Category: Nevin Manimala

JMIR Ment Health. 2022 Aug 15;9(8):e39807. doi: 10.2196/39807.

ABSTRACT

BACKGROUND: Artificial intelligence has the potential to innovate current practices used to detect the imminent risk of suicide and to address shortcomings in traditional assessment methods.

OBJECTIVE: In this paper, we sought to automatically classify short segments (40 milliseconds) of speech according to low versus imminent risk of suicide in a large number (n=281) of telephone calls made to 2 telehealth counselling services in Australia.

METHODS: A total of 281 help line telephone call recordings sourced from On The Line, Australia (n=266, 94.7%) and 000 Emergency services, Canberra (n=15, 5.3%) were included in this study. Imminent risk of suicide was coded for when callers affirmed intent, plan, and the availability of means; level of risk was assessed by the responding counsellor and reassessed by a team of clinical researchers using the Columbia Suicide Severity Rating Scale (=5/6). Low risk of suicide was coded for in an absence of intent, plan, and means and via Columbia suicide Severity Scale Ratings (=1/2). Preprocessing involved normalization and pre-emphasis of voice signals, while voice biometrics were extracted using the statistical language r. Candidate predictors were identified using Lasso regression. Each voice biomarker was assessed as a predictor of suicide risk using a generalized additive mixed effects model with splines to account for nonlinearity. Finally, a component-wise gradient boosting model was used to classify each call recording based on precoded suicide risk ratings.

RESULTS: A total of 77 imminent-risk calls were compared with 204 low-risk calls. Moreover, 36 voice biomarkers were extracted from each speech frame. Caller sex was a significant moderating factor (β=-.84, 95% CI -0.85, -0.84; t=6.59, P<.001). Candidate biomarkers were reduced to 11 primary markers, with distinct models developed for men and women. Using leave-one-out cross-validation, ensuring that the speech frames of no single caller featured in both training and test data sets simultaneously, an area under the precision or recall curve of 0.985 was achieved (95% CI 0.97, 1.0). The gamboost classification model correctly classified 469,332/470,032 (99.85%) speech frames.

CONCLUSIONS: This study demonstrates an objective, efficient, and economical assessment of imminent suicide risk in an ecologically valid setting with potential applications to real-time assessment and response.

TRIAL REGISTRATION: Australian New Zealand Clinical Trials Registry ACTRN12622000486729; https://www.anzctr.org.au/ACTRN12622000486729.aspx.

PMID:35969444 | DOI:10.2196/39807

JMIR Form Res. 2022 Aug 15;6(8):e37054. doi: 10.2196/37054.

ABSTRACT

BACKGROUND: Machine learning uses algorithms that improve automatically through experience. This statistical learning approach is a natural extension of traditional statistical methods and can offer potential advantages for certain problems. The feasibility of using machine learning techniques in health care is predicated on access to a sufficient volume of data in a problem space.

OBJECTIVE: This study aimed to assess the feasibility of data collection from an adolescent population before and after a posterior spine fusion operation.

METHODS: Both physical and psychosocial data were collected. Adolescents scheduled for a posterior spine fusion operation were approached when they were scheduled for the surgery. The study collected repeated measures of patient data, including at least 2 weeks prior to the operation and 6 months after the patients were discharged from the hospital. Patients were provided with a Fitbit Charge 4 (consumer-grade health tracker) and instructed to wear it as often as possible. A third-party web-based portal was used to collect and store the Fitbit data, and patients were trained on how to download and sync their personal device data on step counts, sleep time, and heart rate onto the web-based portal. Demographic and physiologic data recorded in the electronic medical record were retrieved from the hospital data warehouse. We evaluated changes in the patients’ psychological profile over time using several validated questionnaires (ie, Pain Catastrophizing Scale, Patient Health Questionnaire, Generalized Anxiety Disorder Scale, and Pediatric Quality of Life Inventory). Questionnaires were administered to patients using Qualtrics software. Patients received the questionnaire prior to and during the hospitalization and again at 3 and 6 months postsurgery. We administered paper-based questionnaires for the self-report of daily pain scores and the use of analgesic medications.

