Category: Nevin Manimala

PLOS Digit Health. 2022 Aug 8;1(8):e0000076. doi: 10.1371/journal.pdig.0000076. eCollection 2022 Aug.

ABSTRACT

OBJECTIVE: The Pediatric Emergency Care Applied Research Network (PECARN) has developed a clinical-decision instrument (CDI) to identify children at very low risk of intra-abdominal injury. However, the CDI has not been externally validated. We sought to vet the PECARN CDI with the Predictability Computability Stability (PCS) data science framework, potentially increasing its chance of a successful external validation.

MATERIALS & METHODS: We performed a secondary analysis of two prospectively collected datasets: PECARN (12,044 children from 20 emergency departments) and an independent external validation dataset from the Pediatric Surgical Research Collaborative (PedSRC; 2,188 children from 14 emergency departments). We used PCS to reanalyze the original PECARN CDI along with new interpretable PCS CDIs developed using the PECARN dataset. External validation was then measured on the PedSRC dataset.

RESULTS: Three predictor variables (abdominal wall trauma, Glasgow Coma Scale Score <14, and abdominal tenderness) were found to be stable. A CDI using only these three variables would achieve lower sensitivity than the original PECARN CDI with seven variables on internal PECARN validation but achieve the same performance on external PedSRC validation (sensitivity 96.8% and specificity 44%). Using only these variables, we developed a PCS CDI which had a lower sensitivity than the original PECARN CDI on internal PECARN validation but performed the same on external PedSRC validation (sensitivity 96.8% and specificity 44%).

CONCLUSION: The PCS data science framework vetted the PECARN CDI and its constituent predictor variables prior to external validation. We found that the 3 stable predictor variables represented all of the PECARN CDI’s predictive performance on independent external validation. The PCS framework offers a less resource-intensive method than prospective validation to vet CDIs before external validation. We also found that the PECARN CDI will generalize well to new populations and should be prospectively externally validated. The PCS framework offers a potential strategy to increase the chance of a successful (costly) prospective validation.

PMID:36812570 | DOI:10.1371/journal.pdig.0000076

PLOS Digit Health. 2022 Oct 20;1(10):e0000045. doi: 10.1371/journal.pdig.0000045. eCollection 2022 Oct.

ABSTRACT

Many studies have utilized physical activity for predicting mortality risk, using measures such as participant walk tests and self-reported walking pace. The rise of passive monitors to measure participant activity without requiring specific actions opens the possibility for population level analysis. We have developed novel technology for this predictive health monitoring, using limited sensor inputs. In previous studies, we validated these models in clinical experiments with carried smartphones, using only their embedded accelerometers as motion sensors. Using smartphones as passive monitors for population measurement is critically important for health equity, since they are already ubiquitous in high-income countries and increasingly common in low-income countries. Our current study simulates smartphone data by extracting walking window inputs from wrist worn sensors. To analyze a population at national scale, we studied 100,000 participants in the UK Biobank who wore activity monitors with motion sensors for 1 week. This national cohort is demographically representative of the UK population, and this dataset represents the largest such available sensor record. We characterized participant motion during normal activities, including daily living equivalent of timed walk tests. We then compute walking intensity from sensor data, as input to survival analysis. Simulating passive smartphone monitoring, we validated predictive models using only sensors and demographics. This resulted in C-index of 0.76 for 1-year risk decreasing to 0.73 for 5-year. A minimum set of sensor features achieves C-index of 0.72 for 5-year risk, which is similar accuracy to other studies using methods not achievable with smartphone sensors. The smallest minimum model uses average acceleration, which has predictive value independent of demographics of age and sex, similar to physical measures of gait speed. Our results show passive measures with motion sensors can achieve similar accuracy to active measures of gait speed and walk pace, which utilize physical walk tests and self-reported questionnaires.

PMID:36812566 | DOI:10.1371/journal.pdig.0000045

PLOS Digit Health. 2022 Jun 30;1(6):e0000061. doi: 10.1371/journal.pdig.0000061. eCollection 2022 Jun.

