Over the last ten years, there has been considerable progress in using digital behavioral phenotypes, captured passively and continuously from smartphones and wearable devices, to infer depressive mood. However, most digital phenotype studies suffer from poor replicability, often fail to detect clinically relevant events, and use measures of depression that are not validated or suitable for collecting large and longitudinal data. Here, we report high-quality longitudinal validated assessments of depressive mood from computerized adaptive testing paired with continuous digital assessments of behavior from smartphone sensors for up to 40 weeks on 183 individuals experiencing mild to severe symptoms of depression. We apply a combination of cubic spline interpolation and idiographic models to generate individualized predictions of future mood from the digital behavioral phenotypes, achieving high prediction accuracy of depression severity up to three weeks in advance (R2 ≥ 80%) and a 65.7% reduction in the prediction error over a baseline model which predicts future mood based on past depression severity alone. Finally, our study verified the feasibility of obtaining high-quality longitudinal assessments of mood from a clinical population and predicting symptom severity weeks in advance using passively collected digital behavioral data. Our results indicate the possibility of expanding the repertoire of patient-specific behavioral measures to enable future psychiatric research.

Left ventricular ejection fraction (EF) is a predictor of mortality and guides clinical decisions. Although transthoracic echocardiography (TTE) is commonly used for measuring EF, it has limitations, such as subjectivity and requires expert personnel. Advancements in biosensor technology and artificial intelligence are allowing systems capable of determining left ventricular function and providing automated measurement of EF. In this study, we tested new wearable automated real-time biosensors (Cardiac Performance System [CPS]) that compute EF using waveform machine learning on cardiac acoustic signals. The primary aim was to compare the accuracy of CPS EF with TTE EF. Adult patients presenting to cardiology, presurgical, and diagnostic radiology clinical settings in an academic center were enrolled. TTE examination was performed by a sonographer, followed immediately by a 3-minute recording of acoustic signals from CPS biosensors placed on the chest by nonexpert personnel. TTE EF was calculated offline using the Simpson biplane method. A total of 81 patients (aged 19 to 88 years, 27 women, 20% to 80% EF) were included. Deming regression and Bland-Altman analysis were performed to assess the accuracy of CPS EF against TTE EF. Both Deming regression (slope 0.9981; intercept 0.03415%) and Bland-Altman analysis (bias -0.0247%; limits of agreement [-11.65, 11.60]%) demonstrated equivalency between CPS EF and TTE EF. The receiver operating characteristic for measuring sensitivity and specificity of CPS in identifying subjects with abnormal EF showed an area under the curve value of 0.974 for identifying EF <35% and 0.916 for detecting EF <50% CPS EF intraoperator and interoperator assessments demonstrated low variability. In conclusion, this technology measuring cardiac function from noninvasive biosensors and machine learning on acoustic signals provides an accurate EF measurement that is automated, real-time, and acquired rapidly by personnel with minimal training. & COPY; 2023 Elsevier Inc. All rights reserved. (Am J Cardiol 2023

As landscapes become increasingly fragmented, research into impacts from disturbance and how edges affect vegetation and community structure has become more important. Descriptive studies on how microclimate changes across sharp transition zones have long existed in the literature and recently more attention has been focused on understanding the dynamic patterns of microclimate associated with forest edges. Increasing concern about forest fragmentation has led to new technologies for modeling forest microclimates. However, forest boundaries pose important challenges to not only microclimate modeling but also sampling regimes in order to capture the diurnal and seasonal dynamic aspects of microclimate along forest edges. We measured microclimatic variables across a sharp boundary from a clearing into primary lowland tropical rainforest at La Selva Biological Station in Costa Rica. Dynamic changes in diurnal microclimate were measured along three replicated transects, approximately 30 m in length with data collected every 1 m continuously at 30 min intervals for 24 h with a mobile sensor platform supported by a cable infrastructure. We found that a first-order polynomial fit using piece-wise regression provided the most consistent estimation of the forest edge, relative to the visual edge, although we found no “best” sensing parameter as all measurements varied. Edge location estimates based on daytime net shortwave radiation had less difference from the visual edge than other shortwave measurements, but estimates made throughout the day with downward-facing or net infrared radiation sensors were more consistent and closer to the visual edge than any other measurement. This research contributes to the relatively small number of studies that have directly measured diurnal temporal and spatial patterns of microclimate variation across forest edges and demonstrates the use of a flexible mobile platform that enables repeated, high-resolution measurements of gradients of microclimate.

