An Accelerometer-Based Wearable Patch for Robust Respiratory Rate and Wheeze Detection Using Deep Learning.

Wheezing is a critical indicator of various respiratory conditions, including asthma and chronic obstructive pulmonary disease (COPD). Current diagnosis relies on subjective lung auscultation by physicians. Enabling this capability via a low-profile, objective wearable device for remote patient monitoring (RPM) could offer pre-emptive, accurate respiratory data to patients. With this goal as our aim, we used a low-profile accelerometer-based wearable system that utilizes deep learning to objectively detect wheezing along with respiration rate using a single sensor. The miniature patch consists of a sensitive wideband MEMS accelerometer and low-noise CMOS interface electronics on a small board, which was then placed on nine conventional lung auscultation sites on the patient's chest walls to capture the pulmonary-induced vibrations (PIVs). A deep learning model was developed and compared with a deterministic time-frequency method to objectively detect wheezing in the PIV signals using data captured from 52 diverse patients with respiratory diseases. The wearable accelerometer patch, paired with the deep learning model, demonstrated high fidelity in capturing and detecting respiratory wheezes and patterns across diverse and pertinent settings. It achieved accuracy, sensitivity, and specificity of 95%, 96%, and 93%, respectively, with an AUC of 0.99 on the test set-outperforming the deterministic time-frequency approach. Furthermore, the accelerometer patch outperforms the digital stethoscopes in sound analysis while offering immunity to ambient sounds, which not only enhances data quality and performance for computational wheeze detection by a significant margin but also provides a robust sensor solution that can quantify respiration patterns simultaneously.

Detection of pathological mechano-acoustic signatures using precision accelerometer contact microphones in patients with pulmonary disorders.

Monitoring pathological mechano-acoustic signals emanating from the lungs is critical for timely and cost-effective healthcare delivery. Adventitious lung sounds including crackles, wheezes, rhonchi, bronchial breath sounds, stridor or pleural rub and abnormal breathing patterns function as essential clinical biomarkers for the early identification, accurate diagnosis and monitoring of pulmonary disorders. Here, we present a wearable sensor module comprising of a hermetically encapsulated, high precision accelerometer contact microphone (ACM) which enables both episodic and longitudinal assessment of lung sounds, breathing patterns and respiratory rates using a single integrated sensor. This enhanced ACM sensor leverages a nano-gap transduction mechanism to achieve high sensitivity to weak high frequency vibrations occurring on the surface of the skin due to underlying lung pathologies. The performance of the ACM sensor was compared to recordings from a state-of-art digital stethoscope, and the efficacy of the developed system is demonstrated by conducting an exploratory research study aimed at recording pathological mechano-acoustic signals from hospitalized patients with a chronic obstructive pulmonary disease (COPD) exacerbation, pneumonia, and acute decompensated heart failure. This unobtrusive wearable system can enable both episodic and longitudinal evaluation of lung sounds that allow for the early detection and/or ongoing monitoring of pulmonary disease.

Patient recall of health care provider counseling for opioid-acetaminophen prescriptions.

OBJECTIVE: The aim of this study was to determine the frequency and nature of physician, nurse, and pharmacist verbal counseling at the time of a new prescription for an opioid-acetaminophen containing medication as recalled by patients. DESIGN: A mixed methods approach with data from cross sectional, structured interviews was used. SETTING: The settings were one academic emergency department in Chicago, IL and one outpatient pharmacy at a public hospital in Atlanta, GA. PATIENTS: One hundred forty-nine patients receiving a new prescription for an opioid-acetaminophen medication were enrolled. METHODS: Interviews assessed patient recall of counseling they received from their physician, nurse, and pharmacist upon receiving the new prescription. Their responses were unitized and assigned to categories. RESULTS: One hundred forty-nine patients were enrolled; 61.1% African American and 58.4% female. Seven major categories of responses were noted; frequencies of patient recall for counseling in these categories were reported. Four categories related to the content of the counseling discussion were (1) details of administration (patient recall counseling from: physician/nurse only 44.3%, pharmacist only 5.4%, both providers 12.8%); (2) activities to avoid and side effects (36.2%, 4.7%, 8.7%); (3) medication indication (32.9%, 4%, 4%); and (4) addictive potential (9.3%, 1.3%, 0%). Three categories describe patients' recall of the interaction in broad terms: (5) being referred to print informational material accompanying the prescription (MD/RN only 7.4%, pharmacist only 20.1%, both providers 2.7%); (6) having questions solicited (0%, 11.4%, 0%); (7) having no interaction relating to medication counseling (3.4%, 32.2%, 1.3%). CONCLUSIONS: Patients infrequently recall counseling from providers on topics that are important to prevent harm from opioid-acetaminophen prescriptions. Future patient-centered clinical research should target identifying optimal strategies to convey these critical messages.

