Endoscopic iatrogenic esophageal perforation and management: a retrospective outcome analysis in the modern era.

INTRODUCTION: Iatrogenic esophageal perforation (IEP) is a severe adverse event (AE) of upper endoscopy procedures (UEPs) associated with morbidity. Management has shifted from surgery to endotherapy with clip closure (CC), self-expanding metal stent (SEMS), and vacuum therapy (VT). Limited analyses measure outcomes during contemporary interventional endoscopy periods. METHODS: IEPs associated with EGD, upper EUS, small bowel enteroscopy (SBE), and ERCP at a 3-hospital academic center from January 2011 to December 2023 were identified retrospectively from a centralized AE database. Additional information was obtained from medical records. Statistical analysis was performed using Microsoft Excel and STATA. RESULTS: Thirty-two IEPs from 26 EGDs, 4 EUS, 1 SBE, and 1 ERCP were identified. IEPs occurred mostly after dilation (bougie N = 7; balloon, N = 5) or foreign body removal (N = 6). Most IEPs occurred in the lower esophagus (N = 10) or gastroesophageal junction (N = 8). Diagnosis was made at a median 2 h after the injury by endoscopy (N = 14), CT scan (N = 12), esophagram (N = 5), or x-ray (N = 1). Initial treatment included conservative therapy alone (N = 7), CC (N = 3), SEMS (N = 14), SEMS plus CC (N = 3), or surgery (N = 3). Eleven patients required additional treatment including repeat SEMS or adjustment (N = 4) or VT (N = 1). No surgical interventions were required after 2013. The median hospital stay was 3 days. Disposition included discharge to home (N = 25), long-term care facility (N = 2), 4 deaths (12.5% of IEPs), and 1 unknown. CONCLUSIONS: IEPs are rare and occur throughout the esophagus after any UEP. The majority are recognized immediately and managed with endotherapy, or rarely, surgery today. These characteristics likely explain the low mortality in this study.

Adverse Event Fatalities Related to GI Endoscopy.

BACKGROUND: Death after endoscopy is rare, under-reported, and has variable causes. This study aimed to evaluate the incidence and causes of fatal endoscopic adverse events (AEs) across two academic medical centers and to identify patient-, procedure-, and sedation-related risk factors. METHODS: This is a retrospective cohort study of fatal adverse events causally related to endoscopy at Denver Health Medical Center and the University of Colorado Hospital from 2011 to 2020. Fatal AEs were retrieved from the physician-reported database. Electronic medical records were then reviewed to determine medical history, procedure details, subsequent treatments, and time and cause of death. RESULTS: From January 2011 to January 2020, 146,010 GI endoscopy procedures were performed. Median patient age was 70 [51-78] and 57% were male. Thirty-one deaths were identified, 28 of which were attributed to endoscopy, yielding a procedure-related fatality rate of 0.018%. Procedures included 11 EGDs, one colonoscopy, two flexible sigmoidoscopies, six ERCPs, seven upper EUS, and one PEG-J tube placement. Specific causes of death included aspiration in four patients (14%); cardiac arrest or myocardial infarction in seven patients (25%); perforation in nine patients (32%); bleeding in four patients (14%); cholangitis or sepsis without perforation in three patients (11%); and acute pancreatitis in one patient (3.6%). CONCLUSIONS: Fatal endoscopic AEs were rare but tended to occur in older patients with major comorbidities. Most deaths occurred from aspiration pneumonia, cardiac arrest, or perforation-related sepsis within 1 week of the procedure.

Assessment of Psychosocial Functioning in a Large Cohort of Patients with Schizophrenia.

