Data-driven identification of heart failure disease states and progression pathways using electronic health records.

Heart failure (HF) is a leading cause of morbidity, healthcare costs, and mortality. Guideline based segmentation of HF into distinct subtypes is coarse and unlikely to reflect the heterogeneity of etiologies and disease trajectories of patients. While analyses of electronic health records show promise in expanding our understanding of complex syndromes like HF in an evidence-driven way, limitations in data quality have presented challenges for large-scale EHR-based insight generation and decision-making. We present a hypothesis-free approach to generating real-world characteristics and progression patterns of HF. Patient disease state snapshots are extracted from the complaints mentioned in unstructured clinical notes. Typical disease states are generated by clustering and characterized in terms of their distinguishing features, temporal relationships, and risk of important clinical events. Our analysis generates a comprehensive "disease phenome" of real-world patients computed from large, noisy, secondary-use EHR datasets created in a routine clinical setting.

Development of a Method for Clinical Evaluation of Artificial Intelligence-Based Digital Wound Assessment Tools.

Importance: Accurate assessment of wound area and percentage of granulation tissue (PGT) are important for optimizing wound care and healing outcomes. Artificial intelligence (AI)-based wound assessment tools have the potential to improve the accuracy and consistency of wound area and PGT measurement, while improving efficiency of wound care workflows. Objective: To develop a quantitative and qualitative method to evaluate AI-based wound assessment tools compared with expert human assessments. Design, Setting, and Participants: This diagnostic study was performed across 2 independent wound centers using deidentified wound photographs collected for routine care (site 1, 110 photographs taken between May 1 and 31, 2018; site 2, 89 photographs taken between January 1 and December 31, 2019). Digital wound photographs of patients were selected chronologically from the electronic medical records from the general population of patients visiting the wound centers. For inclusion in the study, the complete wound edge and a ruler were required to be visible; circumferential ulcers were specifically excluded. Four wound specialists (2 per site) and an AI-based wound assessment service independently traced wound area and granulation tissue. Main Outcomes and Measures: The quantitative performance of AI tracings was evaluated by statistically comparing error measure distributions between test AI traces and reference human traces (AI vs human) with error distributions between independent traces by 2 humans (human vs human). Quantitative outcomes included statistically significant differences in error measures of false-negative area (FNA), false-positive area (FPA), and absolute relative error (ARE) between AI vs human and human vs human comparisons of wound area and granulation tissue tracings. Six masked attending physician reviewers (3 per site) viewed randomized area tracings for AI and human annotators and qualitatively assessed them. Qualitative outcomes included statistically significant difference in the absolute difference between AI-based PGT measurements and mean reviewer visual PGT estimates compared with PGT estimate variability measures (ie, range, standard deviation) across reviewers. Results: A total of 199 photographs were selected for the study across both sites; mean (SD) patient age was 64 (18) years (range, 17-95 years) and 127 (63.8%) were women. The comparisons of AI vs human with human vs human for FPA and ARE were not statistically significant. AI vs human FNA was slightly elevated compared with human vs human FNA (median [IQR], 7.7% [2.7%-21.2%] vs 5.7% [1.6%-14.9%]; P < .001), indicating that AI traces tended to slightly underestimate the human reference wound boundaries compared with human test traces. Two of 6 reviewers had a statistically higher frequency in agreement that human tracings met the standard area definition, but overall agreement was moderate (352 yes responses of 583 total responses [60.4%] for AI and 793 yes responses of 1166 total responses [68.0%] for human tracings). AI PGT measurements fell in the typical range of variation in interreviewer visual PGT estimates; however, visual PGT estimates varied considerably (mean range, 34.8%; mean SD, 19.6%). Conclusions and Relevance: This study provides a framework for evaluating AI-based digital wound assessment tools that can be extended to automated measurements of other wound features or adapted to evaluate other AI-based digital image diagnostic tools. As AI-based wound assessment tools become more common across wound care settings, it will be important to rigorously validate their performance in helping clinicians obtain accurate wound assessments to guide clinical care.

