Advancements in optical fiber-based wearable sensors for smart health monitoring.

Healthcare system is undergoing a significant transformation from a traditional hospital-centered to an individual-centered one, as a result of escalating chronic diseases, ageing populations, and ever-increasing healthcare costs,. Wearable sensors have become widely used in health monitoring systems since the COVID-19 pandemic. They enable continuous measurement of important health indicators like body temperature, wrist pulse, respiration rate, and non-invasive bio fluids like saliva and perspiration. Over the last few decades, the development has mostly concentrated on electrochemical and electrical wearable sensors. However, due to the drawbacks of such sensors, such as electronic waste, electromagnetic interference, non-electrical security, and poor performance, researchers are exhibiting a strong interest in optical principle-based systems. Fiber-based optical wearables are among the most promising healthcare systems because of advancements in high-sensitivity, durable, multiplexed sensing, and simple integration with flexible materials to improve wearability and simplicity. We present an overview of recent developments in optical fiber-based wearable sensors, focusing on two mechanisms: wavelength interrogation and intensity modulation for the detection of body temperature, pulse rate, respiration rate, body movements, and biomedical noninvasive fluids, with a thorough examination of their benefits and drawbacks. This review also focuses on improving working performance and application techniques for healthcare systems, including the integration of nanomaterials and the usage of the Internet of Things (IoT) with signal processing. Finally, the review concludes with a discussion of the future possibilities and problems for optical fiber-based wearables.

OpenDeID Pipeline for Unstructured Electronic Health Record Text Notes Based on Rules and Transformers: Deidentification Algorithm Development and Validation Study.

BACKGROUND: Electronic health records (EHRs) in unstructured formats are valuable sources of information for research in both the clinical and biomedical domains. However, before such records can be used for research purposes, sensitive health information (SHI) must be removed in several cases to protect patient privacy. Rule-based and machine learning-based methods have been shown to be effective in deidentification. However, very few studies investigated the combination of transformer-based language models and rules. OBJECTIVE: The objective of this study is to develop a hybrid deidentification pipeline for Australian EHR text notes using rules and transformers. The study also aims to investigate the impact of pretrained word embedding and transformer-based language models. METHODS: In this study, we present a hybrid deidentification pipeline called OpenDeID, which is developed using an Australian multicenter EHR-based corpus called OpenDeID Corpus. The OpenDeID corpus consists of 2100 pathology reports with 38,414 SHI entities from 1833 patients. The OpenDeID pipeline incorporates a hybrid approach of associative rules, supervised deep learning, and pretrained language models. RESULTS: The OpenDeID achieved a best F1-score of 0.9659 by fine-tuning the Discharge Summary BioBERT model and incorporating various preprocessing and postprocessing rules. The OpenDeID pipeline has been deployed at a large tertiary teaching hospital and has processed over 8000 unstructured EHR text notes in real time. CONCLUSIONS: The OpenDeID pipeline is a hybrid deidentification pipeline to deidentify SHI entities in unstructured EHR text notes. The pipeline has been evaluated on a large multicenter corpus. External validation will be undertaken as part of our future work to evaluate the effectiveness of the OpenDeID pipeline.

Privacy-protecting behaviours of risk detection in people with dementia using videos.

BACKGROUND: People living with dementia often exhibit behavioural and psychological symptoms of dementia that can put their and others' safety at risk. Existing video surveillance systems in long-term care facilities can be used to monitor such behaviours of risk to alert the staff to prevent potential injuries or death in some cases. However, these behaviours of risk events are heterogeneous and infrequent in comparison to normal events. Moreover, analysing raw videos can also raise privacy concerns. PURPOSE: In this paper, we present two novel privacy-protecting video-based anomaly detection approaches to detect behaviours of risks in people with dementia. METHODS: We either extracted body pose information as skeletons or used semantic segmentation masks to replace multiple humans in the scene with their semantic boundaries. Our work differs from most existing approaches for video anomaly detection that focus on appearance-based features, which can put the privacy of a person at risk and is also susceptible to pixel-based noise, including illumination and viewing direction. We used anonymized videos of normal activities to train customized spatio-temporal convolutional autoencoders and identify behaviours of risk as anomalies. RESULTS: We showed our results on a real-world study conducted in a dementia care unit with patients with dementia, containing approximately 21 h of normal activities data for training and 9 h of data containing normal and behaviours of risk events for testing. We compared our approaches with the original RGB videos and obtained a similar area under the receiver operating characteristic curve performance of 0.807 for the skeleton-based approach and 0.823 for the segmentation mask-based approach. CONCLUSIONS: This is one of the first studies to incorporate privacy for the detection of behaviours of risks in people with dementia. Our research opens up new avenues to reduce injuries in long-term care homes, improve the quality of life of residents, and design privacy-aware approaches for people living in the community.