BACKGROUND: This study addresses the question of whether psychosocial functioning measured by the Personal and Social Performance (PSP) Scale is related to various psychopathological measures in a cohort of patients with schizophrenia. METHODS: The 'Neuroleptic Strategy Study' (NeSSy) performed at 14 German hospitals between 2010 and 2013 compared two treatment strategies instead of individual drugs. Secondary end-points were the two PSP scales as well as measures of quality of life (SF-36) and the Positive and Negative Syndrome Scale (PANSS). RESULTS: 149 patients were randomised. There was no difference between the two treatment strategies (first-generation versus second-generation antipsychotics) with regard to the PSP. There were differences in doctors' assessments regarding psychosocial functioning compared with patients' own assessments. Furthermore, there were relationships between the PSP and quality of life, level of skills (ICF), and severity of disease (PANSS), level of sexual activities and poor well-being under antipsychotic medication but not with cognitive changes. CONCLUSIONS: The findings on psychosocial functioning of patients with schizophrenia related to severity and skill level could be confirmed. Further findings were the correlation between psychosocial functioning and quality of life, well-being under treatment, and sexuality what emphasizes the substantial importance of a reduced psychosocial functioning.

Wearable Patch-Based Estimation of Oxygen Uptake and Assessment of Clinical Status during Cardiopulmonary Exercise Testing in Patients With Heart Failure.

BACKGROUND: To estimate oxygen uptake (VO2) from cardiopulmonary exercise testing (CPX) using simultaneously recorded seismocardiogram (SCG) and electrocardiogram (ECG) signals captured with a small wearable patch. CPX is an important risk stratification tool for patients with heart failure (HF) owing to the prognostic value of the features derived from the gas exchange variables such as VO2. However, CPX requires specialized equipment, as well as trained professionals to conduct the study. METHODS AND RESULTS: We have conducted a total of 68 CPX tests on 59 patients with HF with reduced ejection fraction (31% women, mean age 55 ± 13 years, ejection fraction 0.27 ± 0.11, 79% stage C). The patients were fitted with a wearable sensing patch and underwent treadmill CPX. We divided the dataset into a training-testing set (n = 44) and a separate validation set (n = 24). We developed globalized (population) regression models to estimate VO2 from the SCG and ECG signals measured continuously with the patch. We further classified the patients as stage D or C using the SCG and ECG features to assess the ability to detect clinical state from the wearable patch measurements alone. We developed the regression and classification model with cross-validation on the training-testing set and validated the models on the validation set. The regression model to estimate VO2 from the wearable features yielded a moderate correlation (R2 of 0.64) with a root mean square error of 2.51 ± 1.12 mL · kg-1 · min-1 on the training-testing set, whereas R2 and root mean square error on the validation set were 0.76 and 2.28 ± 0.93 mL · kg-1 · min-1, respectively. Furthermore, the classification of clinical state yielded accuracy, sensitivity, specificity, and an area under the receiver operating characteristic curve values of 0.84, 0.91, 0.64, and 0.74, respectively, for the training-testing set, and 0.83, 0.86, 0.67, and 0.92, respectively, for the validation set. CONCLUSIONS: Wearable SCG and ECG can assess CPX VO2 and thereby classify clinical status for patients with HF. These methods may provide value in the risk stratification of patients with HF by tracking cardiopulmonary parameters and clinical status outside of specialized settings, potentially allowing for more frequent assessments to be performed during longitudinal monitoring and treatment.

Daily shedding dynamics of E. coli O157 in an Australian grass-fed beef herd.

This study aimed to describe the diurnal shedding dynamics of Escherichia coli O157 in cattle managed on pasture. The purpose was to identify the value of a single measurement for predicting the shedding status on subsequent days. Over a 14-day period, 24 beef cows with known E. coli O157 shedding status were sampled twice daily or daily (21 sampling points) and E. coli O157 was enumerated from faeces. No association between shedding status of individual animals within a 7-h period was identified (odds ratio 1·5, P = 0·08). Short-interval sampling demonstrated substantial diurnal volatility in shedding of E. coli O157 that is not evident in studies based on long-interval (>7 days) sampling. The findings contribute to and support previous findings on the question why it has been difficult to achieve progress in understanding the epidemiology of E. coli O157 infection in cattle.

Synchronization of E. coli O157 shedding in a grass-fed beef herd: a longitudinal study.