Multiscale classification of heart failure phenotypes by unsupervised clustering of unstructured electronic medical record data.

As a leading cause of death and morbidity, heart failure (HF) is responsible for a large portion of healthcare and disability costs worldwide. Current approaches to define specific HF subpopulations may fail to account for the diversity of etiologies, comorbidities, and factors driving disease progression, and therefore have limited value for clinical decision making and development of novel therapies. Here we present a novel and data-driven approach to understand and characterize the real-world manifestation of HF by clustering disease and symptom-related clinical concepts (complaints) captured from unstructured electronic health record clinical notes. We used natural language processing to construct vectorized representations of patient complaints followed by clustering to group HF patients by similarity of complaint vectors. We then identified complaints that were significantly enriched within each cluster using statistical testing. Breaking the HF population into groups of similar patients revealed a clinically interpretable hierarchy of subgroups characterized by similar HF manifestation. Importantly, our methodology revealed well-known etiologies, risk factors, and comorbid conditions of HF (including ischemic heart disease, aortic valve disease, atrial fibrillation, congenital heart disease, various cardiomyopathies, obesity, hypertension, diabetes, and chronic kidney disease) and yielded additional insights into the details of each HF subgroup's clinical manifestation of HF. Our approach is entirely hypothesis free and can therefore be readily applied for discovery of novel insights in alternative diseases or patient populations.

Hyperbaric oxygen therapy for COVID-19 patients with respiratory distress: treated cases versus propensity-matched controls.

Objective: Given the high mortality and prolonged duration of mechanical ventilation of COVID-19 patients, we evaluated the safety and efficacy of hyperbaric oxygen for COVID-19 patients with respiratory distress. Methods: This is a single-center clinical trial of COVID-19 patients at NYU Winthrop Hospital from March 31 to April 28, 2020. Patients in this trial received hyperbaric oxygen therapy at 2.0 atmospheres of pressure in monoplace hyperbaric chambers for 90 minutes daily for a maximum of five total treatments. Controls were identified using propensity score matching among COVID-19 patients admitted during the same time period. Using competing-risks survival regression, we analyzed our primary outcome of inpatient mortality and secondary outcome of mechanical ventilation. Results: We treated 20 COVID-19 patients with hyperbaric oxygen. Ages ranged from 30 to 79 years with an oxygen requirement ranging from 2 to 15 liters on hospital days 0 to 14. Of these 20 patients, two (10%) were intubated and died, and none remain hospitalized. Among 60 propensity-matched controls based on age, sex, body mass index, coronary artery disease, troponin, D-dimer, hospital day, and oxygen requirement, 18 (30%) were intubated, 13 (22%) have died, and three (5%) remain hospitalized (with one still requiring mechanical ventilation). Assuming no further deaths among controls, we estimate that the adjusted subdistribution hazard ratios were 0.37 for inpatient mortality (p=0.14) and 0.26 for mechanical ventilation (p=0.046). Conclusion: Though limited by its study design, our results demonstrate the safety of hyperbaric oxygen among COVID-19 patients and strongly suggests the need for a well-designed, multicenter randomized control trial.

Injectable Therapeutic Organoids Using Sacrificial Hydrogels.

Organoids are becoming widespread in drug-screening technologies but have been used sparingly for cell therapy as current approaches for producing self-organized cell clusters lack scalability or reproducibility in size and cellular organization. We introduce a method of using hydrogels as sacrificial scaffolds, which allow cells to form self-organized clusters followed by gentle release, resulting in highly reproducible multicellular structures on a large scale. We demonstrated this strategy for endothelial cells and mesenchymal stem cells to self-organize into blood-vessel units, which were injected into mice, and rapidly formed perfusing vasculature. Moreover, in a mouse model of peripheral artery disease, intramuscular injections of blood-vessel units resulted in rapid restoration of vascular perfusion within seven days. As cell therapy transforms into a new class of therapeutic modality, this simple method-by making use of the dynamic nature of hydrogels-could offer high yields of self-organized multicellular aggregates with reproducible sizes and cellular architectures.

Regenerative Wound Surgery: Practical Application of Regenerative Medicine in the OR.

