A semi-supervised approach to unobtrusively predict abnormality in breathing patterns using hydraulic bed sensor data in older adults aging in place.

Shortness of breath is often considered a repercussion of aging in older adults, as respiratory illnesses like COPD1 or respiratory illnesses due to heart-related issues are often misdiagnosed, under-diagnosed or ignored at early stages. Continuous health monitoring using ambient sensors has the potential to ameliorate this problem for older adults at aging-in-place facilities. In this paper, we leverage continuous respiratory health data collected by using ambient hydraulic bed sensors installed in the apartments of older adults in aging-in-place Americare facilities to find data-adaptive indicators related to shortness of breath. We used unlabeled data collected unobtrusively over the span of three years from a COPD-diagnosed individual and used data mining to label the data. These labeled data are then used to train a predictive model to make future predictions in older adults related to shortness of breath abnormality. To pick the continuous changes in respiratory health we make predictions for shorter time windows (60-s). Hence, to summarize each day's predictions we propose an abnormal breathing index (ABI) in this paper. To showcase the trajectory of the shortness of breath abnormality over time (in terms of days), we also propose trend analysis on the ABI quarterly and incrementally. We have evaluated six individual cases retrospectively to highlight the potential and use cases of our approach.

Linguistic Explanations of Black Box Deep Learning Detectors on Simulated Aerial Drone Imagery.

Deep learning has become increasingly common in aerial imagery analysis. As its use continues to grow, it is crucial that we understand and can explain its behavior. One eXplainable AI (XAI) approach is to generate linguistic summarizations of data and/or models. However, the number of summaries can increase significantly with the number of data attributes, posing a challenge. Herein, we proposed a hierarchical approach for generating and evaluating linguistic statements of black box deep learning models. Our approach scores and ranks statements according to user-specified criteria. A systematic process was outlined for the evaluation of an object detector on a low altitude aerial drone. A deep learning model trained on real imagery was evaluated on a photorealistic simulated dataset with known ground truth across different contexts. The effectiveness and versatility of our approach was demonstrated by showing tailored linguistic summaries for different user types. Ultimately, this process is an efficient human-centric way of identifying successes, shortcomings, and biases in data and deep learning models.

Genetic interactions support an inhibitory relationship between bone morphogenetic protein 2 and netrin 1 during semicircular canal formation.

The semicircular canals of the mammalian inner ear are derived from epithelial pouches in which epithelial cells in the central region of each pouch undergo resorption, leaving behind the region at the rim to form a tube-shaped canal. Lack of proliferation at the rim and/or over-clearing of epithelial cells in the center of the pouch can obliterate canal formation. Otic-specific knockout of bone morphogenetic protein 2 (Bmp2) results in absence of all three semicircular canals; however, the common crus and ampullae housing the sensory tissue (crista) are intact. The lack of Bmp2 causes Ntn1 (which encodes netrin 1), which is required for canal resorption, to be ectopically expressed at the canal rim. Ectopic Ntn1 results in reduction of Dlx5 and Lmo4, which are required for rim formation. These phenotypes can be partially rescued by removing one allele of Ntn1 in the Bmp2 mutants, indicating that Bmp2 normally negatively regulates Ntn1 for canal formation. Additionally, non-resorption of the canal pouch in Ntn1-/- mutants is partially rescued by removing one allele of Bmp2 Thus, reciprocal inhibition between Bmp2 and netrin 1 is involved in canal formation of the vestibule.

New Linguistic Description Approach for Time Series and its Application to Bed Restlessness Monitoring for Eldercare.

Time series analysis has been an active area of research for years, with important applications in forecasting or discovery of hidden information such as patterns or anomalies in observed data. In recent years, the use of time series analysis techniques for the generation of descriptions and summaries in natural language of any variable, such as temperature, heart rate or CO2 emission has received increasing attention. Natural language has been recognized as more effective than traditional graphical representations of numerical data in many cases, in particular in situations where a large amount of data needs to be inspected or when the user lacks the necessary background and skills to interpret it. In this work, we describe a novel mechanism to generate linguistic descriptions of time series using natural language and fuzzy logic techniques. The proposed method generates quality summaries capturing the time series features that are relevant for a user in a particular application, and can be easily customized for different domains. This approach has been successfully applied to the generation of linguistic descriptions of bed restlessness data from residents at TigerPlace (Columbia, Missouri), which is used as a case study to illustrate the modeling process and show the quality of the descriptions obtained.

