JMIR biomedical engineering最新文献

{"title":"A Deep Learning Framework for Predicting Patient Decannulation on Extracorporeal Membrane Oxygenation Devices: Development and Model Analysis Study.","authors":"Joshua Fuller, Alexey Abramov, Dana Mullin, James Beck, Philippe Lemaitre, Elham Azizi","doi":"10.2196/48497","DOIUrl":"10.2196/48497","url":null,"abstract":"<p><strong>Background: </strong>Venovenous extracorporeal membrane oxygenation (VV-ECMO) is a therapy for patients with refractory respiratory failure. The decision to decannulate someone from extracorporeal membrane oxygenation (ECMO) often involves weaning trials and clinical intuition. To date, there are limited prognostication metrics to guide clinical decision-making to determine which patients will be successfully weaned and decannulated.</p><p><strong>Objective: </strong>This study aims to assist clinicians with the decision to decannulate a patient from ECMO, using Continuous Evaluation of VV-ECMO Outcomes (CEVVO), a deep learning-based model for predicting success of decannulation in patients supported on VV-ECMO. The running metric may be applied daily to categorize patients into high-risk and low-risk groups. Using these data, providers may consider initiating a weaning trial based on their expertise and CEVVO.</p><p><strong>Methods: </strong>Data were collected from 118 patients supported with VV-ECMO at the Columbia University Irving Medical Center. Using a long short-term memory-based network, CEVVO is the first model capable of integrating discrete clinical information with continuous data collected from an ECMO device. A total of 12 sets of 5-fold cross validations were conducted to assess the performance, which was measured using the area under the receiver operating characteristic curve (AUROC) and average precision (AP). To translate the predicted values into a clinically useful metric, the model results were calibrated and stratified into risk groups, ranging from 0 (high risk) to 3 (low risk). To further investigate the performance edge of CEVVO, 2 synthetic data sets were generated using Gaussian process regression. The first data set preserved the long-term dependency of the patient data set, whereas the second did not.</p><p><strong>Results: </strong>CEVVO demonstrated consistently superior classification performance compared with contemporary models (P<.001 and P=.04 compared with the next highest AUROC and AP). Although the model's patient-by-patient predictive power may be too low to be integrated into a clinical setting (AUROC 95% CI 0.6822-0.7055; AP 95% CI 0.8515-0.8682), the patient risk classification system displayed greater potential. When measured at 72 hours, the high-risk group had a successful decannulation rate of 58% (7/12), whereas the low-risk group had a successful decannulation rate of 92% (11/12; P=.04). When measured at 96 hours, the high- and low-risk groups had a successful decannulation rate of 54% (6/11) and 100% (9/9), respectively (P=.01). We hypothesized that the improved performance of CEVVO was owing to its ability to efficiently capture transient temporal patterns. Indeed, CEVVO exhibited improved performance on synthetic data with inherent temporal dependencies (P<.001) compared with logistic regression and a dense neural network.</p><p><strong>Conclusions: </strong>The ability to interpret","PeriodicalId":87288,"journal":{"name":"JMIR biomedical engineering","volume":"9 ","pages":"e48497"},"PeriodicalIF":0.0,"publicationDate":"2024-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11041448/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141322163","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An Investigation of Deepfake Voice Detection using Speech Pause Patterns: Pilot Study (Preprint)","authors":"Nikhil Valsan Kulangareth, Jaycee M. Kaufman, Jessica Oreskovic, Yan Fossat","doi":"10.2196/56245","DOIUrl":"https://doi.org/10.2196/56245","url":null,"abstract":"","PeriodicalId":87288,"journal":{"name":"JMIR biomedical engineering","volume":"15 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140506298","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Impact of Audio Data Compression on Feature Extraction for Vocal Biomarker Detection: Validation Study (Preprint)","authors":"Jessica Oreskovic, Jaycee M. Kaufman, Yan Fossat","doi":"10.2196/56246","DOIUrl":"https://doi.org/10.2196/56246","url":null,"abstract":"","PeriodicalId":87288,"journal":{"name":"JMIR biomedical engineering","volume":"19 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140511281","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assessment of Skin Maturity by LED Light at Birth and Its Association With Lung Maturity: Clinical Trial Secondary Outcomes","authors":"Gabriela Silveira Neves, Z. Reis, Roberta Romanelli, James Batchelor","doi":"10.2196/52468","DOIUrl":"https://doi.org/10.2196/52468","url":null,"abstract":"Clinicians face barriers when assessing lung maturity at birth due to global inequalities. Still, strategies for testing based solely on gestational age to predict the likelihood