This study aims to describe in detail the temporal dynamics of E. coli O157 shedding and risk factors for shedding in a grass-fed beef herd. During a 9-month period, 23 beef cows were sampled twice a week (58 sampling points) and E. coli O157 was enumerated from faecal samples. Isolates were screened by PCR for presence of rfbE, stx 1 and stx 2 . The prevalence per sampling day ranged from 0% to 57%. This study demonstrates that many members of the herd were concurrently shedding E. coli O157. Occurrence of rainfall (P < 0·01), feeding silage (P < 0·01) and lactating (P < 0·01) were found to be predictors of shedding. Moving cattle to a new paddock had a negative effect on shedding. This approach, based on short-interval sampling, confirms the known variability of shedding within a herd and highlights that high shedding events are rare.

THE EFFECT OF MATURITY ON HEART RATE RESPONSES DURING TRAINING AND TESTING IN POSTPUBESCENT FEMALE VOLLEYBALL PLAYERS.

The aim of this study was to examine the effect of maturity, assessed as difference between chronological age and age at peak height velocity, on heart rate (HR) responses to maximal and submaximal laboratory and field exercises. Twenty-eight postpubescent female volleyball players participated in the present study (age 13.8 (0.6) yr, body mass 62.5 (8.2) kg and height 1.73 (0.05) m; mean (standard deviation)). They were divided into two groups with regards to their maturation: less matured (LM) and more matured (MM). In laboratory, HR was recorded during 5 min rest, physical working capacity in heart rate 170 bpm, 3 min step test, 30 s Bosco test and Wingate anaerobic test (WAnT) were performed. In field, a 70 min training session (consisted by three parts: warm-up, 1 x 1 drills and team drills) was monitored and 20 m shuttle run endurance test was performed. There was significant difference between LM and MM groups over HR responses (%HR reserve, %HRR) to exercise training (F(2,21) = 6.08, p = 0.008, η2 = 0.37). There was a main effect of part session of exercise program on HR responses with the highest intensity recorded in 1 x 1 drills (-75% HRR) and the lowest in team drills (-60% HRR in LM and -65% HRR in MM). There was also a moderate effect of maturity on HR during cycling against 90 W and in the WAnT, and small effect on HR during cycling against 60 W, in the end of the step test, Bosco test and running endurance test, where the highest scores were recorded in LM. Based on the findings of the present study, it was concluded that maturity exerted an effect of small to moderate magnitude on H R responses in a laboratory setting and this should be taken into account by coaches and trainers when evaluating physiological characteristics.

Microstructural alterations of major thalamic nuclei in the chronic pediatric spinal cord injured population.

Background: The brain undergoes reorganization following spinal cord injury (SCI), but little is known about how the thalamus is affected in pediatric SCIs. Purpose: To characterize microstructural alterations in the thalamus after SCI with diffusion tensor imaging (DTI) metrics. Methods: 18 pediatric participants with chronic SCI (8-20 years) were stratified using the American Spinal Injury Association Impairment Scale (AIS) into groups: A, B, and C/D. DTI of the brain used a 3 T Siemens Verio MRI using the parameters: 20 directions, number of averages = 3, b = 1000 s/mm2, voxel size = 1.8 mm × 1.8 mm, slice thickness = 5 mm, TE = 95 ms, TR = 4300 ms, 30 slices, FOV = 230 × 230 mm2, matrix = 128 × 128, acquisition time = 4:45 min. Diffusion data was processed to generate DTI metrics FA, MD, AD, and RD. Data analysis: DTI metrics were acquired by superimposing the AAL3 thalamic atlas onto participant diffusion images registered to MNI152 space. We utilized a multiple Mann-Whitney U-test to compare between AIS groups, considering values of p ≤ 0.05 as significant. Results: FA, AD, RD, and MD significantly differed in thalamic nuclei between AIS groups A vs B and B vs C/D. Significant nuclei include the right ventral anterior, left intralaminar, bilateral lateral pulvinar, and right lateral geniculate. Conclusion: Our findings suggest the presence of microstructural alterations based on SCI severity in pediatric patients. These results are encouraging and warrant further study.

Reduced incidence of tick paralysis cases in dogs and cats at two emergency clinics in South-East Queensland since 2015: new generation prophylactics as possible explanatory variables.

