Search

BackgroundSuccessful integrations of machine learning into routine clinical care are exceedingly rare, and barriers to its adoption are poorly characterized in the literature. ObjectiveThis study aims to report a quality improvement effort to integrate a deep learning sepsis detection and management platform, Sepsis Watch, into routine clinical care. MethodsIn 2016, a multidisciplinary team consisting of statisticians, data scientists, data engineers, and clinicians was assembled by the leadership of an academic health system to radically improve the detection and treatment of sepsis. This report of the quality improvement effort follows the learning health system framework to describe the problem assessment, design, development, implementation, and evaluation plan of Sepsis Watch. ResultsSepsis Watch was successfully integrated into routine clinical care and reshaped how local machine learning projects are executed. Frontline clinical staff were highly engaged in the design and development of the workflow, machine learning model, and application. Novel machine learning methods were developed to detect sepsis early, and implementation of the model required robust infrastructure. Significant investment was required to align stakeholders, develop trusting relationships, define roles and responsibilities, and to train frontline staff, leading to the establishment of 3 partnerships with internal and external research groups to evaluate Sepsis Watch. ConclusionsMachine learning models are commonly developed to enhance clinical decision making, but successful integrations of machine learning into routine clinical care are rare. Although there is no playbook for integrating deep learning into clinical care, learnings from the Sepsis Watch integration can inform efforts to develop machine learning technologies at other health care delivery systems.

ImportanceLaser-assisted drug delivery (LADD) is used for various medical and cosmetic applications. However, there is insufficient evidence-based guidance to assist clinicians performing LADD.ObjectiveTo develop recommendations for the safe and effective use of LADD.Evidence reviewA systematic literature review of Cochrane Central Register of Controlled Trials, Embase, and MEDLINE was conducted in December 2019 to identify publications reporting research on LADD. A multidisciplinary panel was convened to draft recommendations informed by the systematic review; they were refined through 2 rounds of Delphi survey, 2 consensus meetings, and iterative review by all panelists until unanimous consensus was achieved.FindingsOf the 48 published studies of ablative fractional LADD that met inclusion criteria, 4 were cosmetic studies; 21, oncologic; and 23, medical (not cosmetic/oncologic), and 6 publications of nonablative fractional LADD were included at the request of the expert panel, producing a total of 54 studies. Thirty-four studies (63.0%) were deemed to have low risk of bias, 17 studies (31.5%) had moderate risk, and 3 (5.5%) had serious risk. The key findings that informed the guidelines developed by the expert panel were as follows: LADD is safe in adults and adolescents (≥12 years) with all Fitzpatrick skin types and in patients with immunosuppression; it is an effective treatment for actinic keratosis, cutaneous squamous cell carcinoma in situ, actinic cheilitis, hypertrophic scars, and keloids; it is useful for epidermal and dermal analgesia; drug delivery may be increased through the application of heat, pressure, or occlusion, or by using an aqueous drug solution; laser settings should be selected to ensure that channel diameter is greater than the delivered molecule; antibiotic prophylaxis is not recommended, except with impaired wound healing; antiviral prophylaxis is recommended when treating the face and genitalia; and antifungal prophylaxis is not recommended. The guideline's 15 recommendations address 5 areas of LADD use: (I) indications and contraindications; (II) parameters to report; (III) optimization of drug delivery; (IV) safety considerations; and (V) prophylaxis for bacterial, viral, and fungal infections.Conclusions and relevanceThis systematic review and Delphi consensus approach culminated in an evidence-based clinical practice guideline for safe and effective use of LADD in a variety of applications. Future research will further improve our understanding of this novel treatment technique.

Compared to batch operation, continuous bioprocessing can offer numerous advantages, including increased productivity, improved process control, reduced footprint, and increased flexibility. However, integration of traditional batch operations into a connected process can be challenging. In contrast to batch operations run at constant pressure or high flux, virus filtration in continuous processes may be operated at very low flux. This change in operating conditions may reduce the viral retention performance of the filter which has inhibited adoption of truly continuous virus filtration. To overcome this limitation, a novel approach is described that utilizes serial virus filtration, with a high area ratio between first to second stage filters, to achieve virus retention targets. In this study, virus filters were operated continuously (except for planned process interruptions) for 200 h in a serial configuration at a first to second stage filter area ratio of 13:1 and at a first stage flux of 5 L/m2/h. While the minute virus of mice (MVM) retention performance of the first stage filter was about 4 log reduction value (LRV), there was no virus detected in the second stage filtrate, translating to an MVM LRV across the filtration train of ≥6.7. The second stage filter was the dominant flow resistance at the start of the run but, as it was protected from foulants by the first stage filter, it suffered minimal fouling and the life of the filter train was controlled by the first stage. A theoretical case study projected that continuous virus filtration using serial configuration at high area ratio would have about 30% longer filter changeout time, 14% higher productivity, and virus retention nearly six LRV greater than single stage operation. The findings of this research are expected to provide valuable insights into optimizing virus filtration in continuous bioprocessing. [ABSTRACT FROM AUTHOR]

Purpose: The coordination of respiration with swallowing is critical for facilitation of airway protection and the efficiency of movements that propel ingested material through the upper aerodigestive tract. Confirmation of a predominant pattern in healthy adults provides a platform for comparison to aberrant patterns observed in the population with swallowing impairment (dysphagia). Method: A comprehensive search of published research in MEDLINE via PubMed 1946-2018, Embase 1947-2018, and Proquest Dissertations & Theses Global 1861-2018 was completed. Results: Thirty-seven articles meeting inclusion criteria were selected for data extraction, and the findings were reviewed. In addition, a meta-analysis of the data was completed. A significantly higher occurrence (p < 0.001) of expiration prior to and following the swallow was found when compared to 3 other patterns. The predominance of the pattern was influenced by increases in bolus volume when controlling for participant sample size. Conclusion: Determination of this predominant pattern provides a normative framework for evaluating respiratory-swallow coordination in adults across the age span and highlights the relevance for assessing and incorporating respiratory swallowing coordination during assessment and interventions.