Detection of heart failure with preserved ejection fraction (HFpEF) by non-expert clinicians requires training and experience in operating Doppler echocardiography machines. Doppler echocardiography records were obtained for 18 patients scheduled to undergo right heart catheterization at the Oregon

This paper presents a fully-automated end-to-end phonocardiogram(PCG)-based wearable system capable of providing echocardiography-like metrics for left ventricular (LV) diastolic function assessment. Proxy metrics for five echocardiographic parameters were calculated based on physiologically-motivated features extracted from PCG signals using noise-subtraction, heartbeat-segmentation, and quality-assurance algorithms. The clinical value of these proxy metrics was evaluated using the latest American Society of Echocardiography/European Association of Cardiovascular Imaging guidelines for evaluation of LV diastolic function. When tested on a group of n=34 patients, proxy metrics successfully identified LV diastolic dysfunction in a n=29 subset with 87.5% accuracy, and elevated LV filling pressures in a n=17 subset with 75% accuracy.

Wearable devices offer a promise of immense impact on worldwide global health by offering the potential for non-invasive, constantly vigilant, and low-cost monitoring of individual condition and fundamental advances in guiding healthcare. The urgency of this objective for its individual and societal benefits will attract an expanding community of researchers from backgrounds in nearly every field of computing. This article describes the unprecedented benefits and opportunities for computing research in wearable devices and the multidisciplinary challenges that have not been encountered individually or combined together in previous research. This article is focused on providing guidance to the new community of healthcare in computing researchers who will both create a new field and forge transformative solutions for healthcare delivery to a worldwide population.

The irreversible damage and eventual heart failure caused by untreated aortic stenosis (AS) can be prevented by early detection and timely intervention. Prior work in the field of phonocardiogram (PCG) signal analysis has provided proof of concept for using heart-sound data in AS diagnosis. However, such systems either require operation by trained technicians, fail to address a diverse subject set, or involve unwieldy configuration procedures that challenge real-world application. This paper presents an end-to-end, fully-automated system that uses noise-subtraction, heartbeat-segmentation and quality-assurance algorithms to extract physiologically-motivated features from PCG signals to diagnose AS. When tested on n=96 patients showing a diverse set of cardiac and non-cardiac conditions, the system was able to diagnose AS with 92% sensitivity and 95% specificity.

This paper presents a novel method for automatically detecting the onset of ventricular depolarization in electrocardiogram (ECG). In order to accommodate highly variable ECG morphologies in potentially noisy ECG signals, a weighted combination of factors that are consistent with the onset of ventricular depolarization is computed. Weight parameters are optimized to maximize the detection accuracy. The proposed method is evaluated against diverse datasets, yielding a bias of 1.69 ms, standard deviation of 10.55 ms, and mean absolute error of 6.68 ms.

Significance Caspase-8–mediated apoptotic and receptor-interacting protein (RIP)-dependent necroptotic signaling pathways are recognized host defense mechanisms that act by eliminating virus-infected cells. Cytomegalovirus-encoded inhibitors of apoptosis and necroptosis sustain infection and pathogenesis by preventing specific programmed cell death pathways. In the absence of viral inhibitors, combined apoptotic–necroptotic cell death signaling halts infection, preventing the virus from gaining a foothold in the host. We describe natural cooperation between apoptosis and necroptosis pathways in macrophages and within the host, resulting in robust proinflammatory cytokine responses not observed when infected cells die by either apoptosis or necroptosis alone. Thus, apoptosis combined with necroptosis serves a dual role in limiting herpesvirus persistence in the host.