RESULTS: There were several challenges to data collection from the study population. Only 38% (32/84) of the patients we approached met eligibility criteria, and 50% (16/32) of the enrolled patients dropped out during the follow-up period-on average 17.6 weeks into the study. Of those who completed the study, 69% (9/13) reliably wore the Fitbit and downloaded data into the web-based portal. These patients also had a high response rate to the psychosocial surveys. However, none of the patients who finished the study completed the paper-based pain diary. There were no difficulties accessing the demographic and clinical data stored in the hospital data warehouse.

CONCLUSIONS: This study identifies several challenges to long-term medical follow-up in adolescents, including willingness to participate in these types of studies and compliance with the various data collection approaches. Several of these challenges-insufficient incentives and personal contact between researchers and patients-should be addressed in future studies.

PMID:35969442 | DOI:10.2196/37054

J Med Internet Res. 2022 Aug 11;24(8):e37936. doi: 10.2196/37936.

ABSTRACT

BACKGROUND: The efficacy of pre-exposure prophylaxis (PrEP) is highly dependent on adherence, and one of the main reasons for poor adherence is forgetfulness. Therefore, it is important to explore how to remind users to take their medicine on time.

OBJECTIVE: This study aims to explore the effect of a reminder system on PrEP adherence in men who have sex with men (MSM) to improve adherence. The main function of the reminder system based on the WeChat social media app is to send daily messages to PrEP users reminding them to take their medicine.

METHODS: An open-label, multicenter, prospective cohort study of PrEP in HIV-negative MSM was conducted from November 2019 to June 2021. Study participants who met the criteria were randomly divided into 2 groups: no-reminder group and reminder group. Both groups received daily oral PrEP with follow-up every 3 months. Adherence was measured on the basis of self-report and was defined as the percentage of medications taken on time. Participants in the reminder group scanned a WeChat QR code and received a reminder message every day. Participants in the no-reminder group took daily oral medicines without reminders. The longitudinal trajectories of adherence for both groups were displayed to compare the variability in adherence at each time point. The association between the changes in adherence (no change, improvement, decline) at each time point and the use of the reminder system was analyzed by multinomial logistic regression models to further explore the effectiveness of the system.

RESULTS: A total of 716 MSM were included in the analysis, that is, 372 MSM in the no-reminder group and 344 MSM in the reminder group. Adherence in the no-reminder group fluctuated between 0.75 and 0.80 and that in the reminder group gradually increased over time from 0.76 to 0.88. Adherence at each time point was not statistically different between the 2 groups. Further analysis showed that an improvement in adherence in the early stage was associated with the use of the reminder system (odds ratio [OR] 1.65, 95% CI 1.01-2.70; P=.04). An improvement in average adherence compared to initial adherence was positively associated with the use of the reminder system (OR 1.82, 95% CI 1.10-3.01; P=.02).

CONCLUSIONS: The effect of the reminder system on PrEP adherence in MSM was more significant in the early stage, which is related to the increased motivation of users and the development of medicine-taking habits. The reminder system is potentially effective for early-stage medicine management, encouraging users to develop healthy medicine-taking habits and to increase their adherence.

TRIAL REGISTRATION: Chinese Clinical Trial ChiCTR190026414; http://www.chictr.org.cn/showproj.aspx?proj=35077.

PMID:35969436 | DOI:10.2196/37936

J Med Internet Res. 2022 Aug 15;24(8):e34858. doi: 10.2196/34858.

ABSTRACT

BACKGROUND: A computer application called the National Death Information System (SINADEF) was implemented in Peru so that physicians can prepare death certificates in electronic format and the information is available online. In 2018, only half of the estimated deaths in Peru were certified using SINADEF. When a death is certified in paper format, the probability being entered in the mortality database decreases. It is important to know, from the user’s perspective, the factors that can influence the successful implementation of SINADEF. SINADEF can only be successfully implemented if it is known whether physicians believe that it is useful and easy to operate.

OBJECTIVE: The aim of this study was to identify the perceptions of physicians and other factors as predictors of their behavioral intention to use SINADEF to certify a death.