ABSTRACT

The Earable device is a behind-the-ear wearable originally developed to measure cognitive function. Since Earable measures electroencephalography (EEG), electromyography (EMG), and electrooculography (EOG), it may also have the potential to objectively quantify facial muscle and eye movement activities relevant in the assessment of neuromuscular disorders. As an initial step to developing a digital assessment in neuromuscular disorders, a pilot study was conducted to determine whether the Earable device could be utilized to objectively measure facial muscle and eye movements intended to be representative of Performance Outcome Assessments, (PerfOs) with tasks designed to model clinical PerfOs, referred to as mock-PerfO activities. The specific aims of this study were: To determine whether the Earable raw EMG, EOG, and EEG signals could be processed to extract features describing these waveforms; To determine Earable feature data quality, test re-test reliability, and statistical properties; To determine whether features derived from Earable could be used to determine the difference between various facial muscle and eye movement activities; and, To determine what features and feature types are important for mock-PerfO activity level classification. A total of N = 10 healthy volunteers participated in the study. Each study participant performed 16 mock-PerfOs activities, including talking, chewing, swallowing, eye closure, gazing in different directions, puffing cheeks, chewing an apple, and making various facial expressions. Each activity was repeated four times in the morning and four times at night. A total of 161 summary features were extracted from the EEG, EMG, and EOG bio-sensor data. Feature vectors were used as input to machine learning models to classify the mock-PerfO activities, and model performance was evaluated on a held-out test set. Additionally, a convolutional neural network (CNN) was used to classify low-level representations of the raw bio-sensor data for each task, and model performance was correspondingly evaluated and compared directly to feature classification performance. The model’s prediction accuracy on the Earable device’s classification ability was quantitatively assessed. Study results indicate that Earable can potentially quantify different aspects of facial and eye movements and may be used to differentiate mock-PerfO activities. Specially, Earable was found to differentiate talking, chewing, and swallowing tasks from other tasks with observed F1 scores >0.9. While EMG features contribute to classification accuracy for all tasks, EOG features are important for classifying gaze tasks. Finally, we found that analysis with summary features outperformed a CNN for activity classification. We believe Earable may be used to measure cranial muscle activity relevant for neuromuscular disorder assessment. Classification performance of mock-PerfO activities with summary features enables a strategy for detecting disease-specific signals relative to controls, as well as the monitoring of intra-subject treatment responses. Further testing is needed to evaluate the Earable device in clinical populations and clinical development settings.

PMID:36812552 | DOI:10.1371/journal.pdig.0000061

PLOS Digit Health. 2022 Jun 13;1(6):e0000062. doi: 10.1371/journal.pdig.0000062. eCollection 2022 Jun.

ABSTRACT

Risk scores are widely used for clinical decision making and commonly generated from logistic regression models. Machine-learning-based methods may work well for identifying important predictors to create parsimonious scores, but such ‘black box’ variable selection limits interpretability, and variable importance evaluated from a single model can be biased. We propose a robust and interpretable variable selection approach using the recently developed Shapley variable importance cloud (ShapleyVIC) that accounts for variability in variable importance across models. Our approach evaluates and visualizes overall variable contributions for in-depth inference and transparent variable selection, and filters out non-significant contributors to simplify model building steps. We derive an ensemble variable ranking from variable contributions across models, which is easily integrated with an automated and modularized risk score generator, AutoScore, for convenient implementation. In a study of early death or unplanned readmission after hospital discharge, ShapleyVIC selected 6 variables from 41 candidates to create a well-performing risk score, which had similar performance to a 16-variable model from machine-learning-based ranking. Our work contributes to the recent emphasis on interpretability of prediction models for high-stakes decision making, providing a disciplined solution to detailed assessment of variable importance and transparent development of parsimonious clinical risk scores.

PMID:36812536 | DOI:10.1371/journal.pdig.0000062

PLOS Digit Health. 2022 May 12;1(5):e0000032. doi: 10.1371/journal.pdig.0000032. eCollection 2022 May.

ABSTRACT

Skin cancers related to sunexposure are rising globally, yet largely preventable. Digital solutions enable individually tailored prevention and may play a crucial role in reducing disease burden. We developed SUNsitive, a theory-guided web app to facilitate sun protection and skin cancer prevention. The app collected relevant information through a questionnaire and provided tailored feedback on personal risk, adequate sun protection, skin cancer prevention, and overall skin health. SUNsitive’s effect on sun protection intentions and a set of secondary outcomes was evaluated with a two-arm randomized controlled trial (n = 244). At 2 weeks post-intervention, we did not find any statistical evidence for the intervention’s effect on the primary outcome or any of the secondary outcomes. However, both groups reported improved intentions to sun protect compared to their baseline values. Furthermore, our process outcomes suggest that approaching sun protection and skin cancer prevention with a digital tailored “questionnaire-feedback” format is feasible, well-perceived, and well accepted. Trial registration: Protocol registration: ISRCTN registry (ISRCTN10581468).