3,662,595 5/1972 Hurlburt et al. ...................... 73/141 R 4,009,607 3/1977 Ficken .......... . 73/141R 4,577,493 3/1986 Oesterde ...................................... 73/81 4,584.885 4/1986 Codwell ... 73/862.61 4,598.586 7/1986 Danielson ................ . 73/517 B 4,724,709 2/1988 Antonazzi, Sr. et al. ... 73/701 4,740,410 4/1988 Muller et al. ................ ... 428/133 4,851,080 7/1989 Howe et al. ......... ... 156/647 4,856.338 8/1989 Philippi et al. .......................... 73/701 4,887,467 12/1989 Sakuma et al. .. . 73/517 B 4,891,982 1/1990 Nording ..................................... 73/497 4,896,098 1/1990 Haritonidis et al. . ... 324/663 4,922,159 5/1990 Phillips et al........ ... 318/128 4,945,765 8/1990 Roszhart ................................... 73/517 4,987,779 1/1991 McBrien ... 73/517 B 5,006,487 4/1991 Stokes ... 437/228 5,054,320 10/1991 Yvon ........ 73/517 B 5,103,667 4/1992 Allen et al. ............................... 73/1 D 5,111,693 5/1992 Greiff ....... 73/514 5,115,291 5/1992 Stokes ....................................... 357/26 5,129,983 7/1992 Greiff ............... ... 156/628 5,149,673 9/1992 MacDonald et al. ... 437/192 5,159,277 10/1992 Mount ..................................... 324/721 US005659 195A

Profiling the daily activity of a physically disabled person in the community would enable healthcare professionals to monitor the type, quantity, and quality of their patients' compliance with recommendations for exercise, fitness, and practice of skilled movements, as well as enable feedback about performance in real-world situations. Based on our early research in in-community activity profiling, we present in this paper an end-to-end system capable of reporting a patient's daily activity at multiple levels of granularity: 1) at the highest level, information on the location categories a patient is able to visit; 2) within each location category, information on the activities a patient is able to perform; and 3) at the lowest level, motion trajectory, visualization, and metrics computation of each activity. Our methodology is built upon a physical activity prescription model coupled with MEMS inertial sensors and mobile device kits that can be sent to a patient at home. A novel context-guided activity-monitoring concept with categorical location context is used to achieve enhanced classification accuracy and throughput. The methodology is then seamlessly integrated with motion reconstruction and metrics computation to provide comprehensive layered reporting of a patient's daily life. We also present an implementation of the methodology featuring a novel location context detection algorithm using WiFi augmented GPS and overlays, with motion reconstruction and visualization algorithms for practical in-community deployment. Finally, we use a series of experimental field evaluations to confirm the accuracy of the system.

Human activity monitoring systems using inertial sensors have found wide applications in the field of health and wellness by providing valuable information for diagnostics and rehabilitation processes to doctors and clinicians. As the scales of studies increase, sensor orientation placement errors have become one of the most commonly seen difficulties for such systems. Assuming patients to wear sensors at the correct orientation is unrealistic and will result in a large amount of data loss or distortion. In order to tackle this problem, we propose a double layer classification model. The first layer, not assuming correct sensor orientation, uses orientation-invariant accelerometer magnitude to construct a highly conservative walking detection model. The detected walking beacons from this layer are used to compare to the training template to obtain the true sensor orientation. Then proper rotation matrix can be applied to the whole day data, and fed into the second layer of a finer classifier where orientation-variant features are used. In order to show validity of this method, we hired 7 healthy subjects and 2 stroke patients in the rehab process to wear the sensors for two days and at least 6 hours each day. Ground truth are labeled manually with a Matlab GUI tool. Precision and recall for walking detection in each day are reported and discussed.

Postoperative ileus (POI) can worsen outcomes, increase cost, and prolong hospitalization. We previously found that a disposable, non-invasive acoustic gastrointestinal surveillance (AGIS) biosensor distinguishes healthy controls from patients recovering from abdominal surgery. Here, we tested whether AGIS can prospectively predict which patients will develop POI in a multicenter study.

