based on inexpensive flex substrate for long-term biopotential (EMG/ECG) monitoring

The comfortable, long-term, accurate, and continuous biopotential monitoring is of paramount importance for biomedical applications. In this respect, dry electrodes are the way forward for the next generation of wearable health monitoring devices. However, it is still challenging to record the bioelectrical signals, i.e., electroencephalogram (EEG), electromyogram (EMG), electrocardiogram (ECG), of patients during their everyday life. It is mainly because, soft skin-like, at the same time, electrically conducting and biocompatible materials have to be integrated with electrical circuits. Dry electrodes have the potential to be integrated in this manner into a variety of wearable form factors. However, most dry electrodes are fabricated on rigid substrates, which do not possess sufficient flexibility and conformability to human skin. Novel flexible/stretchable substrates are a topic of research in the state-of-the-art literature for dry electrodes in pursuit of the wearable biopotential electrodes.In this work, a novel flexible and wearable dry electrode technology based on polydimethylsiloxane (PDMS) is presented. It has been tested for EMG and ECG signal acquisition as the proof of principle. The performance of the fabricated dry electrodes is investigated by measuring the contact impedance between the skin and the electrode. The impedance is compared with the commercially available wet Ag/AgCl electrodes. Overall the contact impedance of the dry electrodes is comparable compared to the wet Ag/AgCl in the frequency range of interest for biopotential electrodes. Experimentally received signal quality of EMG/ECG with the dry electrode is comparable to the wet electrode as well. The dry electrodes do not require any skin preparation nor conductive gels. Thanks to the extreme flexibility of our electrode, it provides more robust contact as well as less skin irritation. The provided results suggest that the presented electrodes/technology have the potential to be used in clinical health-care applications. To support this claim, long term EMG/ECG results are also provided in the manuscript.

Artificial Intelligence in Clinical Health Care Applications: Viewpoint.

The idea of artificial intelligence (AI) has a long history. It turned out, however, that reaching intelligence at human levels is more complicated than originally anticipated. Currently, we are experiencing a renewed interest in AI, fueled by an enormous increase in computing power and an even larger increase in data, in combination with improved AI technologies like deep learning. Healthcare is considered the next domain to be revolutionized by artificial intelligence. While AI approaches are excellently suited to develop certain algorithms, for biomedical applications there are specific challenges. We propose six recommendations—the 6Rs—to improve AI projects in the biomedical space, especially clinical health care, and to facilitate communication between AI scientists and medical doctors: (1) Relevant and well-defined clinical question first; (2) Right data (ie, representative and of good quality); (3) Ratio between number of patients and their variables should fit the AI method; (4) Relationship between data and ground truth should be as direct and causal as possible; (5) Regulatory ready; enabling validation; and (6) Right AI method.

Benchmarking deep learning models on large healthcare datasets

Deep learning models (aka Deep Neural Networks) have revolutionized many fields including computer vision, natural language processing, speech recognition, and is being increasingly used in clinical healthcare applications. However, few works exist which have benchmarked the performance of the deep learning models with respect to the state-of-the-art machine learning models and prognostic scoring systems on publicly available healthcare datasets. In this paper, we present the benchmarking results for several clinical prediction tasks such as mortality prediction, length of stay prediction, and ICD-9 code group prediction using Deep Learning models, ensemble of machine learning models (Super Learner algorithm), SAPS II and SOFA scores. We used the Medical Information Mart for Intensive Care III (MIMIC-III) (v1.4) publicly available dataset, which includes all patients admitted to an ICU at the Beth Israel Deaconess Medical Center from 2001 to 2012, for the benchmarking tasks. Our results show that deep learning models consistently outperform all the other approaches especially when the ‘raw’ clinical time series data is used as input features to the models.

Healthcare data warehousing and quality assurance

Healthcare data warehousing presents unique challenges. The industry is rife with often incompatible medical standards and coding schemes that require careful translation. Healthcare data comes from many sources and is delivered in many forms, including published books, individual spreadsheets, and several tape or data formats. Results derived from a healthcare data warehouse must be delivered in accessible form to diverse stakeholders, including healthcare regulators, physicians, hospital administrators, consumers, community activists, and members of the popular press. The industry's widely decentralized and largely autonomous data collection efforts make data quality a significant challenge. Finally, the sensitivity of healthcare data makes privacy and security issues paramount. Healthcare data warehousing will make rigorous, quantitative information available to healthcare decision makers. The authors describe a fully functional healthcare data warehouse used to produce several reports for communities throughout Florida. Building on this work, they're actively pursuing a research agenda to enhance technical data warehousing capabilities while investigating innovative community and clinical healthcare applications.

Empirical support for psychological assessment in clinical health care settings.

Psychologists in health care settings today find it increasingly difficult to obtain authorization and appropriate reimbursement for psychological assessments from 3rd party payers. Authorization and reimbursement denials often are based on allegations that empirical support for the utility and validity of psychological tests is nonexistent or limited. This article reviews a sample of the considerable empirical support that exists for the utility and validity of a variety of psychological tests for a wide range of clinical health care applications. Informed by data such as these, psychologists should become more effective in their abilities to seek authorization and reimbursement for assessment and overturning denials.