INTRODUCTION: This study aimed to determine the incidence of canine and feline tick paralysis cases presenting to two veterinary emergency hospitals before and after the introduction of new generation prophylactic acaricides. METHODS: This was a retrospective study, investigating the number of tick paralysis cases presenting to two emergency and critical care veterinary hospitals in South-East Queensland, from 2008 to 2021. A total of 10,914 dogs and 3696 cats were included over the course of the study. To assess if the introduction of new generation prophylactics in 2015 has coincided with any variation in case numbers, data for each species were analysed graphically and numerically in the first instance, then interrupted time series analyses were performed for the dog and cat data independently. RESULTS: Accounting for seasonal and climatic variation, we estimated a 54.8% reduction in dog (95% CI 45.3%-62.7%) and 44% reduction in cat (95% CI 19.5%-46%) tick paralysis cases presenting to these two clinics. This reduction corresponded with the timing of new generation prophylactic agents being introduced, including isoxazolines and imidacloprid/flumethrin impregnated collars. CONCLUSION: In the population studied, a significant reduction in the incidence of tick paralysis cases treated by veterinarians has occurred from 2015 onwards and was found to be associated with the timing of the release of new generation acaricidal products.

Generative Artificial Intelligence for Chest Radiograph Interpretation in the Emergency Department.

Importance: Multimodal generative artificial intelligence (AI) methodologies have the potential to optimize emergency department care by producing draft radiology reports from input images. Objective: To evaluate the accuracy and quality of AI-generated chest radiograph interpretations in the emergency department setting. Design, Setting, and Participants: This was a retrospective diagnostic study of 500 randomly sampled emergency department encounters at a tertiary care institution including chest radiographs interpreted by both a teleradiology service and on-site attending radiologist from January 2022 to January 2023. An AI interpretation was generated for each radiograph. The 3 radiograph interpretations were each rated in duplicate by 6 emergency department physicians using a 5-point Likert scale. Main Outcomes and Measures: The primary outcome was any difference in Likert scores between radiologist, AI, and teleradiology reports, using a cumulative link mixed model. Secondary analyses compared the probability of each report type containing no clinically significant discrepancy with further stratification by finding presence, using a logistic mixed-effects model. Physician comments on discrepancies were recorded. Results: A total of 500 ED studies were included from 500 unique patients with a mean (SD) age of 53.3 (21.6) years; 282 patients (56.4%) were female. There was a significant association of report type with ratings, with post hoc tests revealing significantly greater scores for AI (mean [SE] score, 3.22 [0.34]; P < .001) and radiologist (mean [SE] score, 3.34 [0.34]; P < .001) reports compared with teleradiology (mean [SE] score, 2.74 [0.34]) reports. AI and radiologist reports were not significantly different. On secondary analysis, there was no difference in the probability of no clinically significant discrepancy between the 3 report types. Further stratification of reports by presence of cardiomegaly, pulmonary edema, pleural effusion, infiltrate, pneumothorax, and support devices also yielded no difference in the probability of containing no clinically significant discrepancy between the report types. Conclusions and Relevance: In a representative sample of emergency department chest radiographs, results suggest that the generative AI model produced reports of similar clinical accuracy and textual quality to radiologist reports while providing higher textual quality than teleradiologist reports. Implementation of the model in the clinical workflow could enable timely alerts to life-threatening pathology while aiding imaging interpretation and documentation.

Rapid health impact assessment of policies to reduce vehicle miles traveled in Oregon.

OBJECTIVE: Health impact assessments (HIAs) enable decisions-makers to assess proposed policies, projects and programmes with respect to their potential health impact. The purpose of this rapid HIA was to inform the debate within a state legislature about the value of state policy and provide information for local planning agencies to better incorporate health considerations into planning activities. STUDY DESIGN: Rapid HIA. METHODS: Literature review was used to evaluate three types of policies to reduce vehicle miles traveled: improving the built environment, increasing the costs of individual driving, and strengthening public transit. RESULTS: Select features of the built environment were found to be associated with increased physical activity, reduced collisions, and decreased air pollution. Increasing the cost of driving was not consistently found to reduce air pollution, increase physical activity, or reduce collisions. Strengthening public transit was associated with increased levels of physical activity. CONCLUSIONS: This rapid HIA provides a framework and focus for future HIAs in this topic area.