PMID:36812525 | DOI:10.1371/journal.pdig.0000032

PLOS Digit Health. 2022 Jun 3;1(6):e0000039. doi: 10.1371/journal.pdig.0000039. eCollection 2022 Jun.

ABSTRACT

Traditional disease surveillance is increasingly being complemented by data from non-traditional sources like medical claims, electronic health records, and participatory syndromic data platforms. As non-traditional data are often collected at the individual-level and are convenience samples from a population, choices must be made on the aggregation of these data for epidemiological inference. Our study seeks to understand the influence of spatial aggregation choice on our understanding of disease spread with a case study of influenza-like illness in the United States. Using U.S. medical claims data from 2002 to 2009, we examined the epidemic source location, onset and peak season timing, and epidemic duration of influenza seasons for data aggregated to the county and state scales. We also compared spatial autocorrelation and tested the relative magnitude of spatial aggregation differences between onset and peak measures of disease burden. We found discrepancies in the inferred epidemic source locations and estimated influenza season onsets and peaks when comparing county and state-level data. Spatial autocorrelation was detected across more expansive geographic ranges during the peak season as compared to the early flu season, and there were greater spatial aggregation differences in early season measures as well. Epidemiological inferences are more sensitive to spatial scale early on during U.S. influenza seasons, when there is greater heterogeneity in timing, intensity, and geographic spread of the epidemics. Users of non-traditional disease surveillance should carefully consider how to extract accurate disease signals from finer-scaled data for early use in disease outbreaks.

PMID:36812505 | DOI:10.1371/journal.pdig.0000039

Aging (Albany NY). 2023 Feb 20;15. doi: 10.18632/aging.204535. Online ahead of print.

ABSTRACT

Our study aimed to observe the correlation between epidermal growth factor receptor (EGFR) and programmed cell death-ligand 1 (PD-L1) expression and evaluate prognostic potential of their co-expression in esophageal squamous cell carcinoma (ESCC) patients. EGFR and PD-L1 expression were evaluated by immunohistochemical analysis. We revealed that there was a positive correlation between EGFR and PD-L1 expression in ESCC (P = 0.004). According to the positive relationship between EGFR and PD-L1, all patients were divided into four groups: EGFR (+)/PD-L1 (+), EGFR (+)/PD-L1 (-), EGFR (-)/PD-L1 (+), and EGFR (-)/PD-L1 (-). In 57 ESCC patients without surgery, we found that EGFR and PD-L1 co-expression were statistically correlated with a lower objective response rate (ORR) (p = 0.029), overall survival (OS) (p = 0.018) and progression-free survival (PFS) (p = 0.045) than those with one or none positive protein. Furthermore, PD-L1 expression has a significant positive correlation with infiltration level of 19 immune cells, EGFR expression was significantly correlated with infiltration level of 12 immune cells. The infiltration level of CD8 T cell and B cell were negatively correlated with EGFR expression. On the contrary with EGFR, the infiltration level of CD8 T cell, and B cell were positively correlated with PD-L1 expression. In conclusion, EGFR and PD-L1 co-expression could predict poor ORR and survival in ESCC without surgery, indicating a subset of patients who may benefit from a combination of targeted therapy against EGFR and PD-L1, which may expand the population benefiting from immunotherapy and reduce the occurrence of hyper progressive diseases.

PMID:36812484 | DOI:10.18632/aging.204535

Appl Physiol Nutr Metab. 2023 Feb 22. doi: 10.1139/apnm-2022-0425. Online ahead of print.