METHODS: This study had an observational, cross-sectional design. A survey was provided to physicians working in Peru, who used SINADEF to certify a death for a period of 12 months, starting in November 2019. A questionnaire was adapted based on the Technology Acceptance Model. The questions measured the dimensions of subjective norm, image, job relevance, output quality, demonstrability of results, perceived usefulness, perceived ease of use, and behavioral intention to use. Chi-square and logistic regression tests were used in the analysis, and a confidence level of 95% was chosen to support a significant association.

RESULTS: In this study, 272 physicians responded to the survey; 184 (67.6%) were men and the average age was 45.3 (SD 10.1) years. The age range was 24 to 73 years. In the bivariate analysis, the intention to use SINADEF was found to be associated with (1) perceived usefulness, expressed as “using SINADEF avoids falsifying a death certificate” (P<.001), “using SINADEF reduces the risk of errors” (P<.001), and “using SINADEF allows for filling out a certificate in less time” (P<.001); and (2) perceived ease of use, expressed as “I think SINADEF is easy to use” (P<.001). In the logistic regression, perceived usefulness (odds ratio [OR] 8.5, 95% CI 2.2-32.3; P=.002), perceived ease of use (OR 10.1, 95% CI 2.4-41.8; P=.001), and training in filling out death certificates (OR 8.3, 95% CI 1.6-42.8; P=.01) were found to be predictors of the behavioral intention to use SINADEF.

CONCLUSIONS: The behavioral intention to use SINADEF was related to the perception that it is an easy-to-use system, the belief that it improves the performance of physicians in carrying out the task at hand, and with training in filling out death certificates.

PMID:35969435 | DOI:10.2196/34858

Scand J Pain. 2022 Aug 16. doi: 10.1515/sjpain-2022-0055. Online ahead of print.

ABSTRACT

OBJECTIVES: Existing equipment for quantitative sensory testing is generally expensive and not easily applicable in a clinical setting thus simple bed-side devices are warranted. Pressure hyperalgesia is a common finding in patients with musculoskeletal pain and an experimental model is delayed-onset muscle soreness (DOMS). DOMS is characterised by muscle hyperalgesia and some studies report facilitation of temporal summation of pain. This study aimed to detect DOMS induced muscle hyperalgesia and temporal summation of pain using a newly developed bed-side quantitative sensory testing device to deliver standardised pressure.

METHODS: Twenty-two healthy participants participated in two sessions with the second session approximately 48 h after baseline. Pressure pain intensities were assessed from the gastrocnemius muscle with four probes calibrated to apply 2, 4, 6 and 8 kg, respectively. Temporal summation of pain (10 stimuli delivered at 0.5 Hz using the 6 kg probe) intensities were assessed from the same location. DOMS was evoked in the gastrocnemius muscle by an eccentric exercise. Sleepiness and physical activity were measured with the Epworth Sleepiness Scale and the Global Physical Activity Questionnaire to investigate if they were associated with the quantitative sensory testing measures.

RESULTS: Pressure pain intensity was significantly increased 48 h after induction of DOMS when compared to baseline for all four probes (p<0.05). Temporal summation of pain was not statistically significant affected by DOMS and sleep quality and physical activity did not associate with any of the measures.

CONCLUSIONS: This study introduces a simple, bed-side assessment tool for the assessment of pressure pain intensity and hence hyperalgesia and temporal summation of pain.

PMID:35969427 | DOI:10.1515/sjpain-2022-0055

Ann Am Thorac Soc. 2022 Aug 15. doi: 10.1513/AnnalsATS.202203-226OC. Online ahead of print.