A Machine Learning Model to Predict Length of Stay and Mortality among Diabetes and Hypertension Inpatients.

Background and Objectives: Taiwan is among the nations with the highest rates of Type 2 Diabetes Mellitus (T2DM) and Hypertension (HTN). As more cases are reported each year, there is a rise in hospital admissions for people seeking medical attention. This creates a burden on hospitals and affects the overall management and administration of the hospitals. Hence, this study aimed to develop a machine learning (ML) model to predict the Length of Stay (LoS) and mortality among T2DM and HTN inpatients. Materials and Methods: Using Taiwan's National Health Insurance Research Database (NHIRD), this cohort study consisted of 58,618 patients, where 25,868 had T2DM, 32,750 had HTN, and 6419 had both T2DM and HTN. We analyzed the data with different machine learning models for the prediction of LoS and mortality. The evaluation was done by plotting descriptive statistical graphs, feature importance, precision-recall curve, accuracy plots, and AUC. The training and testing data were set at a ratio of 8:2 before applying ML algorithms. Results: XGBoost showed the best performance in predicting LoS (R2 0.633; RMSE 0.386; MAE 0.123), and RF resulted in a slightly lower performance (R2 0.591; RMSE 0.401; MAE 0.027). Logistic Regression (LoR) performed the best in predicting mortality (CV Score 0.9779; Test Score 0.9728; Precision 0.9432; Recall 0.9786; AUC 0.97 and AUPR 0.93), closely followed by Ridge Classifier (CV Score 0.9736; Test Score 0.9692; Precision 0.9312; Recall 0.9463; AUC 0.94 and AUPR 0.89). Conclusions: We developed a robust prediction model for LoS and mortality of T2DM and HTN inpatients. Linear Regression showed the best performance for LoS, and Logistic Regression performed the best in predicting mortality. The results showed that ML algorithms can not only help healthcare professionals in data-driven decision-making but can also facilitate early intervention and resource planning.

Minimum variance-embedded deep kernel regularized least squares method for one-class classification and its applications to biomedical data.

Deep kernel learning has been well explored for multi-class classification tasks; however, relatively less work is done for one-class classification (OCC). OCC needs samples from only one class to train the model. Most recently, kernel regularized least squares (KRL) method-based deep architecture is developed for the OCC task. This paper introduces a novel extension of this method by embedding minimum variance information within this architecture. This embedding improves the generalization capability of the classifier by reducing the intra-class variance. In contrast to traditional deep learning methods, this method can effectively work with small-size datasets. We conduct a comprehensive set of experiments on 18 benchmark datasets (13 biomedical and 5 other datasets) to demonstrate the performance of the proposed classifier. We compare the results with 16 state-of-the-art one-class classifiers. Further, we also test our method for 2 real-world biomedical datasets viz.; detection of Alzheimer's disease from structural magnetic resonance imaging data and detection of breast cancer from histopathological images. Proposed method exhibits more than 5% F1 score compared to existing state-of-the-art methods for various biomedical benchmark datasets. This makes it viable for application in biomedical fields where relatively less amount of data is available.

Dynamic optical contrast imaging as a novel modality for rapidly distinguishing head and neck squamous cell carcinoma from surrounding normal tissue.

