High-frequency temperature monitoring for early detection of febrile adverse events in patients with cancer

Data Preprocessing Techniques for AI and Machine Learning Readiness: Scoping Review of Wearable Sensor Data in Cancer Care

BACKGROUND

Wearable sensors are increasingly being explored in health care, including in cancer care, for their potential in continuously monitoring patients. Despite their growing adoption, significant challenges remain in the quality and consistency of data collected from wearable sensors. Moreover, preprocessing pipelines to clean, transform, normalize, and standardize raw data have not yet been fully optimized.

OBJECTIVE

This study aims to conduct a scoping review of preprocessing techniques used on raw wearable sensor data in cancer care, specifically focusing on methods implemented to ensure their readiness for artificial intelligence and machine learning (AI/ML) applications. We sought to understand the current landscape of approaches for handling issues, such as noise, missing values, normalization or standardization, and transformation, as well as techniques for extracting meaningful features from raw sensor outputs and converting them into usable formats for subsequent AI/ML analysis.

METHODS

We systematically searched IEEE Xplore, PubMed, Embase, and Scopus to identify potentially relevant studies for this review. The eligibility criteria included (1) mobile health and wearable sensor studies in cancer, (2) written and published in English, (3) published between January 2018 and December 2023, (4) full text available rather than abstracts, and (5) original studies published in peer-reviewed journals or conferences.

RESULTS

The initial search yielded 2147 articles, of which 20 (0.93%) met the inclusion criteria. Three major categories of preprocessing techniques were identified: data transformation (used in 12/20, 60% of selected studies), data normalization and standardization (used in 8/20, 40% of the selected studies), and data cleaning (used in 8/20, 40% of the selected studies). Transformation methods aimed to convert raw data into more informative formats for analysis, such as by segmenting sensor streams or extracting statistical features. Normalization and standardization techniques usually normalize the range of features to improve comparability and model convergence. Cleaning methods focused on enhancing data reliability by handling artifacts like missing values, outliers, and inconsistencies.

CONCLUSIONS

While wearable sensors are gaining traction in cancer care, realizing their full potential hinges on the ability to reliably translate raw outputs into high-quality data suitable for AI/ML applications. This review found that researchers are using various preprocessing techniques to address this challenge, but there remains a lack of standardized best practices. Our findings suggest a pressing need to develop and adopt uniform data quality and preprocessing workflows of wearable sensor data that can support the breadth of cancer research and varied patient populations. Given the diverse preprocessing techniques identified in the literature, there is an urgency for a framework that can guide researchers and clinicians in preparing wearable sensor data for AI/ML applications. For the scoping review as well as our research, we propose a general framework for preprocessing wearable sensor data, designed to be adaptable across different disease settings, moving beyond cancer care.

Thermal stress, p53 structures and learning from elephants

As species adapt to climatic changes, temperature-dependent functions of p53 in development, metabolism and cancer will adapt as well. Structural analyses of p53 epitopes interacting in response to environmental stressors, such as heat, may uncover physiologically relevant functions of p53 in cell regulation and genomic adaptations. Here we explore the multiple p53 elephant paradigm with an experimentally validated in silico model showing that under heat stress some p53 copies escape negative regulation by the MDM2 E3 ubiquitin ligase. Multiple p53 isoforms have evolved naturally in the elephant thus presenting a unique experimental system to study the scope of p53 functions and the contribution of environmental stressors to DNA damage. We assert that fundamental insights derived from studies of a historically heat-challenged mammal will provide important insights directly relevant to human biology in the light of climate change when 'heat' may introduce novel challenges to our bodies and health.

Continuous Temperature Telemonitoring of Patients with COVID-19 and Other Infectious Diseases Treated in Hospital-at-Home: Viture® System Validation

Body temperature must be monitored in patients receiving Hospital-at-Home (HaH) care for COVID-19 and other infectious diseases. Continuous temperature telemonitoring (CTT) detects fever and patient deterioration early, facilitating decision-making. We performed a validation clinical study assessing the safety, comfort, and impact on healthcare practice of Viture®, a CTT system, compared with a standard digital axillary thermometer in 208 patients with COVID-19 and other infectious diseases treated in HaH at the Navarra University Hospital (HUN). Overall, 3258 pairs of measurements showed a clinical bias of -0.02 °C with limits of agreement of -0.96/+0.92 °C, a 95% acceptance rate, and a mean absolute deviation of 0.36 (SD 0.30) °C. Viture® detected 3 times more febrile episodes and revealed fever in 50% more patients compared with spot measurements. Febrile episodes were detected 7.23 h (mean) earlier and modified the diagnostic and/or therapeutic approach in 43.2% of patients. Viture® was validated for use in a clinical setting and was more effective in detecting febrile episodes than conventional methods.