ABSTRACT

Rationale: Chronic Obstructive Pulmonary Disease (COPD) mortality risk is often estimated using the BODE index (including body mass index, forced expiratory volume in one second (FEV1), dyspnea score, and six-minute walk distance). Diffusing capacity (DLCO) is a potential predictor of mortality that reflects physiology distinct from that in the BODE index. Objectives: This study evaluated DLCO as a predictor of mortality using participants from the COPDGene study. Methods: We performed time-to-event analyses of individuals with COPD (former/current smokers with FEV1/FVC <0.7) and DLCO measurements from the COPDGene Phase 2 visit. Cox proportional hazard methods were used to model survival, adjusting for age, sex, pack-years, smoking status, BODE index, computed tomography (CT) percent emphysema (low attenuation areas <-950 Hounsfield units), CT airway wall thickness, and history of cardiovascular or kidney diseases. C-statistics for models with DLCO and BODE score were used to compare discriminative accuracy. Results: Of 2329 participants, 378(16.8%) died during the follow-up period (median 4.9 years). In adjusted analyses, for every 10% decrease in DLCO %predicted, mortality increased by 29% (Hazard ratio 1.29, 95% CI 1.17 – 1.41, p<0.001). When compared to other clinical predictors, DLCO %predicted performed similarly to BODE (C-statistic DLCO 0.68, BODE 0.70), and the addition of DLCO to BODE improved its discriminative accuracy (C-statistic 0.71). Conclusions: Diffusing capacity, a measure of gas transfer, strongly predicted all-cause mortality in individuals with COPD, independent of BODE index and CT evidence of emphysema and airway wall thickness. These findings support inclusion of DLCO in prognostic models for COPD.

PMID:35969416 | DOI:10.1513/AnnalsATS.202203-226OC

JMIR Form Res. 2022 Aug 12;6(8):e37163. doi: 10.2196/37163.

ABSTRACT

BACKGROUND: The Philippines HIV epidemic is one of the fastest growing epidemics globally, and infections among men who have sex with men are increasing at an alarming rate. Connect for Life Philippines is a mobile health (mHealth) intervention that supports antiretroviral therapy (ART) adherence in this key population through individualized voice calls and SMS text messages.

OBJECTIVE: The objective of this process evaluation is to assess the intervention reach, dose delivered and received, fidelity, and acceptability and to describe contextual factors affecting the implementation of an mHealth adherence support intervention for patients on ART in a clinic in Metro Manila, Philippines.

METHODS: A mixed methods process evaluation approach was used in an observational cohort study. Quantitative data sources for the process evaluation were call and SMS text message logs obtained from the mHealth platform and questionnaires collected at 12-, 24-, and 48-week study visits. Qualitative data were collected from process reports and through a series of focus group discussions conducted with a subset of participants during the intervention development phase, after an initial 8-week pilot phase, and at the end of the study.

RESULTS: The 462 study participants received 31,095 interactive voice calls and 8234 SMS text messages during the study. Owing to technical issues, intervention fidelity was low, with only 22.1% (102/462) of the participants receiving reminders via voice calls and others (360/462, 77.9%) receiving only SMS text messages during the intervention. After 48 weeks in the study, 63.5% (293/462) of the participants reported that they would be quite likely or very likely to recommend the program to a friend, and 53.8% (249/462) of the participants reported that they benefited quite a bit or very much from the intervention. Participants who were on ART for <6 months at the beginning of the study and those who received the daily or weekly pill reminders were more likely to report that they benefited from the intervention (P=.02 and P=.01, respectively).

CONCLUSIONS: The Connect for Life intervention had high participant satisfaction and acceptability, especially among those who received high dose of the intervention. However, poor reliability of local telecommunication networks had a large impact on the intervention’s usability, fidelity, and dose received.

PMID:35969425 | DOI:10.2196/37163

JAMA Netw Open. 2022 Aug 1;5(8):e2226691. doi: 10.1001/jamanetworkopen.2022.26691.

ABSTRACT

IMPORTANCE: Despite increasing interest in assessing patient social needs in health care settings, there has been little research examining the performance of housing-related screening questions.

OBJECTIVE: To examine the performance of 2 single-item screening questions assessing emergency department (ED) patients’ self-perceived risk of future homelessness.

DESIGN, SETTING, AND PARTICIPANTS: This prospective cohort study was conducted among a randomly selected sample of adult ED patients from 2016 to 2017 in a public hospital ED in New York City. Data were analyzed from September 2019 through October 2021.