ABSTRACT

Disease-related malnutrition is common in hospital patients. The Health Standards Organization Canadian Malnutrition Prevention, Detection, and Treatment Standard was published in 2021. The purpose of this study was to determine the current state of nutrition care in hospitals prior to implementation of the Standard. An online survey was distributed to hospitals across Canada via email. A representative reported on nutrition best practices based on the Standard at the hospital level. Descriptive and bivariate statistics were completed for selected variables based on size and type of hospital. One hundred and forty-three responses from 9 provinces were received (56% community, 23% academic, 21% other). Malnutrition risk screening was being completed on admission in 74% (n=106/142) of hospitals, although not all units participated in screening all patients. Nutrition-focused physical exam is completed as part of a nutrition assessment in 74% (n=101/139) of sites. Flagging a malnutrition diagnosis (n= 38/104) and physician documentation (18/136) were sporadic. Academic and medium (100- 499 beds) and large hospitals (500+ beds) were more likely to have a physician document a malnutrition diagnosis. Some, but not all, best practices are occurring in Canadian hospitals on a regular basis. This demonstrates a need for continued knowledge mobilization of the Standard.

PMID:36812481 | DOI:10.1139/apnm-2022-0425

Lymphat Res Biol. 2023 Feb 22. doi: 10.1089/lrb.2022.0017. Online ahead of print.

ABSTRACT

Background: Breast cancer-related lymphedema (BCRL) is a common complication of breast cancer treatment. Anecdotal and qualitative research suggests that heat and hot weather cause an exacerbation of BCRL; however, there is little quantitative evidence to support this. The aim of this article is to investigate the relationship between seasonal climate variation and limb size, volume, fluid distribution, and diagnosis in women following breast cancer treatment. Methods and Results: Women older than the age of 35 years who had undergone treatment for breast cancer were invited to participate. Twenty-five women aged between 38 and 82 years were recruited. Seventy-two percent received surgery, radiation therapy, and chemotherapy as part of their breast cancer treatment. Participants completed anthropometric, circumferential, and bioimpedance measures and a survey on three occasions: November (spring), February (summer), and June (winter). Diagnostic criteria of >2 cm and >200 mL difference between the affected and unaffected arm, and a positive bioimpedance ratio of >1.139 for a dominant arm and >1.066 for nondominant arm was applied across the three measurement occasions. No significant correlation between seasonal variation in climate and upper limb size, volume, or fluid distribution were found in women diagnosed with or at risk of developing BCRL. Lymphedema diagnosis depends on the season and diagnostic measurement tool utilized. Conclusion: There was no statistically significant variation in limb size, volume, or fluid distribution in this population across spring, summer, and winter, although there were linked trends in these values. The diagnosis of lymphedema, however, varied between individual participants throughout the year. This has important implications for the implementation/commencement of treatment and management. Further research with a larger population in different climates is required to explore the status of women with respect to BCRL. The use of common clinical diagnostic criteria did not result in consistent diagnostic classification of BCRL for the women involved in this study.

PMID:36812466 | DOI:10.1089/lrb.2022.0017

JCO Oncol Pract. 2023 Feb 22:OP2200649. doi: 10.1200/OP.22.00649. Online ahead of print.

ABSTRACT

BACKGROUND: The COVID-19 pandemic led to the rapid implementation of remote work, but few studies have examined the impact. We evaluated clinical staff experience with working remotely at a large, urban comprehensive cancer center in Toronto, Canada.

METHODS: An electronic survey was disseminated between June 2021, and August 2021, via e-mail to staff who had completed at least some remote work during the COVID-19 pandemic. Factors associated with a negative experience were examined with binary logistic regression. Barriers were derived from a thematic analysis of open-text fields.

RESULTS: Most respondents (N = 333; response rate, 33.2%) were age 40-69 years (46.2%), female (61.3%), and physicians (24.6%). Although the majority of respondents wished to continue remote work (85.6%), relative to administrative staff (admin), physicians (odds ratio [OR], 16.6; 95% CI, 1.45 to 190.14) and pharmacists (OR, 12.6; 95% CI, 1.0 to 158.9) were more likely to want to return on-site. Physicians were approximately eight times more likely to report dissatisfaction with remote work (OR, 8.4; 95% CI, 1.4 to 51.6) and 24 times more likely to report that remote work negatively affected efficiency (OR, 24.0; 95% CI, 2.7 to 213.0); nurses were approximately seven times more likely to report the need for additional resources (OR, 6.5; 95% CI, 1.71 to 24.48) and/or training (OR, 7.02; 95% CI, 1.78 to 27.62). The most common barriers were the absence of fair processes for allocation of remote work, poor integration of digital applications and connectivity, and poor role clarity.

CONCLUSION: Although overall satisfaction with working remotely was high, work is needed to overcome barriers to implementation of remote and hybrid work models in the health care setting.

PMID:36812455 | DOI:10.1200/OP.22.00649