Factors influencing dairy cattle farmer use of antimicrobials on farms in New South Wales, Australia.

Antimicrobial use (AMU) in the food chain is a potential driver of antimicrobial resistance. Despite Australia's strong regulation of AMU limited to veterinary prescriptions, a proportion of empirical antimicrobial treatments are administered by dairy farmers to manage common cattle health problems. This cross-sectional survey identified key influences on AMU by dairy cattle farmers within New South Wales, Australia, to detect opportunities for antimicrobial stewardship (AMS) engagement. The study identified existing relationships, resources and attitudes of the dairy farmers that could be optimised for on-farm AMS strategies. Farmers were most highly influenced by veterinary advice and clinical signs of the animal followed by the withholding period and the potential for antimicrobial resistance development. Farmers' high confidence regarding their own knowledge of antimicrobials (>90%), their high regard for veterinary advice (>90%) and high rate of veterinary health care plan use (69%) provides a strong framework to build the profile and practice of AMS on dairy farms. Positive engagement by dairy farmers (survey response of 20%), was achieved by working with the NSW Food Authority. Despite respondents reporting low reliance on formal (government and commercial) organisations for information about AMU, their engagement demonstrates an opportunity for groups with unparalleled access to dairy farmers to drive AMS. An association between frequent use of veterinary advice and respondents keeping ceftiofur on-farm requires further investigation. Quantitative and qualitative analysis of on-farm resources, decision-making, and practices is required to understand how practices relate to veterinary advice and accepted standards of appropriate AMU on dairy farms.

Estimation of Changes in Intracardiac Hemodynamics Using Wearable Seismocardiography and Machine Learning in Patients With Heart Failure: A Feasibility Study.

OBJECTIVE: Tracking changes in hemodynamic congestion and the consequent proactive readjustment of treatment has shown efficacy in reducing hospitalizations for patients with heart failure (HF). However, the cost-prohibitive nature of these invasive sensing systems precludes their usage in the large patient population affected by HF. The objective of this research is to estimate the changes in pulmonary artery mean pressure (PAM) and pulmonary capillary wedge pressure (PCWP) following vasodilator infusion during right heart catheterization (RHC), using changes in simultaneously recorded wearable seismocardiogram (SCG) signals captured with a small wearable patch. METHODS: A total of 20 patients with HF (20% women, median age 55 (interquartile range (IQR), 44-64) years, ejection fraction 24 (IQR, 16-43)) were fitted with a wearable sensing patch and underwent RHC with vasodilator challenge. We divided the dataset randomly into a training-testing set (n = 15) and a separate validation set (n = 5). We developed globalized (population) regression models to estimate changes in PAM and PCWP from the changes in simultaneously recorded SCG. RESULTS: The regression model estimated both pressures with good accuracies: root-mean-square-error (RMSE) of 2.5 mmHg and R2 of 0.83 for estimating changes in PAM, and RMSE of 1.9 mmHg and R2 of 0.93 for estimating changes in PCWP for the training-testing set, and RMSE of 2.7 mmHg and R2 of 0.81 for estimating changes in PAM, and RMSE of 2.9 mmHg and R2 of 0.95 for estimating changes in PCWP for the validation set respectively. CONCLUSION: Changes in wearable SCG signals may be used to track acute changes in intracardiac hemodynamics in patients with HF. SIGNIFICANCE: This method holds promise in tracking longitudinal changes in hemodynamic congestion in hemodynamically-guided remote home monitoring and treatment for patients with HF.

Proposal of a 2-tier histologic grading system for canine cutaneous mast cell tumors to more accurately predict biological behavior.