EXPOSURES: Responses on patient surveys conducted at the baseline ED visit for 2 single-item screening questions on self-perceived risk for future housing instability and homelessness were collected. One question asked patients if they were worried about having stable housing in the next 2 months, and the other question asked them to rate the likelihood that they would enter a homeless shelter in the next 6 months.

OUTCOMES: Homeless shelter entry 2, 6, and 12 months after an ED visit, assessed using shelter administrative data in the study city, which was linked with participant baseline survey responses.

RESULTS: There were 1919 study participants (976 [51.0%] men and 931 [48.6%] women among 1915 individuals with gender data; 700 individuals aged 31-50 years [36.5%] among 1918 individuals with age data; 1126 Hispanic or Latinx individuals [59.0%], 368 non-Hispanic Black individuals [19.3%], and 225 non-Hispanic White individuals [11.8%] among 1908 individuals with race and ethnicity data). Within 2, 6, and 12 months of the ED visit, 45 patients (2.3%), 66 patients (3.4%), and 95 patients (5.0%) had entered shelter, respectively. For both single-item screening questions, participants who answered affirmatively had significantly higher likelihood of future shelter entry at each time point examined (eg, at 2 months: 31 participants responding yes [6.5%] vs 14 participants responding no [1.0%] to the question concerning being worried about having stable housing in the next 2 months). Sensitivity of the screening questions ranged from 0.27 to 0.69, specificity from 0.76 to 0.97, positive predictive value from 0.07 to 0.27, and area under the receiver operating characteristic curve from 0.62 to 0.72.

CONCLUSIONS AND RELEVANCE: This study found that 2 single-item screening questions assessing ED patient self-perceived risk of future housing instability and homelessness had adequate to good performance in identifying risk for future shelter entry. Such single-item screening questions should be further tested before broad adoption.

PMID:35969399 | DOI:10.1001/jamanetworkopen.2022.26691

JAMA Netw Open. 2022 Aug 1;5(8):e2226701. doi: 10.1001/jamanetworkopen.2022.26701.

ABSTRACT

IMPORTANCE: When society introduces and accepts new transportation modes, it is important to map risks and benefits.

OBJECTIVE: To compare electric scooter (e-scooter) and bicycle injuries.

DESIGN, SETTING, AND PARTICIPANTS: This cohort study is based on prospectively collected data on Norwegian patients who sustained e-scooter or bicycle injuries and presented to an emergency department affiliated with Oslo University Hospital between January 1, 2019, and March 31, 2020.

MAIN OUTCOMES AND MEASURES: e-Scooter and bicycle injuries were evaluated for associations with sex, age, time of injury, helmet use, intoxication, body region, and injury severity. Descriptive statistics are presented as mean (SD) or number with percentage, with significance set at P < .05 (2-tailed).

RESULTS: During the study period, 3191 patients were included (850 e-scooter riders, 2341 bicyclists) with 3839 injuries recorded (997 e-scooter, 2842 bicycle). The mean (SD) age of those injured was 34 (17) years, 2026 riders (63.5%) were male, 1474 (46.2%) were helmeted at the time of injury, and 516 (16.2%) were intoxicated by alcohol or other drugs. The annual incidence of injuries was 120 per 100 000 inhabitants for e-scooters and 340 per 100 000 inhabitants for bicycles. Men were overrepresented in both groups (529 e-scooter riders [62.2%] and 1497 bicyclists [63.9%]). e-Scooter riders were younger than bicyclists (mean [SD] age, 31 [12] vs 35 [18] years). Most injured e-scooter riders were aged 20 to 40 years, whereas injured bicyclists had a broader age distribution. e-Scooter injuries commonly occurred on weekends (378 [46.6%]) and during evening (230 [32.3%]) or nighttime (242 [34.1%]) hours. Most bicycle injuries occurred during weekdays (1586 [69.7%]) and daytime (1762 [61.3%]). e-Scooter riders were more often intoxicated (336 [39.5%] vs 180 [7.7%]) and had a lower rate of helmet use (18 [2.1%] vs 1456 [62.2%]). During nighttime, 230 injured e-scooter riders (91.3%) and 86 bicyclists (69.4%) were intoxicated. e-Scooter riders had more head and neck (317 [31.7%] vs 636 [22.4%]) and lower-limb (285 [28.6%] vs 632 [22.2%]) injuries and fewer upper-limb (341 [34.2%] vs 1276 [44.9%]), thoracic (41 [4.1%] vs 195 [6.9%]), and abdominal, pelvic, and lumbar (13 [1.3%] vs 103 [3.6%]) injuries.