of respiratory distress syndrome (RDS) do not offer a comprehensive approach to addressing the challenge of uncertain outcomes. We hypothesize that a noninvasive assessment of skin maturity may indicate lung maturity. This study aimed to assess the association between a newborn’s skin maturity and RDS occurrence. We conducted a case-control nested in a prospective cohort study, a secondary endpoint of a multicenter clinical trial. The study was carried out in 5 Brazilian urban reference centers for highly complex perinatal care. Of 781 newborns from the cohort study, 640 were selected for the case-control analysis. Newborns with RDS formed the case group and newborns without RDS were the controls. All newborns with other diseases exhibiting respiratory manifestations were excluded. Skin maturity was assessed from the newborn's skin over the sole by an optical device that acquired a reflection signal through an LED sensor. The device, previously validated, measured and recorded skin reflectance. Clinical data related to respiratory outcomes were gathered from medical records during the 72-hour follow-up of the newborn, or until discharge or death, whichever occurred first. The main outcome measure was the association between skin reflectance and RDS using univariate and multivariate binary logistic regression. Additionally, we assessed the connection between skin reflectance and factors such as neonatal intensive care unit (NICU) admission and the need for ventilatory support. Out of 604 newborns, 470 (73.4%) were from the RDS group and 170 (26.6%) were from the control group. According to comparisons between the groups, newborns with RDS had a younger gestational age (31.6 vs 39.1 weeks, P<.001) and birth weight (1491 vs 3121 grams, P<.001) than controls. Skin reflectance was associated with RDS (odds ratio [OR] 0.982, 95% CI 0.979-0.985, R2=0.632, P<.001). This relationship remained significant when adjusted by the cofactors antenatal corticosteroid and birth weight (OR 0.994, 95% CI 0.990-0.998, R2=0.843, P<.001). Secondary outcomes also showed differences in skin reflectance. The mean difference was 0.219 (95% CI 0.200-0.238) between newborns that required ventilatory support versus those that did not and 0.223 (95% CI 0.205-0.241) between newborns that required NICU admission versus those that did not. Skin reflectance was associated with ventilatory support (OR 0.996, 95% CI 0.992-0.999, R2=0.814, P=.01) and with NICU admission (OR 0.994, 95% CI 0.990-0.998, R2=0.867, P=.004). Our findings present a potential marker of lung immaturity at birth using the indirect method of skin assessment. Using the RDS clinical condition and a medical device, this study demonstrated the synchrony between lung and skin maturity. Registro Brasileiro ","PeriodicalId":87288,"journal":{"name":"JMIR biomedical engineering","volume":"35 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139159568","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Measuring Heart Rate Accurately in Patients With Parkinson Disease During Intense Exercise: Usability Study of Fitbit Charge 4","authors":"Giulia Colonna, Jocelyn Hoye, Bart de Laat, Gelsina Stanley, Alaaddin Ibrahimy, S. Tinaz, Evan D. Morris","doi":"10.2196/51515","DOIUrl":"https://doi.org/10.2196/51515","url":null,"abstract":"\u0000 \u0000 Parkinson disease (PD) is the second most common neurodegenerative disease, affecting approximately 1% of the world’s population.\u0000Increasing evidence suggests that aerobic physical exercise can be beneficial in mitigating both motor and nonmotor symptoms of the disease.\u0000In a recent pilot study of the role of exercise on PD, we sought to confirm exercise intensity by monitoring heart rate (HR). For this purpose, we asked participants to wear a chest strap HR monitor (Polar Electro Oy) and the Fitbit Charge 4 (Fitbit Inc) wrist-worn HR monitor as a potential proxy due to its convenience.\u0000Polar H10 has been shown to provide highly accurate R-R interval measurements. Therefore, we treated it as the gold standard in this study. It has been shown that Fitbit Charge 4 has comparable accuracy to Polar H10 in healthy participants. It has yet to be determined if the Fitbit is as accurate as Polar H10 in patients with PD during rest and exercise.\u0000 \u0000 \u0000 \u0000 This study aimed to compare Fitbit Charge 4 to Polar H10 for monitoring HR in patients with PD at rest and during an intensive exercise program.\u0000 \u0000 \u0000 \u0000 A total of 596 exercise sessions from 11 (6 male and 5 female) participants were collected simultaneously with both devices. Patients with early-stage PD (Hoehn and Yahr ≤2) were enrolled in a 6-month exercise program designed for patients with PD. They participated in 3 one-hour exercise sessions per week. They wore both Fitbit and Polar H10 during each session. Sessions included rest, warm-up, intense exercise, and cool-down periods.