Tracking personalized functional health in older adults using geriatric assessments.

BACKGROUND: Higher levels of functional health in older adults leads to higher quality of life and improves the ability to age-in-place. Tracking functional health objectively could help clinicians to make decisions for interventions in case of health deterioration. Even though several geriatric assessments capture several aspects of functional health, there is limited research in longitudinally tracking personalized functional health of older adults using a combination of these assessments. METHODS: We used geriatric assessment data collected from 150 older adults to develop and validate a functional health prediction model based on risks associated with falls, hospitalizations, emergency visits, and death. We used mixed effects logistic regression to construct the model. The geriatric assessments included were Activities of Daily Living (ADL), Instrumental Activities of Daily Living (IADL), Mini-Mental State Examination (MMSE), Geriatric Depression Scale (GDS), and Short Form 12 (SF12). Construct validators such as fall risks associated with model predictions, and case studies with functional health trajectories were used to validate the model. RESULTS: The model is shown to separate samples with and without adverse health event outcomes with an area under the receiver operating characteristic curve (AUC) of > 0.85. The model could predict emergency visit or hospitalization with an AUC of 0.72 (95% CI 0.65-0.79), fall with an AUC of 0.86 (95% CI 0.83-0.89), fall with hospitalization with an AUC of 0.89 (95% CI 0.85-0.92), and mortality with an AUC of 0.93 (95% CI 0.88-0.97). Multiple comparisons of means using Turkey HSD test show that model prediction means for samples with no adverse health events versus samples with fall, hospitalization, and death were statistically significant (p < 0.001). Case studies for individual residents using predicted functional health trajectories show that changes in model predictions over time correspond to critical health changes in older adults. CONCLUSIONS: The personalized functional health tracking may provide clinicians with a longitudinal view of overall functional health in older adults to help address the early detection of deterioration trends and decide appropriate interventions. It can also help older adults and family members take proactive steps to improve functional health.

Persistent Metastatic Thyroid Carcinoma.

The decision to biopsy small thyroid nodules (TNs) is controversial. Careful ultrasound (US) evaluation with shear wave elastography (SWE) of TN and cervical lymph nodes (LNs) may aid in the decision to biopsy and subsequently influence the extent of surgery. A 46-year-old female presented with TNs and hypothyroidism. Her target TN in the left lobe measured 4.8 mm × 4 mm × 4 mm. Fine needle aspiration biopsy of the left TN and a left neck level 6 LN was diagnostic for papillary thyroid carcinoma. In the left lateral neck posterior to the jugular vein, there was a LN with possible microcalcifications that could not be sampled due to vascular proximity. SWE examination showed high velocity suspicious for metastatic disease. In summary, risk stratification for small TNs and cervical LNs can be difficult. SWE can provide valuable information for assessing the risk for malignancy.

Linguistic summarization of in-home sensor data.

INTRODUCTION: With the increase in the population of older adults around the world, a significant amount of work has been done on in-home sensor technology to aid the elderly age independently. However, due to the large amounts of data generated by the sensors, it takes a lot of effort and time for the clinicians to makes sense of this data. In this work, we develop a system to help make this data more useful by presenting it in the form of natural language. METHODS: We start by identifying important attributes in the sensor data that are relevant to the health of the elderly. We then develop algorithms to extract these important health related features from the sensor parameters and summarize them in natural language. We focus on making the natural language summaries to be informative, accurate and concise. RESULTS: We designed multiple surveys using real and synthetic data to validate the summaries produced by our algorithms. We show that the algorithms produce meaningful results comparable to human subjects. We also implemented our linguistic summarization system to produce summaries of data leading to health alerts derived from the sensor data. The system is running live in 110 apartments currently. By the means of retrospective case studies, we illustrate that the linguistic summaries are able to make the connection between changes in the sensor data and the health of the elderly. CONCLUSIONS: We present a system that extracts important clinically relevant features from in-home sensor data generated in the apartments of the elderly and summarize those features in natural language. The preliminary testing of our summarization system shows that it has the potential to help the clinicians utilize this data effectively.