Spotlight on Luminescence Thermometry: Basics, Challenges, and Cutting-Edge Applications

Luminescence (nano)thermometry is a remote sensing technique that relies on the temperature dependency of the luminescence features (e.g., bandshape, peak energy or intensity, and excited state lifetimes and risetimes) of a phosphor to measure temperature. This technique provides precise thermal readouts with superior spatial resolution in short acquisition times. Although luminescence thermometry is just starting to become a more mature subject, it exhibits enormous potential in several areas, e.g., optoelectronics, photonics, micro- and nanofluidics, and nanomedicine. This work reviews the latest trends in the field, including the establishment of a comprehensive theoretical background and standardized practices. The reliability, repeatability, and reproducibility of the technique are also discussed, along with the use of multiparametric analysis and artificial-intelligence algorithms to enhance thermal readouts. In addition, examples are provided to underscore the challenges that luminescence thermometry faces, alongside the need for a continuous search and design of new materials, experimental techniques, and analysis procedures to improve the competitiveness, accessibility, and popularity of the technology.

Efficient assessment of real-world dynamics of circadian rhythms in heart rate and body temperature from wearable data

Laboratory studies have made unprecedented progress in understanding circadian physiology. Quantifying circadian rhythms outside of laboratory settings is necessary to translate these findings into real-world clinical practice. Wearables have been considered promising way to measure these rhythms. However, their limited validation remains an open problem. One major barrier to implementing large-scale validation studies is the lack of reliable and efficient methods for circadian assessment from wearable data. Here, we propose an approximation-based least-squares method to extract underlying circadian rhythms from wearable measurements. Its computational cost is ∼ 300-fold lower than that of previous work, enabling its implementation in smartphones with low computing power. We test it on two large-scale real-world wearable datasets: [Formula: see text] of body temperature data from cancer patients and ∼ 184 000 days of heart rate and activity data collected from the 'Social Rhythms' mobile application. This shows successful extraction of real-world dynamics of circadian rhythms. We also identify a reasonable harmonic model to analyse wearable data. Lastly, we show our method has broad applicability in circadian studies by embedding it into a Kalman filter that infers the state space of the molecular clocks in tissues. Our approach facilitates the translation of scientific advances in circadian fields into actual improvements in health.

Free-living core body temperature monitoring using a wrist-worn sensor after COVID-19 booster vaccination: a pilot study

Core body temperature (CBT) is a key vital sign and fever is an important indicator of disease. In the past decade, there has been growing interest for vital sign monitoring technology that may be embedded in wearable devices, and the COVID-19 pandemic has highlighted the need for remote patient monitoring systems. While wrist-worn sensors allow continuous assessment of heart rate and oxygen saturation, reliable measurement of CBT at the wrist remains challenging. In this study, CBT was measured continuously in a free-living setting using a novel technology worn at the wrist and compared to reference core body temperature measurements, i.e., CBT values acquired with an ingestible temperature-sensing pill. Fifty individuals who received the COVID-19 booster vaccination were included. The datasets of 33 individuals were used to develop the CBT prediction algorithm, and the algorithm was then validated on the datasets of 17 participants. Mean observation time was 26.4 h and CBT > 38.0 °C occurred in 66% of the participants. CBT predicted by the wrist-worn sensor showed good correlation to the reference CBT (r = 0.72). Bland-Altman statistics showed an average bias of 0.11 °C of CBT predicted by the wrist-worn device compared to reference CBT, and limits of agreement were - 0.67 to + 0.93 °C, which is comparable to the bias and limits of agreement of commonly used tympanic membrane thermometers. The small size of the components needed for this technology would allow its integration into a variety of wearable monitoring systems assessing other vital signs and at the same time allowing maximal freedom of movement to the user.

A pilot intervention of using a mobile health app (ONC Roadmap) to enhance health-related quality of life in family caregivers of pediatric patients with cancer

Background

The Roadmap mobile health (mHealth) app was developed to provide health-related quality of life (HRQOL) support for family caregivers of patients with cancer.