\u0000We calculated the bias in the HR of the Fitbit Charge 4 at rest (5 min) and during intense exercise (20 min) by comparing the mean HR during each of the periods to the respective means measured by Polar H10 (HRFitbit – HRPolar). We also measured the sensitivity and specificity of Fitbit Charge 4 to detect average HRs that exceed the threshold for intensive exercise, defined as 70% of an individual’s theoretical maximum HR. Different types of correlations between the 2 devices were investigated.\u0000 \u0000 \u0000 \u0000 The mean bias was 1.68 beats per minute (bpm) at rest and 6.29 bpm during high-intensity exercise, with an overestimation by Fitbit Charge 4 in both conditions. The mean bias of the Fitbit across both rest and intensive exercise periods was 3.98 bpm. The device’s sensitivity in identifying high-intensity exercise sessions was 97.14%. The correlation between the 2 devices was nonlinear, suggesting Fitbit’s tendency to saturate at high values of HR.\u0000 \u0000 \u0000 \u0000 The performance of Fitbit Charge 4 is comparable to Polar H10 for assessing exercise intensity in a cohort of patients with PD (mean bias 3.98 bpm). The device could be considered a reasonable surrogate for more cumbersome chest-worn devices in future studies of clinical cohorts.\u0000","PeriodicalId":87288,"journal":{"name":"JMIR biomedical engineering","volume":"48 48","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138588625","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Severity Classification Using Dynamic Time Warping-Based Voice Biomarkers for COVID-19 Infected Patients: A Feasibility Study (Preprint)","authors":"Teruhisa Watase, Yasuhiro Omiya, Shinichi Tokuno","doi":"10.2196/50924","DOIUrl":"https://doi.org/10.2196/50924","url":null,"abstract":"Background In Japan, individuals with mild COVID-19 illness previously required to be monitored in designated areas and were hospitalized only if their condition worsened to moderate illness or worse. Daily monitoring using a pulse oximeter was a crucial indicator for hospitalization. However, a drastic increase in the number of patients resulted in a shortage of pulse oximeters for monitoring. Therefore, an alternative and cost-effective method for monitoring patients with mild illness was required. Previous studies have shown that voice biomarkers for Parkinson disease or Alzheimer disease are useful for classifying or monitoring symptoms; thus, we tried to adapt voice biomarkers for classifying the severity of COVID-19 using a dynamic time warping (DTW) algorithm where voice wavelets can be treated as 2D features; the differences between wavelet features are calculated as scores. Objective This feasibility study aimed to test whether DTW-based indices can generate voice biomarkers for a binary classification model using COVID-19 patients’ voices to distinguish moderate illness from mild illness at a significant level. Methods We conducted a cross-sectional study using voice samples of COVID-19 patients. Three kinds of long vowels were processed into 10-cycle waveforms with standardized power and time axes. The DTW-based indices were generated by all pairs of waveforms and tested with the Mann-Whitney U test (α<.01) and verified with a linear discrimination analysis and confusion matrix to determine which indices were better for binary classification of disease severity. A binary classification model was generated based on a generalized linear model (GLM) using the most promising indices as predictors. The receiver operating characteristic curve/area under the curve (ROC/AUC) validated the model performance, and the confusion matrix calculated the model accuracy. Results Participants in this study (n=295) were infected with COVID-19 between June 2021 and March 2022, were aged 20 years or older, and recuperated in Kanagawa prefecture. Voice samples (n=110) were selected from the participants’ attribution matrix based on age group, sex, time of infection, and whether they had mild illness (n=61) or moderate illness (n=49). The DTW-based variance indices were found to be significant (P<.001, except for 1 of 6 indices), with a balanced accuracy in the range between 79% and 88.6% for the /a/, /e/, and /u/ vowel sounds. The GLM achieved a high balance accuracy of 86.3% (for /a/), 80.2% (for /e/), and 88% (for /u/) and ROC/AUC of 94.8% (95% CI 90.6%-94.8%) for /a/, 86.5% (95% CI 79.8%-86.5%) for /e/, and 95.6% (95% CI 92.1%-95.6%) for /u/. Conclusions The proposed model can be a voice biomarker for an alternative and cost-effective method of monitoring the progress of COVID-19 patients in care.","PeriodicalId":87288,"journal":{"name":"JMIR biomedical engineering","volume":"20 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135585441","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Continuous Critical Respiratory Parameter Measurements Using a Single Low-Cost Relative Humidity Sensor: Evaluation Study","authors":"Fabrice Vaussenat, Abhiroop Bhattacharya, Julie Payette, Jaime A Benavides-Guerrero, Alexandre Perrotton, Luis Felipe Gerlein, Sylvain G Cloutier","doi":"10.2196/47146","DOIUrl":"https://doi.org/10.2196/47146","url":null,"abstract":"Background Accurate and portable respiratory parameter