A phosphoarray platform is capable of personalizing kinase inhibitor therapy in head and neck cancers.

Tyrosine kinase inhibitors are effective treatments for cancers. Knowing the specific kinase mutants that drive the underlying cancers predict therapeutic response to these inhibitors. Thus, the current protocol for personalized cancer therapy involves genotyping tumors in search of various driver mutations and subsequently individualizing the tyrosine kinase inhibitor to the patients whose tumors express the corresponding driver mutant. While this approach works when known driver mutations are found, its limitation is the dependence on driver mutations as predictors for response. To complement the genotype approach, we hypothesize that a phosphoarray platform is equally capable of personalizing kinase inhibitor therapy. We selected head and neck squamous cell carcinoma as the cancer model to test our hypothesis. Using the receptor tyrosine kinase phosphoarray, we identified the phosphorylation profiles of 49 different tyrosine kinase receptors in five different head and neck cancer cell lines. Based on these results, we tested the cell line response to the corresponding kinase inhibitor therapy. We found that this phosphoarray accurately informed the kinase inhibitor response profile of the cell lines. Next, we determined the phosphorylation profiles of 39 head and neck cancer patient derived xenografts. We found that absent phosphorylated EGFR signal predicted primary resistance to cetuximab treatment in the xenografts without phosphorylated ErbB2. Meanwhile, absent ErbB2 signaling in the xenografts with phosphorylated EGFR is associated with a higher likelihood of response to cetuximab. In summary, the phosphoarray technology has the potential to become a new diagnostic platform for personalized cancer therapy.

Society for maternal-fetal medicine (SMFM) special report: the maternal-fetal medicine subspecialists' role within a health care system.

A maternal-fetal medicine (MFM) subspecialist has advanced knowledge of the medical, surgical, obstetrical, fetal, and genetic complications of pregnancy and their effects on both the mother and fetus. MFM subspecialists are complementary to obstetric care providers in providing consultations, co-management, or transfer of care for complicated patients before, during, and after pregnancy. The MFM subspecialist provides peer and patient education and performs research concerning the most recent approaches and treatments for obstetrical problems, thus promoting risk-appropriate care for these complicated pregnancies. The relationship between the obstetric care provider and the MFM subspecialist depends on the acuity of the maternal and/or fetal condition and the local resources. To achieve the goal of promoting early access and sustained adequate prenatal care for all pregnant women, we encourage collaboration with obstetricians, family physicians, certified midwives, and others, and we also encourage providing preconception, prenatal, and postpartum care counseling and coordination. Effective communication between all obstetric care team members is imperative. This special report was written with the intent that it would be broad in scope and appeal to a diverse readership, including administrators, allowing it to be applied to various systems of care both horizontally and vertically. We understand that these relationships are often complex and there are more models of care than could be addressed in this document. However, we aimed to promote the development of a highly effective team approach to the care of the high-risk pregnancy that will be useful in the most common models for obstetric care in the United States. The MFM subspecialist functions most effectively within a fully integrated and collaborative health care environment. This document defines the various roles that the MFM subspecialist can fulfill within different heath care systems through consultation, co-management, and transfer of care, as well as education, research, and leadership.

A roundtable discussion: home healthcare-not a hospital in the home.