Methods

Eligibility included: family caregivers (age ≥18 years) who self-reported as the primary caregiver of their pediatric patient with cancer; patients (age ≥5 years) who were receiving cancer care at the University of Michigan. Feasibility was calculated as the percentage of caregivers who logged into ONC Roadmap and engaged with it at least twice weekly for at least 50% of the 120-day study duration. Feasibility and acceptability was also assessed through a Feasibility and Acceptability questionnaire and the Mobile App Rating Scale to specifically assess app-quality. Exploratory analyses were also conducted to assess HRQOL self- or parent proxy assessments and physiological data capture.

Results

Between September 2020-September 2021, 100 participants (or 50 caregiver-patient dyads) consented and enrolled in the ONC Roadmap study for 120-days. Feasibility of the study was met, wherein the majority of caregivers (N=32; 65%) logged into ONC Roadmap and engaged with it at least twice weekly for at least 50% of the study duration (defined a priori in the Protocol). The Feasibility and Acceptability questionnaire responses indicated that the study was feasible and acceptable with the majority (>50%) reporting Agree or Strongly Agree with positive Net Favorability [(Agree + Strongly Agree) - (Disagree + Totally Disagree)] in each of the domains (e.g., Fitbit use, ONC Roadmap use, completing longitudinal assessments, engaging in similar future study, study expectations). Improvements were seen across the majority of the mental HRQOL domains across all groups; even though underpowered, there were significant improvements in caregiver-specific aspects of HRQOL and anxiety and in depression and fatigue for children (ages 8-17 years), and a trend toward improvement in depression for children ages 8-17 years and in fatigue for adult patients.

Conclusions

This study supports that mHealth technology may be a promising platform to provide HRQOL support for caregivers of pediatric patients with cancer. Importantly, the findings suggest that the study protocol was feasible, and participants were favorable to participate in future studies of this intervention alongside routine cancer care delivery.

High-frequency temperature monitoring at home using a wearable device: A case series of early fever detection and antibiotic administration for febrile neutropenia with bacteremia

We present a case series of three febrile episodes in neutropenic pediatric cancer patients who wore a Food and Drug Administration approved high-frequency temperature monitoring (HFTM) wearable device (WD) at home. The WD detected fever events when temperature monitoring by thermometer did not detect fever or was not feasible to perform. Two of the episodes were associated with bloodstream infections and the WD detected fevers 5 and 12 h prior to fevers detected by thermometer, triggering earlier medical evaluation and more prompt administration of antibiotics. These observations provide a basis for future investigation of home-based HFTM to improve infection-related outcomes in pediatric oncology.

Feasibility, Acceptability, and Performance of a Continuous Temperature Monitor in Older Adults and Staff in Congregate-Living Facilities

OBJECTIVES

Residents of congregate-living facilities are susceptible to disability and mortality from infection given the presence of advanced age, multimorbidity, and frailty-as demonstrated in the recent COVID pandemic. This study assessed the feasibility, acceptability, and applicability of a continuous temperature monitoring device in a congregate-living facility with residents of independent living, assisted living, and their care-providing staff. We hypothesized that a wearable device compared with daily manual temperature assessment would be well tolerated and more effective at detecting temperature variances than current standard of care body temperature assessment.

DESIGN

Feasibility study.

SETTING AND PARTICIPANTS

Residents of assisted and independent living and staff of a retirement community.

METHODS

Thirty-five participants, including residents in assisted- and independent-living facilities (25) and staff (10) were enrolled in a 90-day feasibility study and wore a continuous temperature sensor from March to July 2021. Primary outcomes included study completion, ability to reapply the sensor, temperature data acquisition, and data availability from the sensors. A secondary analysis of the temperature data involved comparing the method of obtaining temperature using the continuous monitoring device against standard of care using traditional manual thermometers.

RESULTS

Overall, 91.3% of residents, who were in the study during the first reapplication, were able to apply the device without assistance (21 of 23), and 80% of resident participants completed the study (20 of 25). For staff participants, completion rates and reapplication rates were 100%. Data acquisition rates from the continuous temperature devices were much higher than manual temperatures. Four episodes of fever were detected by the devices; manual temperature checks did not identify these events.

CONCLUSIONS AND IMPLICATIONS

Continuous temperature monitoring in an older adult population and the staff in congregate-living facilities is feasible and acceptable. This approach identified fever undetected by current standard of care indicating the capability of this device for earlier detection of fevers.