measurements are critical for properly managing chronic obstructive pulmonary diseases (COPDs) such as asthma or sleep apnea, as well as controlling ventilation for patients in intensive care units, during surgical procedures, or when using a positive airway pressure device for sleep apnea. Objective The purpose of this research is to develop a new nonprescription portable measurement device that utilizes relative humidity sensors (RHS) to accurately measure key respiratory parameters at a cost that is approximately 10 times less than the industry standard. Methods We present the development, implementation, and assessment of a wearable respiratory measurement device using the commercial Bosch BME280 RHS. In the initial stage, the RHS was connected to the pneumotach (PNT) gold standard device via its external connector to gather breathing metrics. Data collection was facilitated using the Arduino platform with a Bluetooth Low Energy connection, and all measurements were taken in real time without any additional data processing. The device’s efficacy was tested with 7 participants (5 men and 2 women), all in good health. In the subsequent phase, we specifically focused on comparing breathing cycle and respiratory rate measurements and determining the tidal volume by calculating the region between inhalation and exhalation peaks. Each participant's data were recorded over a span of 15 minutes. After the experiment, detailed statistical analysis was conducted using ANOVA and Bland-Altman to examine the accuracy and efficiency of our wearable device compared with the traditional methods. Results The perfused air measured with the respiratory monitor enables clinicians to evaluate the absolute value of the tidal volume during ventilation of a patient. In contrast, directly connecting our RHS device to the surgical mask facilitates continuous lung volume monitoring. The results of the 1-way ANOVA showed high P values of .68 for respiratory volume and .89 for respiratory rate, which indicate that the group averages with the PNT standard are equivalent to those with our RHS platform, within the error margins of a typical instrument. Furthermore, analysis utilizing the Bland-Altman statistical method revealed a small bias of 0.03 with limits of agreement (LoAs) of –0.25 and 0.33. The RR bias was 0.018, and the LoAs were –1.89 and 1.89. Conclusions Based on the encouraging results, we conclude that our proposed design can be a viable, low-cost wearable medical device for pulmonary parametric measurement to prevent and predict the progression of pulmonary diseases. We believe that this will encourage the research community to investigate the application of RHS for monitoring the pulmonary health of individuals.","PeriodicalId":87288,"journal":{"name":"JMIR biomedical engineering","volume":"AES-10 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135170420","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Wearable Vibratory Device (The Emma Watch) to Address Action Tremor in Parkinson Disease: Pilot Feasibility Study.","authors":"Alissa Pacheco, Tempest A van Schaik, Nadzeya Paleyes, Miguel Blacutt, Julio Vega, Abigail R Schreier, Haiyan Zhang, Chelsea Macpherson, Radhika Desai, Gavin Jancke, Lori Quinn","doi":"10.2196/40433","DOIUrl":"10.2196/40433","url":null,"abstract":"<p><strong>Background: </strong>Parkinson disease (PD) is a neurodegenerative disease that has a wide range of motor symptoms, such as tremor. Tremors are involuntary movements that occur in rhythmic oscillations and are typically categorized into rest tremor or action tremor. Action tremor occurs during voluntary movements and is a debilitating symptom of PD. As noninvasive interventions are limited, there is an ever-increasing need for an effective intervention for individuals experiencing action tremors. The Microsoft Emma Watch, a wristband with 5 vibrating motors, is a noninvasive, nonpharmaceutical intervention for tremor attenuation.</p><p><strong>Objective: </strong>This pilot study investigated the use of the Emma Watch device to attenuate action tremor in people with PD.</p><p><strong>Methods: </strong>The sample included 9 people with PD who were assessed on handwriting and hand function tasks performed on a digitized tablet. Tasks included drawing horizontal or vertical lines, tracing a star, spiral, writing \"elelelel\" in cursive, and printing a standardized sentence. Each task was completed 3 times with the Emma Watch programmed at different vibration intensities, which were counterbalanced: high intensity, low intensity (sham), and no vibration. Digital analysis from the tablet captured kinematic, dynamic, and spatial attributes of drawing and writing samples to calculate mathematical indices that quantify upper limb motor function. APDM Opal sensors (APDM Wearable Technologies) placed on both wrists were used to calculate metrics of acceleration and jerk. A questionnaire was provided to each participant after using the Emma Watch to gain a better understanding of their perspectives of using the device. In addition, drawings were compared to determine whether there were any visual differences between intensities.