RESUMEN
[This corrects the article DOI: 10.2196/28260.].
RESUMEN
BACKGROUND: Overcrowding of hospitals and emergency departments (EDs) is a growing problem. However, not all ED consultations are necessary. For example, 80% of patients in the ED with chest pain do not have an acute coronary syndrome (ACS). Artificial intelligence (AI) is useful in analyzing (medical) data, and might aid health care workers in prehospital clinical decision-making before patients are presented to the hospital. OBJECTIVE: The aim of this study was to develop an AI model which would be able to predict ACS before patients visit the ED. The model retrospectively analyzed prehospital data acquired by emergency medical services' nurse paramedics. METHODS: Patients presenting to the emergency medical services with symptoms suggestive of ACS between September 2018 and September 2020 were included. An AI model using a supervised text classification algorithm was developed to analyze data. Data were analyzed for all 7458 patients (mean 68, SD 15 years, 54% men). Specificity, sensitivity, positive predictive value (PPV), and negative predictive value (NPV) were calculated for control and intervention groups. At first, a machine learning (ML) algorithm (or model) was chosen; afterward, the features needed were selected and then the model was tested and improved using iterative evaluation and in a further step through hyperparameter tuning. Finally, a method was selected to explain the final AI model. RESULTS: The AI model had a specificity of 11% and a sensitivity of 99.5% whereas usual care had a specificity of 1% and a sensitivity of 99.5%. The PPV of the AI model was 15% and the NPV was 99%. The PPV of usual care was 13% and the NPV was 94%. CONCLUSIONS: The AI model was able to predict ACS based on retrospective data from the prehospital setting. It led to an increase in specificity (from 1% to 11%) and NPV (from 94% to 99%) when compared to usual care, with a similar sensitivity. Due to the retrospective nature of this study and the singular focus on ACS it should be seen as a proof-of-concept. Other (possibly life-threatening) diagnoses were not analyzed. Future prospective validation is necessary before implementation.
RESUMEN
BACKGROUND: The older population needs solutions for independent living and reducing the burden on caregivers while maintaining the quality and dignity of life. OBJECTIVE: The aim of this study was to design, develop, and evaluate an older adult health care app that supports trained caregivers (ie, formal caregivers) and relatives (ie, informal caregivers). We aimed to identify the factors that affect user acceptance of interfaces depending on the user's role. METHODS: We designed and developed an app with 3 user interfaces that enable remote sensing of an older adult's daily activities and behaviors. We conducted user evaluations (N=25) with older adults and their formal and informal caregivers to obtain an overall impression of the health care monitoring app in terms of user experience and usability. In our design study, the participants had firsthand experience with our app, followed by a questionnaire and individual interview to express their opinions on the app. Through the interview, we also identified their views on each user interface and interaction modality to identify the relationship between the user's role and their acceptance of a particular interface. The questionnaire answers were statistically analyzed, and we coded the interview answers based on keywords related to a participant's experience, for example, ease of use and usefulness. RESULTS: We obtained overall positive results in the user evaluation of our app regarding key aspects such as efficiency, perspicuity, dependability, stimulation, and novelty, with an average between 1.74 (SD 1.02) and 2.18 (SD 0.93) on a scale of -3.0 to 3.0. The overall impression of our app was favorable, and we identified that "simple" and "intuitive" were the main factors affecting older adults' and caregivers' preference for the user interface and interaction modality. We also identified a positive user acceptance of the use of augmented reality by 91% (10/11) of the older adults to share information with their formal and informal caregivers. CONCLUSIONS: To address the need for a study to evaluate the user experience and user acceptance by older adults as well as both formal and informal caregivers regarding the user interfaces with multimodal interaction in the context of health monitoring, we designed, developed, and conducted user evaluations with the target user groups. Our results through this design study show important implications for designing future health monitoring apps with multiple interaction modalities and intuitive user interfaces in the older adult health care domain.
RESUMEN
BACKGROUND: One of the main challenges of health monitoring systems is the support of older persons in living independently in their homes and with relatives. Smart homes equipped with internet of things devices can allow older persons to live longer in their homes. Previous surveys used to identify sensor-based data sets in human activity recognition systems have been limited by the use of public data set characteristics, data collected in a controlled environment, and a limited number of older participants. OBJECTIVE: The objective of our study is to build a model that can learn the daily routines of older persons, detect deviations in daily living behavior, and notify these anomalies in near real-time to relatives. METHODS: We extracted features from large-scale sensor data by calculating the time duration and frequency of visits. Anomalies were detected using a parametric statistical approach, unusually short or long durations being detected by estimating the mean (µ) and standard deviation (σ) over hourly time windows (80 to 355 days) for different apartments. The confidence level is at least 75% of the tested values within two (σ) from the mean. An anomaly was triggered where the actual duration was outside the limits of 2 standard deviations (µ-2σ, µ+2σ), activity nonoccurrence, or absence of activity. RESULTS: The patterns detected from sensor data matched the routines self-reported by users. Our system observed approximately 1000 meals and bathroom activities and notifications sent to 9 apartments between July and August 2020. A service evaluation of received notifications showed a positive user experience, an average score of 4 being received on a 1 to 5 Likert-like scale. One was poor, two fair, three good, four very good, and five excellent. Our approach considered more than 75% of the observed meal activities were normal. This figure, in reality, was 93%, normal observed meal activities of all participants falling within 2 standard deviations of the mean. CONCLUSIONS: In this research, we developed, implemented, and evaluated a real-time monitoring system of older participants in an uncontrolled environment, with off-the-shelf sensors and internet of things devices being used in the homes of older persons. We also developed an SMS-based notification service and conducted user evaluations. This service acts as an extension of the health/social care services operated by the municipality of Skellefteå provided to older persons and relatives.
RESUMEN
LoRaWAN has become popular as an IoT enabler. The low cost, ease of installation and the capacity of fine-tuning the parameters make this network a suitable candidate for the deployment of smart cities. In northern Sweden, in the smart region of Skellefteå, we have deployed a LoRaWAN to enable IoT applications to assist the lives of citizens. As Skellefteå has a subarctic climate, we investigate how the extreme changes in the weather happening during a year affect a real LoRaWAN deployment in terms of SNR, RSSI and the use of SF when ADR is enabled. Additionally, we evaluate two propagation models (Okumura-Hata and ITM) and verify if any of those models fit the measurements obtained from our real-life network. Our results regarding the weather impact show that cold weather improves the SNR while warm weather makes the sensors select lower SFs, to minimize the time-on-air. Regarding the tested propagation models, Okumura-Hata has the best fit to our data, while ITM tends to overestimate the RSSI values.