Objective: To synthesize the methodologies of studies that evaluate the impacts of heat exposure on morbidity and mortality. Methods: Embase, MEDLINE, Web of Science, and Scopus were searched from date of inception until 1 March 2023 for English language literature on heat exposure and health outcomes. Records were collated, deduplicated and screened, and full texts were reviewed for inclusion and data abstraction. Eligibility for inclusion was determined as any article with climate‐related heat exposure and an associated morbidity/mortality outcome. Results: Of 13,136 records initially identified, 237 articles were selected for analysis. The scope of research represented 43 countries, with most studies conducted in China (62), the USA (44), and Australia (16). Across all studies, there were 141 unique climate data sources, no standard threshold for extreme heat, and 200 unique health outcome data sources. The distributed lag non‐linear model (DLNM) was the most common analytic method (48.1% of studies) and had high usage rates in China (68.9%) and the USA (31.8%); Australia frequently used conditional logistic regression (50%). Conditional logistic regression was most prevalent in case‐control studies (5 of 8 studies, 62.5%) and in case‐crossover studies (29 of 70, 41.4%). DLNMs were most common in time series studies (64 of 111, 57.7%) and ecological studies (13 of 20, 65.0%). Conclusions: This review underscores the heterogeneity of methods in heat impact studies across diverse settings and provides a resource for future researchers. Underrepresentation of certain countries, health outcomes, and limited data access were identified as potential barriers. Plain Language Summary: Climate change and global warming are major threats to public health, leading to increased illness and death worldwide due to rising temperatures. Heatwaves are becoming more frequent and severe, causing various health problems, particularly affecting low‐income and minority communities. Studying the link between heat and health requires diverse methods due to regional differences. Different study designs and analytical techniques have been used, but there is no consensus on the best approach. Factors like heat severity, duration, air quality, and humidity must be considered. However, defining extreme heat and determining the best metric for heat exposure remain debated. With climate change worsening, understanding previous research on heat‐related health impacts is crucial for future policies and adaptation strategies. This scoping review aims to address gaps in knowledge by examining the range of epidemiological approaches used to study the effects of extreme heat on health outcomes. Key Points: Distributed lag non‐linear models were widely used across various health outcomes and study designs, especially in time series studiesThere were disparities in research focus across different regions with regions like Africa and Oceania being underrepresentedAccess to public health data and standardized definitions for extreme heat remain significant challenges in heat impact studies [ABSTRACT FROM AUTHOR]

While prior meta-analyses in anatomy education have explored the effects of laboratory pedagogies and histology media on learner performance, the effects of student-centered learning (SCL) and computer-aided instruction (CAI) have not been broadly evaluated. This research sought to answer the question, "How effective are student-centered pedagogies and CAI at increasing student knowledge gains in anatomy compared to traditional didactic approaches?" Relevant studies published within the past 51 years were searched using five databases. Predetermined eligibility criteria were applied to the screening of titles and abstracts to discern their appropriateness for study inclusion. A summary effect size was estimated to determine the effects of SCL and CAI on anatomy performance outcomes. A moderator analysis of study features was also performed. Of the 3,035 records screened, 327 underwent full-text review. Seven studies, which comprised 1,564 participants, were included in the SCL analysis. An additional 19 studies analyzed the effects of CAI in the context of 2,570 participants. Upon comparing SCL to traditional instruction, a small positive effect on learner performance was detected (standardized mean difference (SMD = 0.24; [CI = 0.07, 0.42]; P = 0.006). Likewise, students with CAI exposure moderately outscored those with limited or no access to CAI (SMD = 0.59; [CI = 0.20, 0.98]; P = 0.003). Further analysis of CAI studies identified effects (P = 0.001) for learner population, publication period, interventional approach, and intervention frequency. Overall, learners exposed to SCL and supplemental CAI outperformed their more classically-trained peers as evidenced by increases in short-term knowledge gains.

Nutritional compromise, low levels of vitamin D, chronic inflammation, abnormal growth, and physical inactivity affect bone metabolism and compromise long‐term bone health in individuals with epidermolysis bullosa (EB). The result is a high risk for osteopenia, osteoporosis, and pathologic fractures, but this important consequence of EB has been the focus of few investigations. Our scoping review found 21 publications that assessed the current understanding and clinical practices for monitoring of osteoporosis and its treatment in EB. Recommendations summarized from 13 of these publications include early nutritional and weight assessments before 2 years of age; bloodwork every 6–12 months starting at birth; Tanner stage assessments every 6 months to detect any pubertal delay; DEXA scans starting at age 6 years with repeated scans every 1–2 years, except in mild cases; and vitamin D supplementation of 80–320 IU daily for children 0–7 years and 720 IU for patients >8 years. [ABSTRACT FROM AUTHOR]

In clinical practice, nurses are expected to understand and implement the science that supports patient care, yet they fall short of goals to implement evidence in practice. One reason is difficulty in interpreting research results. Interpretation requires an ability to read and speak a language that many nurses have never mastered-the language of data. This article presents a skill-based solution for use in nursing professional development to improve nurses' understanding of statistics as a language.