Risk of unintentional overdose with non-prescription acetaminophen products.

BACKGROUND: There is increasing concern over the risk of consumer unintentional misuse of non-prescription (a.k.a. 'over-the-counter') medications containing acetaminophen, which could lead to acute liver failure. OBJECTIVE: To determine the prevalence of potential misuse and overdose of over-the-counter medications containing acetaminophen, either alone or in combination. DESIGN: Cross-sectional, structured interviews with literacy assessment. SETTING: One academic and one community-based general internal medicine practice in Chicago, IL, and one academic general internal medicine practice and a public hospital clinic in Atlanta, GA. PATIENTS: Five hundred adults seeking primary care, ages 18-80. MEASUREMENT: Demonstration of how and when patients would take over-the-counter medications containing acetaminophen, alone or in combination with one another, over a 24-hour period. RESULTS: Overall, 23.8 % of participants demonstrated they would overdose on a single over-the-counter acetaminophen product by exceeding a dose of four grams in a 24-hour period; 5.2 % made serious errors by dosing out more than six grams. In addition, 45.6 % of adults demonstrated they would overdose by 'double-dipping' with two acetaminophen-containing products. In multivariable analyses, limited literacy (Relative Risk Ratio (RR) 1.65, 95 % Confidence Interval (CI) 1.03-2.66) and heavy acetaminophen use in the past six months (RR 1.70, 95 % CI 1.10-2.64) were independently associated with overdosing over-the-counter products. CONCLUSION: Misunderstanding of the active ingredient and proper instructions for over-the-counter medications containing acetaminophen is common. The potential for errors and adverse events associated with unintentional misuse of these products is substantial, particularly among heavy users of acetaminophen and those with limited literacy.

Patient communication during handovers between emergency medicine and internal medicine residents.

BACKGROUND: Communication failures are a key cause of medical errors and are particularly prevalent during handovers of patients between services. OBJECTIVE: To explore current perceptions of effectiveness in communicating critical patient information during admission handovers between emergency medicine (EM) residents and internal medicine (IM) residents. METHODS: Study design was a survey of IM and EM residents at a large urban hospital. Residents were surveyed about whether critical information was communicated during patient handovers. Measurements included comparisons between IM and EM residents about their perceptions of effective communication of key patient information and the quality of handovers. RESULTS: Ninety-three percent of EM residents (50 of 54) and 80% of IM residents (74 of 93) responded to the survey. The EM residents judged their handover performance to be better than how their IM colleagues assessed them on most questions. The IM residents reported that one-half of the time, EM residents provided organized and clear information, whereas EM residents self-reported that they did so most of the time (80%-90%). The IM residents reported that 25% of handovers were suboptimal and resulted in admission to an inappropriate level of care, and 10% led to harm or delay in care. The EM residents reported suboptimal communication was less common (5%). On the global assessment of whether the admission handover provided the information needed for good patient care, IM residents rated the quality of the handover data lower than did responding EM residents. CONCLUSIONS: There are gaps in communicating critical patient information during admission handovers as perceived by EM and IM residents. This information can form the basis for efforts to improve these handovers.

Developing consumer-centered, nonprescription drug labeling a study in acetaminophen.

BACKGROUND: In the U.S., acetaminophen overdose has surpassed viral hepatitis as the leading cause of acute liver failure, and misuse contributes to more than 30,000 hospitalizations annually. Half to two thirds of acetaminophen overdoses are unintentional, suggesting the root cause is likely poor understanding of medication labeling or failure to recognize the consequences of exceeding the recommended maximum daily dosage. PURPOSE: Elicit subject feedback about active ingredient and dosing information on over-the-counter (OTC) acetaminophen and elicit feedback on proposed plain-language text and icons. METHODS: Six focus groups, preceded by individual interviews, were conducted in April 2010 among 45 adults in two cities from two clinics and an adult basic education center. The individual interviews evaluated knowledge of OTC pain relievers, attention to product label information and literacy level while the group discussion elicited preference for label messages and icons. Analyses were conducted from April to June 2010. RESULTS: Forty-four percent read at or below the 6th-grade level. Individual interviews revealed that <50% of participants routinely examine product label information. Only 31% know acetaminophen is in Tylenol®. The groups achieved consensus on a preferred icon for acetaminophen, desired explicit statement of potential liver damage in the warning against simultaneous use of acetaminophen products, and indicated preference for an icon and wording for maximum dose. CONCLUSIONS: With the high prevalence of OTC use, a consumer-centered approach to developing icons and messages to promote awareness and safe use of acetaminophen could benefit consumers.