</p><p><strong>Results: </strong>In total, 9 people with PD were tested: 4 males and 5 females with a mean age of 67 (SD 9.4) years. There were no differences between conditions in the outcomes of interest measured with the tablet (duration, mean velocity, number of peaks, pause time, and number of pauses). Visual differences were observed within a small subset of participants, some of whom reported perceived improvement. The majority of participants (8/9) reported the Emma Watch was comfortable, and no problems with the device were reported.</p><p><strong>Conclusions: </strong>There were visually depicted and subjectively reported improvements in handwriting for a small subset of individuals. This pilot study was limited by a small sample size, and this should be taken into consideration with the interpretation of the quantitative results. Combining vibratory devices, such as the Emma Watch, with task specific training, or personalizing the frequency to one's individual tremor may be important steps to consider when evaluating the effect of vibratory devices on hand function or writing ability in future studies. While the E","PeriodicalId":87288,"journal":{"name":"JMIR biomedical engineering","volume":" ","pages":"e40433"},"PeriodicalIF":0.0,"publicationDate":"2023-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11041244/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45889430","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development and Testing of a Data Capture Device for Use With Clinical Incentive Spirometers: Testing and Usability Study.","authors":"Michael L Burns, Anik Sinha, Alexander Hoffmann, Zewen Wu, Tomas Medina Inchauste, Aaron Retsky, David Chesney, Sachin Kheterpal, Nirav Shah","doi":"10.2196/46653","DOIUrl":"10.2196/46653","url":null,"abstract":"<p><strong>Background: </strong>The incentive spirometer is a basic and common medical device from which electronic health care data cannot be directly collected. As a result, despite numerous studies investigating clinical use, there remains little consensus on optimal device use and sparse evidence supporting its intended benefits such as prevention of postoperative respiratory complications.</p><p><strong>Objective: </strong>The aim of the study is to develop and test an add-on hardware device for data capture of the incentive spirometer.</p><p><strong>Methods: </strong>An add-on device was designed, built, and tested using reflective optical sensors to identify the real-time location of the volume piston and flow bobbin of a common incentive spirometer. Investigators manually tested sensor level accuracies and triggering range calibrations using a digital flowmeter. A valid breath classification algorithm was created and tested to determine valid from invalid breath attempts. To assess real-time use, a video game was developed using the incentive spirometer and add-on device as a controller using the Apple iPad.</p><p><strong>Results: </strong>In user testing, sensor locations were captured at an accuracy of 99% (SD 1.4%) for volume and 100% accuracy for flow. Median and average volumes were within 7.5% (SD 6%) of target volume sensor levels, and maximum sensor triggering values seldom exceeded intended sensor levels, showing a good correlation to placement on 2 similar but distinct incentive spirometer designs. The breath classification algorithm displayed a 100% sensitivity and a 99% specificity on user testing, and the device operated as a video game controller in real time without noticeable interference or delay.</p><p><strong>Conclusions: </strong>An effective and reusable add-on device for the incentive spirometer was created to allow the collection of previously inaccessible incentive spirometer data and demonstrate Internet-of-Things use on a common hospital device. This design showed high sensor accuracies and the ability to use data in real-time applications, showing promise in the ability to capture currently inaccessible clinical data. Further use of this device could facilitate improved research into the incentive spirometer to improve adoption, incentivize adherence, and investigate the clinical effectiveness to help guide clinical care.</p>","PeriodicalId":87288,"journal":{"name":"JMIR biomedical engineering","volume":" ","pages":"e46653"},"PeriodicalIF":0.0,"publicationDate":"2023-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11041496/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48977252","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Radar-Based Opioid Overdose Detection Device for Public Restrooms: Design, Development, and Evaluation (Preprint)","authors":"Jessica Oreskovic, Jaycee Kaufman, Anirudh Thommandram, Yan Fossat","doi":"10.2196/51754","DOIUrl":"https://doi.org/10.2196/51754","url":null,"abstract":"","PeriodicalId":87288,"journal":{"name":"JMIR biomedical engineering","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135491570","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}