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.

Tumor Suppressor DAPK1 Catalyzes Adhesion Assembly on Rigid but Anoikis on Soft Matrices.

Cancer cells normally grow on soft surfaces due to impaired mechanosensing of the extracellular matrix rigidity. Upon restoration of proper mechanosensing, cancer cells undergo apoptosis on soft surfaces (anoikis) like most normal cells. However, the link between mechanosensing and activation of anoikis is not clear. Here we show that death associated protein kinase 1 (DAPK1), a tumor suppressor that activates cell death, is directly linked to anoikis activation through rigidity sensing. We find that when rigidity sensing is decreased through inhibition of DAPK1 activity, cells are transformed for growth on soft matrices. Further, DAPK1 catalyzes matrix adhesion assembly and is part of adhesions on rigid surfaces. This pathway involves DAPK1 phosphorylation of tropomyosin1.1, the talin1 head domain, and tyrosine phosphorylation of DAPK1 by Src. On soft surfaces, DAPK1 rapidly dissociates from the adhesion complexes and activates apoptosis as catalyzed by PTPN12 activity and talin1 head. Thus, DAPK1 is important for adhesion assembly on rigid surfaces and the activation of anoikis on soft surfaces through its binding to rigidity-sensing modules.

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.

Large and reversible myosin-dependent forces in rigidity sensing.

Cells sense the rigidity of their environment through localized pinching, which occurs when myosin molecular motors generate contractions within actin filaments anchoring the cell to its surroundings. We present high-resolution experiments performed on these elementary contractile units in cells. Our experimental results challenge the current understanding of molecular motor force generation. Surprisingly, bipolar myosin filaments generate much larger forces per motor than measured in single molecule experiments. Further, contraction to a fixed distance, followed by relaxation at the same rate, is observed over a wide range of matrix rigidities. Lastly, step-wise displacements of the matrix contacts are apparent during both contraction and relaxation. Building upon a generic two-state model of molecular motor collections, we interpret these unexpected observations as spontaneously emerging features of a collective motor behavior. Our approach explains why, in the cellular context, collections of resilient and slow motors contract in a stepwise fashion while collections of weak and fast motors do not. We thus rationalize the specificity of motor contractions implied in rigidity sensing compared to previous in vitro observations.

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.

Force-Induced Calpain Cleavage of Talin Is Critical for Growth, Adhesion Development, and Rigidity Sensing.

Cell growth depends upon formation of cell-matrix adhesions, but mechanisms detailing the transmission of signals from adhesions to control proliferation are still lacking. Here, we find that the scaffold protein talin undergoes force-induced cleavage in early adhesions to produce the talin rod fragment that is needed for cell cycle progression. Expression of noncleavable talin blocks cell growth, adhesion maturation, proper mechanosensing, and the related property of EGF activation of motility. Further, the expression of talin rod in the presence of noncleavable full-length talin rescues cell growth and other functions. The cleavage of talin is found in early adhesions where there is also rapid turnover of talin that depends upon calpain and TRPM4 activity as well as the generation of force on talin. Thus, we suggest that an important function of talin is its control over cell cycle progression through its cleavage in early adhesions.

EGFR and HER2 activate rigidity sensing only on rigid matrices.

Epidermal growth factor receptor (EGFR) interacts with integrins during cell spreading and motility, but little is known about the role of EGFR in these mechanosensing processes. Here we show, using two different cell lines, that in serum- and EGF-free conditions, EGFR or HER2 activity increase spreading and rigidity-sensing contractions on rigid, but not soft, substrates. Contractions peak after 15-20 min, but diminish by tenfold after 4 h. Addition of EGF at that point increases spreading and contractions, but this can be blocked by myosin-II inhibition. We further show that EGFR and HER2 are activated through phosphorylation by Src family kinases (SFK). On soft surfaces, neither EGFR inhibition nor EGF stimulation have any effect on cell motility. Thus, EGFR or HER2 can catalyse rigidity sensing after associating with nascent adhesions under rigidity-dependent tension downstream of SFK activity. This has broad implications for the roles of EGFR and HER2 in the absence of EGF both for normal and cancerous growth.

Cellular response to substrate rigidity is governed by either stress or strain.

Cells sense the rigidity of their substrate; however, little is known about the physical variables that determine their response to this rigidity. Here, we report traction stress measurements carried out using fibroblasts on polyacrylamide gels with Young's moduli ranging from 6 to 110 kPa. We prepared the substrates by employing a modified method that involves N-acryloyl-6-aminocaproic acid (ACA). ACA allows for covalent binding between proteins and elastomers and thus introduces a more stable immobilization of collagen onto the substrate when compared to the conventional method of using sulfo-succinimidyl-6-(4-azido-2-nitrophenyl-amino) hexanoate (sulfo-SANPAH). Cells remove extracellular matrix proteins off the surface of gels coated using sulfo-SANPAH, which corresponds to lower values of traction stress and substrate deformation compared to gels coated using ACA. On soft ACA gels (Young's modulus <20 kPa), cell-exerted substrate deformation remains constant, independent of the substrate Young's modulus. In contrast, on stiff substrates (Young's modulus >20 kPa), traction stress plateaus at a limiting value and the substrate deformation decreases with increasing substrate rigidity. Sustained substrate strain on soft substrates and sustained traction stress on stiff substrates suggest these may be factors governing cellular responses to substrate rigidity.