Chronic nonhealing wounds cause significant morbidity and mortality and remain a challenging condition to treat. Regenerative wound surgery involves operative debridement of wounds to remove dead and healing-impaired tissue and bacterial contamination and, subsequently, the application of regenerative medicine treatments to accelerate healing. Regenerative treatments aim to restore native tissue structure and function by targeting biological mechanisms underlying impaired healing. A wide range of regenerative modalities are used for treating chronic and complex wounds, including decellularized scaffolds, living engineered donor tissues, autologous stem cells, and recombinant growth factors. Each of these modalities has specific and sometimes complex requirements for implementation. The advanced wound care team, including OR staff members, should be aware of how these products are used and regulated. This article highlights some of the common and emerging regenerative treatments that are applied in wound surgery and focuses on how the products are used practically in the OR.

A Framework to Assist Providers in the Management of Patients with Chronic, Nonhealing Wounds.

GENERAL PURPOSE: To describe the development of an evidence-based wound electronic medical record (WEMR) framework for providers to execute timely, protocol-based, best-practice care for patients with chronic, nonhealing wounds. TARGET AUDIENCE: This continuing education activity is intended for physicians, physician assistants, nurse practitioners, and nurses with an interest in skin and wound care. LEARNING OBJECTIVES/OUTCOMES: After completing this continuing education activity, you should be better able to: ABSTRACT: The care of patients with nonhealing wounds involves a host of treatment modalities. The authors developed a wound-specific framework to enhance provider management of these wounds and a summary sheet to involve patients and caregivers in their own healthcare to improve treatment adherence and outcomes. Implementing evidence-based practice for chronic wounds enables corrective actions to optimize care.

A Wolf in Sheep's Clothing: An Unusual Presentation of Diabetic Myonecrosis.

GENERAL PURPOSE: To provide information about the diagnosis and treatment of diabetic myonecrosis (DMN).This continuing education activity is intended for physicians, physician assistants, nurse practitioners, and nurses with an interest in skin and wound care.After participating in this educational activity, the participant should be better able to:1. Cite the incidence and symptomatology of diabetic myonecrosis.2. Identify the diagnostic tests associated with DMN.3. Summarize the evidence-based treatments for DMN.Diabetic myonecrosis is a rare complication of poorly controlled diabetes mellitus that presents similarly to many common conditions such as cellulitis, abscess, and fasciitis. Therefore, a high index of suspicion is required for diagnosis. Magnetic resonance imaging is the investigative test of choice. Treatment includes antiplatelet therapy, nonsteroidal anti-inflammatory agents, and glycemic control.

An unusual presentation of Merkel cell carcinoma: a case report.

Merkel cell carcinoma (MCC) is a rare, aggressive carcinoma that usually arises in sun-exposed regions. MCC is a primary neuroendocrine tumor that arises in the skin. This report describes an unusual case of MCC on the buttocks that was treated with excision, radiation and chemotherapy. Physicians should consider MCC as a differential diagnosis when encountering a rapidly growing, painless lesion. Early diagnosis and treatment may improve patient survival rates.

A direct tissue-grafting approach to increasing endogenous brown fat.

There is widespread evidence that increasing functional mass of brown adipose tissue (BAT) via browning of white adipose tissue (WAT) could potentially counter obesity and diabetes. However, most current approaches focus on administration of pharmacological compounds which expose patients to highly undesirable side effects. Here, we describe a simple and direct tissue-grafting approach to increase BAT mass through ex vivo browning of subcutaneous WAT, followed by re-implantation into the host; this cell-therapy approach could potentially act synergistically with existing pharmacological approaches. With this process, entitled "exBAT", we identified conditions, in both mouse and human tissue, that convert whole fragments of WAT to BAT via a single step and without unwanted off-target pharmacological effects. We show that ex vivo, exBAT exhibited UCP1 immunostaining, lipid droplet formation, and mitochondrial metabolic activity consistent with native BAT. In mice, exBAT exhibited a highly durable phenotype for at least 8 weeks. Overall, these results enable a simple and scalable tissue-grafting strategy, rather than pharmacological approaches, for increasing endogenous BAT and studying its effect on host weight and metabolism.