Currently, prognostic and therapeutic determinations for canine cutaneous mast cell tumors (MCTs) are primarily based on histologic grade. However, the use of different grading systems by veterinary pathologists and institutional modifications make the prognostic value of histologic grading highly questionable. To evaluate the consistency of microscopic grading among veterinary pathologists and the prognostic significance of the Patnaik grading system, 95 cutaneous MCTs from 95 dogs were graded in a blinded study by 28 veterinary pathologists from 16 institutions. Concordance among veterinary pathologists was 75% for the diagnosis of grade 3 MCTs and less than 64% for the diagnosis of grade 1 and 2 MCTs. To improve concordance among pathologists and to provide better prognostic significance, a 2-tier histologic grading system was devised. The diagnosis of high-grade MCTs is based on the presence of any one of the following criteria: at least 7 mitotic figures in 10 high-power fields (hpf); at least 3 multinucleated (3 or more nuclei) cells in 10 hpf; at least 3 bizarre nuclei in 10 hpf; karyomegaly (ie, nuclear diameters of at least 10% of neoplastic cells vary by at least two-fold). Fields with the highest mitotic activity or with the highest degree of anisokaryosis were selected to assess the different parameters. According to the novel grading system, high-grade MCTs were significantly associated with shorter time to metastasis or new tumor development, and with shorter survival time. The median survival time was less than 4 months for high-grade MCTs but more than 2 years for low-grade MCTs.

Recommended guidelines for the conduct and evaluation of prognostic studies in veterinary oncology.

There is an increasing need for more accurate prognostic and predictive markers in veterinary oncology because of an increasing number of treatment options, the increased financial costs associated with treatment, and the emotional stress experienced by owners in association with the disease and its treatment. Numerous studies have evaluated potential prognostic and predictive markers for veterinary neoplastic diseases, but there are no established guidelines or standards for the conduct and reporting of prognostic studies in veterinary medicine. This lack of standardization has made the evaluation and comparison of studies difficult. Most important, translating these results to clinical applications is problematic. To address this issue, the American College of Veterinary Pathologists' Oncology Committee organized an initiative to establish guidelines for the conduct and reporting of prognostic studies in veterinary oncology. The goal of this initiative is to increase the quality and standardization of veterinary prognostic studies to facilitate independent evaluation, validation, comparison, and implementation of study results. This article represents a consensus statement on the conduct and reporting of prognostic studies in veterinary oncology from veterinary pathologists and oncologists from around the world. These guidelines should be considered a recommendation based on the current state of knowledge in the field, and they will need to be continually reevaluated and revised as the field of veterinary oncology continues to progress. As mentioned, these guidelines were developed through an initiative of the American College of Veterinary Pathologists' Oncology Committee, and they have been reviewed and endorsed by the World Small Animal Veterinary Association.

Is repeated-sprint ability of soccer players predictable from field-based or laboratory physiological tests?

AIM: The aim of this study was to investigate multiple regression models with prediction equations that would enable a valid estimate of running repeated-sprint ability (RSA) in soccer players from the variables measured in field and laboratory physiological tests. METHODS: Adolescent soccer players (N=33) performed five field performance tests and two laboratory tests for assessment of muscle strength of legs, sprint ability, anaerobic power and capacity, aerobic power and capacity, and running economy. These tests served as potential predictors of RSA. RSA was assessed by a intermittent anaerobic running test (IAnRT) consisted of ten 20 m sprints. RESULTS: Multiple regression analysis revealed that the mean speed in the 20 m sprint test and the 2 km endurance running test accounted for 89% of total variation in the mean running speed in the IAnRT (VIAnRT) as the indicator of capacity for multiple sprint work (R2=0.89, SEM=0.09 m.s-1). Using the variables from the laboratory tests, the best prediction of the VIAnRT was obtained from the running speed at the ventilatory threshold level (VVT) and anaerobic power (Pmax.kg-1) (R2=0.49, SEM=0.21 m.s-1). CONCLUSION: Performance in the multiple-sprint exercise as an indicator of RSA can be estimated by the regression equation with two predictors - mean speed in the 20 m sprint and 2 km running test with an error of 4%.

Wearable Cuff-Less Blood Pressure Estimation at Home via Pulse Transit Time.