On-site Night Float by Attending Physicians: A Model to Improve Resident Education and Patient Care.

BACKGROUND: In 2003, the Accreditation Council for Graduate Medical Education instituted common duty hour limits, and in 2008 the Institute of Medicine recommended additional limits on continuous duty hours. Using a night-float system is an accepted approach for adhering to duty hour mandates. OBJECTIVE: To determine the effect of an on-site night-float attending physician on resident education and patient care. METHODS: Night-float residents and daytime ward residents were surveyed at the end of their rotation about the impact of an on-site night-float attending physician on education and quality of patient care. Responses were provided on a 5-point Likert scale ranging from 1, strongly agree, to 5, strongly disagree. RESULTS: Overall, 92 of the 140 distributed surveys were completed (66% response rate). Night-float residents found the night-float attending physician to be helpful with cross-cover issues (mean  =  2.00), initial history and physical examination (mean  =  1.56), choosing appropriate diagnostic tests (mean  =  1.79), developing a treatment plan (mean  =  1.74), and improving overall patient care (mean  =  1.91). Daytime ward residents were very satisfied with the quality of the admission workups (mean  =  1.78), tests and diagnostic procedures (mean  =  1.76), and initial treatment plan (mean  =  1.62) provided by the night-float service. CONCLUSION: A night-float system that includes on-site attending physician supervision can provide a valuable opportunity for resident education and may help improve the quality of patient care.

The HCAP gap: differences between self-reported practice patterns and published guidelines for health care-associated pneumonia.

BACKGROUND: Health care-associated pneumonia (HCAP) is prevalent among hospitalized patients. In contrast to community-acquired pneumonia (CAP), patients with HCAP are at increased risk for multidrug-resistant organisms, and appropriate initial antibiotic therapy is associated with reduced mortality. METHODS: An online survey was distributed to faculty and housestaff at 4 academic medical centers. The survey required respondents to choose initial antibiotic therapy for 9 hypothetical pneumonia cases (7 cases of HCAP and 2 cases of CAP). Answers were considered correct if the antibiotic regimen chosen was consistent with published guidelines. In addition, physicians rated their knowledge of current guidelines, as well as their level of agreement with guideline recommendations. RESULTS: Surveys were sent to 1313 physicians with a response rate of 65% (n = 855). Respondents included physicians in the following categories: hospital medicine/internal medicine, 60%; emergency medicine, 25%; and critical care, 13%. Respondents selected guideline-concordant antibiotic regimens 78% of the time for CAP, but only 9% of the time for HCAP. Because mean scores for HCAP questions were extremely low (mean, 0.63 correct answers out of 7), differences in performance between groups were too small to be meaningful. Despite their poor performance, 71% of the respondents stated that they are aware of published guidelines for HCAP, and 79% stated that they agree with and practice according to the guidelines. CONCLUSIONS: In this survey, physicians reported they were aware of, agreed with, and practiced according to published pneumonia guidelines; however, the overwhelming majority did not choose guideline-concordant therapy when tested.

Internal medicine training in the inpatient setting. A review of published educational interventions.

PURPOSE: Although the inpatient setting has served as the predominant educational site of internal medicine training programs, many changes and factors are currently affecting education in this setting. As a result, many educational organizations are calling for reforms in inpatient training. This report reviews the available literature on specific internal medicine inpatient educational interventions and proposes recommendations for improving internal medicine training in this setting. METHOD: We searched Medline for articles published between 1966 and August 2004 which focused on internal medicine training interventions in the inpatient setting; bibliographies of Medline-identified articles, as well as articles suggested by experts in the field provided additional citations. We then reviewed, classified, and abstracted only articles where an assessment of learner outcomes was included. RESULTS: Thirteen studies of inpatient internal medicine educational interventions were found that included an outcome assessment. All were single institution studies. The majority of these studies was of poor methodological quality and focused on specific content areas of internal medicine. None assessed the effectiveness or impact of internal medicine core inpatient experiences or curriculum. CONCLUSION: This review identifies significant gaps in our understanding of what constitutes effective inpatient education. The paucity of high quality research in the internal medicine inpatient setting highlights the urgent need to formally define and study what constitutes an effective "core" inpatient curriculum.