Wound Care Center of Excellence: A Process for Continuous Monitoring and Improvement of Wound Care Quality.

GENERAL PURPOSE: To provide information about a study using a new process for continuous monitoring to improve chronic wound care quality.This continuing education activity is intended for physicians, physician assistants, nurse practitioners, and nurses with an interest in skin and wound care.After completing this continuing education activity, you should be better able to:1. Recognize problems associated with chronic wound care.2. Identify methods used in this project to improve care.3. Illustrate the findings from this and similar projects and implications for providing improved wound care.Patients with chronic wounds require complex care because of comorbidities that can affect healing. Therefore, the goal of this project was to develop a system of reviewing all hospitalized patients seen by the study authors' wound care service on a weekly basis to decrease readmissions, morbidity, and mortality. Weekly multidisciplinary conferences were conducted to evaluate patient data and systematically assess for adherence to wound care protocols, as well as to create and modify patient care plans. This review of pathology and the performance of root-cause analyses often led to improved patient care.

Practical Application of Granulocyte-Macrophage Colony-Stimulating Factor (GM-CSF) in Patients with Wounds.

Rapidly evolving advances in wound-care technologies and treatment modalities, including locally injectable granulocyte-macrophage colony-stimulating factor (GM-CSF), are increasingly being used. Based on its role in the stimulation and recruitment of key contributors to wound healing, such as keratinocytes, macrophages, and fibroblasts, GM-CSF is considered to play an essential role in the wound-healing cascade. Synthetic GM-CSF has been shown to have a positive effect on the healing of chronic wounds when given as a local injection in a small number of patients. Subsequent randomized, controlled trials demonstrated that GM-CSF accelerated the healing of chronic wounds. This paper reviews the proposed mechanism of action of GM-CSF in wound healing. We also describe its method of application in the operating room at a tertiary care center for patients with wounds. Key Messages: Many types of chronic wounds have an altered keratinocyte and macrophage function that can be potentially assuaged by the addition of locally injected growth factor therapy to standard-of-care treatment. Granulocyte-macrophage colony-stimulating factor (GM-CSF) has been shown to be beneficial for the treatment of chronic, non-healing wounds. This article reviews the data on GM-CSF, reports a proposed mechanism of action, and describes its use by a team of wound surgeons.

A Perioperative Approach to Increase Limb Salvage When Treating Foot Ulcers in Patients With Diabetes.

Foot ulceration in patients with diabetes increases the risk of lower extremity amputation. Major amputations produce substantial adverse consequences, increase length of hospital stay, diminish quality of life, and increase mortality. In this article, we describe approaches that decrease amputations and improve the quality of life for patients with diabetes and foot ulcers. We highlight the role of the perioperative nurse, who is essential to providing optimal patient care in the perioperative period. Perioperative care of patients with diabetes involves providing optimal surveillance for a break in the skin of the foot, screening for neuropathy, following guidelines for foot ulcer infections, preparing for pathophysiology-based debridement, using adjuvant therapies, and offloading the patient's affected foot. Nurses should understand the disease process and pathophysiology and how to use these approaches in the perioperative setting to assist in curtailing the morbidity and mortality associated with foot ulcers in patients with diabetes.

The Future of Data-Driven Wound Care.

Care for patients with chronic wounds can be complex, and the chances of poor outcomes are high if wound care is not optimized through evidence-based protocols. Tracking and managing every variable and comorbidity in patients with wounds is difficult despite the increasing use of wound-specific electronic medical records. Harnessing the power of big data analytics to help nurses and physicians provide optimized care based on the care provided to millions of patients can result in better outcomes. Numerous applications of machine learning toward workflow improvements, inpatient monitoring, outpatient communication, and hospital operations can improve overall efficiency and efficacy of care delivery in and out of the hospital, while reducing adverse events and complications. This article provides an overview of the application of big data analytics and machine learning in health care, highlights important recent advances, and discusses how these technologies may revolutionize advanced wound care.