Failure to detect changes in patients' postoperative health status increases the risk of adverse outcomes, including complications and readmission. We sought to design and implement a real-time surveillance system for postoperative colorectal surgery patients using wireless health technology. Participants were assigned a preprogrammed tablet computer during their inpatient hospitalization, and asked to complete a daily survey regarding their postoperative health status until their first clinic visit. Surveys were transmitted wirelessly to a secure database for review. As a pilot study, we report on our first 20 consecutively enrolled patients, monitored for 265 patient days. Overall compliance was 63 per cent (data available for 166 of the 265 days), but varied by patient from 26 to 100 per cent. We were able to reliably collect basic data on postoperative health status as well as patient-reported outcomes not previously captured by standard assessment techniques. Qualitative data suggest that the experience strengthened patients' relationship with their surgeon and aided in their recovery. Postoperative remote monitoring is feasible, and provides more detailed and complete information to the clinical team. Wireless health technology represents an opportunity to close the information gap between discharge and first clinic visit, and, eventually, to improve patient-provider communication, increase patient satisfaction, and prevent unnecessary readmissions.

This study uses high-frequency appliance-level electricity consumption data for 124 apartments over 24 months to provide a better understanding of appliance-level electricity consumption behavior. We conduct our analysis in a standardized set of apartments with similar appliances, which allows us to identify behavioral differences in electricity use. The Results show that households' estimations of appliance-level consumption are inaccurate and that they overestimate lighting use by 75% and underestimate plug-load use by 29%. We find that similar households using the same major appliances exhibit substantial variation in appliance-level electricity consumption. For example, households in the 75th percentile of HVAC usage use over four times as much electricity as a user in the 25th percentile. Additionally, we show that behavior accounts for 25–58% of this variation. Lastly, we find that replacing the existing refrigerator with a more energy-efficient model leads to overall energy savings of approximately 11%. This is equivalent to results from behavioral interventions targeting all appliances but might not be as cost effective. Our findings have important implications for behavior-based energy conservation policies.

Background: Postoperative ileus (POI) can worsen outcomes, increase cost, and prolong hospitalization.An objective marker could help identify POI patients who should not follow standardized enhanced recovery pathways.We developed a disposable, non-invasive wearable biosensor that adheres to the external abdominal wall and monitors intra-abdominal acoustic events.Specialized software identifies stereotyped motility sounds while gating-out extraneous noise; the result is an "intestinal rate" (IR) of motility events per minute.Previous research found the sensor distinguishes POI from non-POI subjects in cross-sectional analysis (J Gastrointest Surg 2014;18:1795).The current study performed longitudinal monitoring of GI motility, akin to "GI telemetry," to examine differences in post-op motility between POI and non-POI subjects.Methods: We studied a small, disposable sensor with a highfidelity microphone that adheres externally to the abdominal wall (Figure 1).The device connects to a bedside computer that uses an acoustic signal processing system to measure and display motility events.We recruited subjects to wear the device both 30 minutes before and continuously after colorectal surgery.We calculated mean IR every hour until discharge and separated patients into those with vs. without POI during their post-op course.We defined POI as vomiting, need for nasogastric decompression, or imaging consistent with ileus.We used t-tests to compare: 1) mean IR in POI vs. non-POI groups across all postop days (PODs); 2) relative change in IR from POD#1 to POD#2; and 3) across all subjects, mean IR on days with evidence of POI vs. no POI.Results: Continuous GI telemetry was performed on 12 subjects (4 POI; 8 non-POI; age=54+13; 50%M).Figure 2 shows a sample tracing in a POI subject with persistently low IR.Mean IR was 45% lower in POI vs. non-POI groups (1.6 vs. 2.9 events/min; p<0.001).Across all subjects, IR was lower in days with POI vs. without POI (2.1 vs. 3.5 events/min; p<0.001).The first 24 hours after surgery revealed high variability in motility among subjects and no difference in IR between groups.However, in POI subjects, IR dropped by 48% between POD#1 and POD#2, whereas non-POI subjects had a 38% increase in IR during the same period (p<0.006).There were no differences in immediate pre-op IR between groups.Conclusion: Non-invasive, abdominal acoustic monitoring with "GI telemetry" distinguishes POI from non-POI subjects.Immediate pre-and post-op motility is difficult to interpret and may not predict POI, but evidence of decreasing IR between POD#1 and #2 indicates evolving POI and should raise caution with advancing feeds.Future research will evaluate variations in post-op IR in a larger sample and determine whether "GI telemetry" can assist with safe and effective post-op decisions about feeding and timing of discharge.