Home healthcare is vital for a large percentage of the population. According to data from the U.S. Food and Drug Administration (FDA) and the Centers for Disease Control (CDC), 7 million people in the United States receive home healthcare annually. The use of medical devices in the home and other nonclinical environments is increasing dramatically. By the year 2050, an estimated 27 million people will need continuing care in the home or in the community and not in a controlled clinical environment. 1 The FDA recently announced its Home Use Devices Initiative and issued the document, "Draft Guidance for Industry and FDA Staff-Design Considerations for Devices Intended for Home Use" on Dec. 12, 2012. 2 The Center for Devices and Radiological Health (CDRH) regulates medical devices, but that regulatory authority alone is not enough to ensure safe and effective use of devices in the home. To address these and other issues, AAMI and FDA will co-host a summit on healthcare technology in nonclinical settings Oct. 9-10, 2013.

Genome-wide linkage analyses identify Hfhl1 and Hfhl3 with frequency-specific effects on the hearing spectrum of NIH Swiss mice.

BACKGROUND: The mammalian cochlea receives and analyzes sound at specific places along the cochlea coil, commonly referred to as the tonotopic map. Although much is known about the cell-level molecular defects responsible for severe hearing loss, the genetics responsible for less severe and frequency-specific hearing loss remains unclear. We recently identified quantitative trait loci (QTLs) Hfhl1 and Hfhl2 that affect high-frequency hearing loss in NIH Swiss mice. Here we used 2f1-f2 distortion product otoacoustic emissions (DPOAE) measurements to refine the hearing loss phenotype. We crossed the high frequency hearing loss (HFHL) line of NIH Swiss mice to three different inbred strains and performed linkage analysis on the DPOAE data obtained from the second-generation populations. RESULTS: We identified a QTL of moderate effect on chromosome 7 that affected 2f1-f2 emissions intensities (Hfhl1), confirming the results of our previous study that used auditory brainstem response (ABR) thresholds to identify QTLs affecting HFHL. We also identified a novel significant QTL on chromosome 9 (Hfhl3) with moderate effects on 2f1-f2 emissions intensities. By partitioning the DPOAE data into frequency subsets, we determined that Hfhl1 and Hfhl3 affect hearing primarily at frequencies above 24 kHz and 35 kHz, respectively. Furthermore, we uncovered additional QTLs with small effects on isolated portions of the DPOAE spectrum. CONCLUSIONS: This study identifies QTLs with effects that are isolated to limited portions of the frequency map. Our results support the hypothesis that frequency-specific hearing loss results from variation in gene activity along the cochlear partition and suggest a strategy for creating a map of cochlear genes that influence differences in hearing sensitivity and/or vulnerability in restricted portions of the cochlea.

Ethics guidelines for research with the recently dead.

The objective of the multidisciplinary expert Consensus Panel on Research with the Recently Dead (CPRRD) was to craft ethics guidelines for research with the recently dead. The CPRRD recommends that research with the recently dead: (i) receive scientific and ethical review and oversight; (ii) involve the community of potential research subjects; (iii) be coordinated with organ procurement organizations; (iv) not conflict with organ donation or required autopsy; (v) use procedures respectful of the dead; (vi) be restricted to one procedure per day; (vii) preferably be authorized by first-person consent, though both general advance research directives and surrogate consent are acceptable; (viii) protect confidentiality; (ix) not impose costs on subjects' estates or next of kin and not involve payment; (x) clearly explain ultimate disposition of the body.

Clinical alarm hazards: a "top ten" health technology safety concern.

For the past several years ECRI Institute has published a list of Top Ten Health Technology Hazards. This list is based on ECRI's extensive research in health technology safety and on data provided to its problemreporting systems. For every year that the Top Ten list has been published, Alarm Hazards have been at or near the top of the list. Improving alarm safety requires a systematic review of a hospital's alarm-based technologies and analysis of alarm management policies like alarm escalation strategies and staffing patterns. It also requires careful selection of alarm setting criteria for each clinical care area. This article will overview the clinical alarm problems that have been identified through ECRI Institute's research and analysis of various problem reporting databases, including those operated by ECRI Institute. It will also highlight suggestions for improvement, particularly from a technology design and technology management perspective.

Explainable Fall Risk Prediction in Older Adults Using Gait and Geriatric Assessments.