Human Skin Constructs with Spatially Controlled Vasculature Using Primary and iPSC-Derived Endothelial Cells.

Vascularization of engineered human skin constructs is crucial for recapitulation of systemic drug delivery and for their long-term survival, functionality, and viable engraftment. In this study, the latest microfabrication techniques are used and a novel bioengineering approach is established to micropattern spatially controlled and perfusable vascular networks in 3D human skin equivalents using both primary and induced pluripotent stem cell (iPSC)-derived endothelial cells. Using 3D printing technology makes it possible to control the geometry of the micropatterned vascular networks. It is verified that vascularized human skin equivalents (vHSEs) can form a robust epidermis and establish an endothelial barrier function, which allows for the recapitulation of both topical and systemic delivery of drugs. In addition, the therapeutic potential of vHSEs for cutaneous wounds on immunodeficient mice is examined and it is demonstrated that vHSEs can both promote and guide neovascularization during wound healing. Overall, this innovative bioengineering approach can enable in vitro evaluation of topical and systemic drug delivery as well as improve the potential of engineered skin constructs to be used as a potential therapeutic option for the treatment of cutaneous wounds.

Challenges and promises in modeling dermatologic disorders with bioengineered skin.

The tremendous cost of drug development is often attributed to the long time interval between identifying lead compounds in preclinical studies to assessing clinical efficacy in randomized clinical trials. Many candidate molecules show promise in cell culture or animal models, only to fail in late stage in human investigations. There is a need for novel technologies that allow investigators to quickly and reliably predict drug safety and efficacy. The advent of microtechnology has made it possible to integrate multiple microphysiologic organ systems into a single microfabricated chip. This review focuses on three-dimensional engineered skin, which has enjoyed a long history of uses both in clinical treatments of refractory ulcers and as a laboratory model. We discuss current biological and engineering challenges in construction of a robust bioengineered skin and provide a blueprint for its potential utility to model dermatologic disorders such as psoriasis or cutaneous drug reactions.

Building a microphysiological skin model from induced pluripotent stem cells.

The discovery of induced pluripotent stem cells (iPSCs) in 2006 was a major breakthrough for regenerative medicine. The establishment of patient-specific iPSCs has created the opportunity to model diseases in culture systems, with the potential to rapidly advance the drug discovery field. Current methods of drug discovery are inefficient, with a high proportion of drug candidates failing during clinical trials due to low efficacy and/or high toxicity. Many drugs fail toxicity testing during clinical trials, since the cells on which they have been tested do not adequately model three-dimensional tissues or their interaction with other organs in the body. There is a need to develop microphysiological systems that reliably represent both an intact tissue and also the interaction of a particular tissue with other systems throughout the body. As the port of entry for many drugs is via topical delivery, the skin is the first line of exposure, and also one of the first organs to demonstrate a reaction after systemic drug delivery. In this review, we discuss our strategy to develop a microphysiological system using iPSCs that recapitulates human skin for analyzing the interactions of drugs with the skin.

Engineering extracellular matrix structure in 3D multiphase tissues.

In native tissues, microscale variations in the extracellular matrix (ECM) structure can drive different cellular behaviors. Although control over ECM structure could prove useful in tissue engineering and in studies of cellular behavior, isotropic 3D matrices poorly replicate variations in local microenvironments. In this paper, we demonstrate a method to engineer local variations in the density and size of collagen fibers throughout 3D tissues. The results showed that, in engineered multiphase tissues, the structures of collagen fibers in both the bulk ECM phases (as measured by mesh size and width of fibers) as well as at tissue interfaces (as measured by density of fibers and thickness of tissue interfaces) could be modulated by varying the collagen concentrations and gelling temperatures. As the method makes use of a previously published technique for tissue bonding, we also confirmed that significant adhesion strength at tissue interfaces was achieved under all conditions tested. Hence, this study demonstrates how collagen fiber structures can be engineered within all regions of a multiphase tissue scaffold by exploiting knowledge of collagen assembly, and presents an approach to engineer local collagen structure that complements methods such as flow alignment and electrospinning.