BACKGROUND: Head and neck squamous cell carcinomas (HNSCCs) are debilitating diseases for which a patient's prognosis depends heavily on complete tumor resection. Currently, the surgeon's fingers determine the location of tissue margins. This study evaluated the diagnostic utility of a novel imaging modality, dynamic optical contrast imaging (DOCI), in the detection of HNSCC. This system generates contrast by illuminating the tissue with pulsed light and detecting variations in endogenous fluorophore lifetimes. METHODS: A total of 47 fresh ex vivo samples from 15 patients were imaged with the DOCI system immediately after surgical resection. DOCI maps were analyzed to determine the statistical significance of contrast between tumors and adjacent nonmalignant tissue. Pilot intraoperative clinical data were also acquired. RESULTS: Statistical significance (P < .05) between muscle and tumor was established for 10 of 10 emission wavelengths, between collagen and tumor for 8 of 10 emission wavelengths, and between fat and tumor for 2 of 10 wavelengths. The system extracted relative fluorescence decay information in a surgically relevant field of view in <2 minutes. CONCLUSIONS: This study demonstrates the feasibility of using DOCI to rapidly and accurately distinguish HNSCC from surrounding normal tissue. An analysis of DOCI images revealed microscopic characterization sufficient for tissue-type identification consistent with histology. Such an intraoperative tool would be transformative by allowing the rapid delineation of tumor tissue from nontumor tissue and thus maximizing the efficacy of resection and improving patient outcomes. Cancer 2017;123:879-86. © 2016 American Cancer Society.

Microarray Analysis of Differentially-Expressed Genes Encoding CYP450 and Phase II Drug Metabolizing Enzymes in Psoriasis and Melanoma.

Cytochrome P450 drug metabolizing enzymes are implicated in personalized medicine for two main reasons. First, inter-individual variability in CYP3A4 expression is a confounding factor during cancer treatment. Second, inhibition or induction of CYP3A4 can trigger adverse drug-drug interactions. However, inflammation can downregulate CYP3A4 and other drug metabolizing enzymes and lead to altered metabolism of drugs and essential vitamins and lipids. Little is known about effects of inflammation on expression of CYP450 genes controlling drug metabolism in the skin. Therefore, we analyzed seven published microarray datasets, and identified differentially-expressed genes in two inflammatory skin diseases (melanoma and psoriasis). We observed opposite patterns of expression of genes regulating metabolism of specific vitamins and lipids in psoriasis and melanoma samples. Thus, genes controlling the turnover of vitamin D (CYP27B1, CYP24A1), vitamin A (ALDH1A3, AKR1B10), and cholesterol (CYP7B1), were up-regulated in psoriasis, whereas melanomas showed downregulation of genes regulating turnover of vitamin A (AKR1C3), and cholesterol (CYP39A1). Genes controlling abnormal keratinocyte differentiation and epidermal barrier function (CYP4F22, SULT2B1) were up-regulated in psoriasis. The up-regulated CYP24A1, CYP4F22, SULT2B1, and CYP7B1 genes are potential drug targets in psoriatic skin. Both disease samples showed diminished drug metabolizing capacity due to downregulation of the CYP1B1 and CYP3A5 genes. However, melanomas showed greater loss of drug metabolizing capacity due to downregulation of the CYP3A4 gene.

Microarray analysis of differentially expressed genes regulating lipid metabolism during melanoma progression.

A new hallmark of cancer involves acquisition of a lipogenic phenotype which promotes tumorigenesis. Little is known about lipid metabolism in melanomas. Therefore, we used BRB (Biometrics Research Branch) class comparison tool with multivariate analysis to identify differentially expressed genes in human cutaneous melanomas, compared with benign nevi and normal skin derived from the microarray dataset (GDS1375). The methods were validated by identifying known melanoma biomarkers (CITED1, FGFR2, PTPRF, LICAM, SPP1 and PHACTR1) in our results. Eighteen genes regulating metabolism of fatty acids, lipid second messengers and gangliosides were 2-9 fold upregulated in melanomas of GDS-1375. Out of the 18 genes, 13 were confirmed by KEGG pathway analysis and 10 were also significantly upregulated in human melanoma cell lines of NCI-60 Cell Miner database. Results showed that melanomas upregulated PPARGC1A transcription factor and its target genes regulating synthesis of fatty acids (SCD) and complex lipids (FABP3 and ACSL3). Melanoma also upregulated genes which prevented lipotoxicity (CPT2 and ACOT7) and regulated lipid second messengers, such as phosphatidic acid (AGPAT-4, PLD3) and inositol triphosphate (ITPKB, ITPR3). Genes for synthesis of pro-tumorigenic GM3 and GD3 gangliosides (UGCG, HEXA, ST3GAL5 and ST8SIA1) were also upregulated in melanoma. Overall, the microarray analysis of GDS-1375 dataset indicated that melanomas can become lipogenic by upregulating genes, leading to increase in fatty acid metabolism, metabolism of specific lipid second messengers, and ganglioside synthesis.