CONCLUSIONS AND RELEVANCE: In this cohort study, e-scooter riders were younger than bicyclists, did not use helmets, were more often intoxicated, and were more often injured during nighttime. The rate of intoxication among e-scooter riders injured at night was high. Preventive measures, including awareness campaigns, regulating e-scooter availability, improving infrastructure, and implementing stricter helmet and alcohol policies, may prove effective for reducing injuries.

PMID:35969397 | DOI:10.1001/jamanetworkopen.2022.26701

JAMA Neurol. 2022 Aug 15. doi: 10.1001/jamaneurol.2022.2290. Online ahead of print.

ABSTRACT

IMPORTANCE: Drug-resistant epilepsy (DRE) is thought to be associated with increased mortality, but larger population-based studies are lacking. Additionally, the benefit of effective management in DRE lacks evidence.

OBJECTIVE: To examine the association of utilization of care with mortality in US veterans with DRE.

DESIGN, SETTING, AND PARTICIPANTS: Observational cohort study conducted between October 1, 2013, and March 31, 2020. Mortality statistics in US veterans with DRE were compared to the US general population and all veterans within the Veterans Health Administration. Epilepsy was defined as use of 1 or more antiseizure medications (ASMs) for 30 days or longer with a seizure diagnosis or 1 inpatient or 2 outpatient encounters with an epilepsy diagnosis. DRE was defined as the use of 2 or more ASMs. Among 9.6 million US veterans, 164 435 (1.7%) had epilepsy, of whom 55 571 (33.8%) had DRE. Epilepsy and DRE were administratively identified based on criteria noted in design. Identified participants were included for analysis.

EXPOSURES: Veterans with DRE.

MAIN OUTCOMES AND MEASURES: Standardized mortality ratio (SMR).

RESULTS: Among US veterans with DRE, the mean (SD) age was 58.3 (15.4) years, and 49 430 individuals (88.9%) were male. Of ethnicity data gathered, 3170 individuals (5.7%) were Hispanic or Latino, 50 599 (91.1%) were not Hispanic or Latino, 842 (1.5%) declined to answer, and 960 (1.7%) were recorded as unknown. Of race data gathered, 516 individuals (0.9%) were American Indian or Alaskan Native, 270 (0.5%) were Asian, 11 316 (20.4%) were Black or African American, 587 (1.1%) were of multiple races, 453 (0.8%) were Native Hawaiian or Pacific Islander, 39 543 (71.2%) were White, 1697 (3.1%) declined to answer, and 1189 (2.1%) were recorded as unknown. SMR was 1.50 (95% CI, 1.47-1.53) compared with the US general population and 1.56 (95% CI, 1.53-1.59) compared with all veterans. Utilization rates were 81.1% (n = 45 057) for neurology clinic evaluation, 66.4% (n = 36 905) for magnetic resonance imaging (MRI), and 49.6% (n = 27 546) for electroencephalography (EEG) testing. Only 8350 individuals (15.0%) had comprehensive epilepsy evaluations and 3357 (6.0%) had epilepsy monitoring. Multivariable analysis revealed an association between lower mortality and neurology clinic evaluation, EEG, MRI, epilepsy monitoring, and the use of more than 2 ASMs after adjusting for age and comorbidities.

CONCLUSIONS AND RELEVANCE: Mortality rates were significantly higher in US veterans with DRE compared to the general population. Better utilization of comprehensive epilepsy care, diagnostic services, and medications were each associated with reduced mortality. These findings indicate that appropriate management of DRE is critical in this population.

PMID:35969384 | DOI:10.1001/jamaneurol.2022.2290