Older adults aged 65 and above are at higher risk of falls. Predicting fall risk early can provide caregivers time to provide interventions, which could reduce the risk, potentially avoiding a possible fall. In this paper, we present an analysis of 6-month fall risk prediction in older adults using geriatric assessments, GAITRite measurements, and fall history. The geriatric assessments included were Activities of Daily Living (ADL), Instrumental Activities of Daily Living (IADL), Mini-Mental State Examination (MMSE), Geriatric Depression Scale (GDS), and Short Form 12 (SF12). These geriatric assessments are collected by staff nurses regularly in senior care facilities. From the GAITRite assessments on the residents, we included the Functional Ambulatory Profile (FAP) scores and gait speed to predict fall risk. We used the SHAP (SHapley Additive exPlanations) approach to explain our model predictions to understand which predictor variables contributed to increase or decrease the fall risk for an individual prediction. In case of a high fall risk prediction, predictor variables that contributed the most to elevate the risk could be further examined by the health providers for more personalized health interventions. We used the geriatric assessments, GAITRite measurements, and fall history data collected from 92 older adult residents (age = 86.2 ± 6.4, female = 57) to train machine learning models to predict 6-month fall risk. Our models predicted a 6-month fall with an AUC of 0.80 (95% CI of 0.76-0.85), sensitivity of 0.82 (95% CI of 0.74-0.89), specificity of 0.72 (95% CI of 0.67-0.76), F1 score of 0.76 (95% CI of 0.72-0.79), and accuracy of 0.75 (95% CI of 0.72-0.79). These results show that our early fall risk prediction method performs well in identifying residents who are at higher fall risk, which offers care providers and family members valuable time to perform preventive actions.

Artificial Intelligence to Aid Glaucoma Diagnosis and Monitoring: State of the Art and New Directions.

Recent developments in the use of artificial intelligence in the diagnosis and monitoring of glaucoma are discussed. To set the context and fix terminology, a brief historic overview of artificial intelligence is provided, along with some fundamentals of statistical modeling. Next, recent applications of artificial intelligence techniques in glaucoma diagnosis and the monitoring of glaucoma progression are reviewed, including the classification of visual field images and the detection of glaucomatous change in retinal nerve fiber layer thickness. Current challenges in the direct application of artificial intelligence to further our understating of this disease are also outlined. The article also discusses how the combined use of mathematical modeling and artificial intelligence may help to address these challenges, along with stronger communication between data scientists and clinicians.

Mechanism-Driven Modeling to Aid Non-invasive Monitoring of Cardiac Function via Ballistocardiography.

Left ventricular (LV) catheterization provides LV pressure-volume (P-V) loops and it represents the gold standard for cardiac function monitoring. This technique, however, is invasive and this limits its applicability in clinical and in-home settings. Ballistocardiography (BCG) is a good candidate for non-invasive cardiac monitoring, as it is based on capturing non-invasively the body motion that results from the blood flowing through the cardiovascular system. This work aims at building a mechanistic connection between changes in the BCG signal, changes in the P-V loops and changes in cardiac function. A mechanism-driven model based on cardiovascular physiology has been used as a virtual laboratory to predict how changes in cardiac function will manifest in the BCG waveform. Specifically, model simulations indicate that a decline in LV contractility results in an increase of the relative timing between the ECG and BCG signal and a decrease in BCG amplitude. The predicted changes have subsequently been observed in measurements on three swine serving as pre-clinical models for pre- and post-myocardial infarction conditions. The reproducibility of BCG measurements has been assessed on repeated, consecutive sessions of data acquisitions on three additional swine. Overall, this study provides experimental evidence supporting the utilization of mechanism-driven mathematical modeling as a guide to interpret changes in the BCG signal on the basis of cardiovascular physiology, thereby advancing the BCG technique as an effective method for non-invasive monitoring of cardiac function.

Noninvasive cardiovascular monitoring based on electrocardiography and ballistocardiography: a feasibility study on patients in the surgical intensive care unit.