OBJECTIVE: We developed a wearable watch-based device to provide noninvasive, cuff-less blood pressure (BP) estimation in an at-home setting. METHODS: The watch measures single-lead electrocardiogram (ECG), tri-axial seismocardiogram (SCG), and multi-wavelength photoplethysmogram (PPG) signals to compute the pulse transit time (PTT), allowing for BP estimation. We sent our custom watch device and an oscillometric BP cuff home with 21 healthy subjects, and captured the natural variability in BP over the course of a 24-hour period. RESULTS: After calibration, our Pearson correlation coefficient (PCC) of 0.69 and root-mean-square-error (RMSE) of 2.72 mmHg suggest that noninvasive PTT measurements correlate with around-the-clock BP. Using a novel two-point calibration method, we achieved a RMSE of 3.86 mmHg. We further demonstrated the potential of a semi-globalized adaptive model to reduce calibration requirements. CONCLUSION: This is, to the best of our knowledge, the first time that BP has been comprehensively estimated noninvasively using PTT in an at-home setting. We showed a more convenient method for obtaining ambulatory BP than through the use of the standard oscillometric cuff. We presented new calibration methods for BP estimation using fewer calibration points that are more practical for a real-world scenario. SIGNIFICANCE: A custom watch (SeismoWatch) capable of taking multiple BP measurements enables reliable remote monitoring of daily BP and paves the way towards convenient hypertension screening and management, which can potentially reduce hospitalizations and improve quality of life.

Enabling Continuous Wearable Reflectance Pulse Oximetry at the Sternum.

In light of the recent Coronavirus disease (COVID-19) pandemic, peripheral oxygen saturation (SpO2) has shown to be amongst the vital signs most indicative of deterioration in persons with COVID-19. To allow for the continuous monitoring of SpO2, we attempted to demonstrate accurate SpO2 estimation using our custom chest-based wearable patch biosensor, capable of measuring electrocardiogram (ECG) and photoplethysmogram (PPG) signals with high fidelity. Through a breath-hold protocol, we collected physiological data with a wide dynamic range of SpO2 from 20 subjects. The ratio of ratios (R) used in pulse oximetry to estimate SpO2 was robustly extracted from the red and infrared PPG signals during the breath-hold segments using novel feature extraction and PPGgreen-based outlier rejection algorithms. Through subject independent training, we achieved a low root-mean-square error (RMSE) of 2.64 ± 1.14% and a Pearson correlation coefficient (PCC) of 0.89. With subject-specific calibration, we further reduced the RMSE to 2.27 ± 0.76% and increased the PCC to 0.91. In addition, we showed that calibration is more efficiently accomplished by standardizing and focusing on the duration of breath-hold rather than the resulting range in SpO2. The accurate SpO2 estimation provided by our custom biosensor and the algorithms provide research opportunities for a wide range of disease and wellness monitoring applications.

Amalgamation of cloud-based colonoscopy videos with patient-level metadata to facilitate large-scale machine learning.

Background and study aims Storage of full-length endoscopic procedures is becoming increasingly popular. To facilitate large-scale machine learning (ML) focused on clinical outcomes, these videos must be merged with the patient-level data in the electronic health record (EHR). Our aim was to present a method of accurately linking patient-level EHR data with cloud stored colonoscopy videos. Methods This study was conducted at a single academic medical center. Most procedure videos are automatically uploaded to the cloud server but are identified only by procedure time and procedure room. We developed and then tested an algorithm to match recorded videos with corresponding exams in the EHR based upon procedure time and room and subsequently extract frames of interest. Results Among 28,611 total colonoscopies performed over the study period, 21,170 colonoscopy videos in 20,420 unique patients (54.2 % male, median age 58) were matched to EHR data. Of 100 randomly sampled videos, appropriate matching was manually confirmed in all. In total, these videos represented 489,721 minutes of colonoscopy performed by 50 endoscopists (median 214 colonoscopies per endoscopist). The most common procedure indications were polyp screening (47.3 %), surveillance (28.9 %) and inflammatory bowel disease (9.4 %). From these videos, we extracted procedure highlights (identified by image capture; mean 8.5 per colonoscopy) and surrounding frames. Conclusions We report the successful merging of a large database of endoscopy videos stored with limited identifiers to rich patient-level data in a highly accurate manner. This technique facilitates the development of ML algorithms based upon relevant patient outcomes.