The time interval between the peaks in the electroccardiogram (ECG) and ballistocardiogram (BCG) waveforms, TEB, has been associated with the pre-ejection period (PEP), which is an important marker of ventricular contractility. However, the applicability of BCG-related markers in clinical practice is limited by the difficulty to obtain a replicable and consistent signal on patients. In this study, we test the feasibility of BCG measurements within a complex clinical setting, by means of an accelerometer under the head pillow of patients admitted to the Surgical Intensive Care Unit (SICU). The proposed technique proved capable of capturing TEB based on the R peaks in the ECG and the BCG in its head-to-toe and dorso- ventral directions. TEB detection was found to be consistent and repeatable both in healthy individuals and SICU patients over multiple data acquisition sessions. This work provides a promising starting point to investigate how TEB changes may relate to the patients' complex health conditions and give additional clinical insight into their care needs.

Combining Physiology-Based Modeling and Evolutionary Algorithms for Personalized, Noninvasive Cardiovascular Assessment Based on Electrocardiography and Ballistocardiography.

Purpose: This study proposes a novel approach to obtain personalized estimates of cardiovascular parameters by combining (i) electrocardiography and ballistocardiography for noninvasive cardiovascular monitoring, (ii) a physiology-based mathematical model for predicting personalized cardiovascular variables, and (iii) an evolutionary algorithm (EA) for searching optimal model parameters. Methods: Electrocardiogram (ECG), ballistocardiogram (BCG), and a total of six blood pressure measurements are recorded on three healthy subjects. The R peaks in the ECG are used to segment the BCG signal into single BCG curves for each heart beat. The time distance between R peaks is used as an input for a validated physiology-based mathematical model that predicts distributions of pressures and volumes in the cardiovascular system, along with the associated BCG curve. An EA is designed to search the generation of parameter values of the cardiovascular model that optimizes the match between model-predicted and experimentally-measured BCG curves. The physiological relevance of the optimal EA solution is evaluated a posteriori by comparing the model-predicted blood pressure with a cuff placed on the arm of the subjects to measure the blood pressure. Results: The proposed approach successfully captures amplitudes and timings of the most prominent peak and valley in the BCG curve, also known as the J peak and K valley. The values of cardiovascular parameters pertaining to ventricular function can be estimated by the EA in a consistent manner when the search is performed over five different BCG curves corresponding to five different heart-beats of the same subject. Notably, the blood pressure predicted by the physiology-based model with the personalized parameter values provided by the EA search exhibits a very good agreement with the cuff-based blood pressure measurement. Conclusion: The combination of EA with physiology-based modeling proved capable of providing personalized estimates of cardiovascular parameters and physiological variables of great interest, such as blood pressure. This novel approach opens the possibility for developing quantitative devices for noninvasive cardiovascular monitoring based on BCG sensing.

Extending the Morphological Hit-or-Miss Transform to Deep Neural Networks.

While most deep learning architectures are built on convolution, alternative foundations such as morphology are being explored for purposes such as interpretability and its connection to the analysis and processing of geometric structures. The morphological hit-or-miss operation has the advantage that it considers both foreground information and background information when evaluating the target shape in an image. In this article, we identify limitations in the existing hit-or-miss neural definitions and formulate an optimization problem to learn the transform relative to deeper architectures. To this end, we model the semantically important condition that the intersection of the hit and miss structuring elements (SEs) should be empty and present a way to express Don't Care (DNC), which is important for denoting regions of an SE that are not relevant to detecting a target pattern. Our analysis shows that convolution, in fact, acts like a hit-to-miss transform through semantic interpretation of its filter differences. On these premises, we introduce an extension that outperforms conventional convolution on benchmark data. Quantitative experiments are provided on synthetic and benchmark data, showing that the direct encoding hit-or-miss transform provides better interpretability on learned shapes consistent with objects, whereas our morphologically inspired generalized convolution yields higher classification accuracy. Finally, qualitative hit and miss filter visualizations are provided relative to single morphological layer.