Machine learning and artificial intelligence (AI)-driven technologies are contributing significantly to various facets of medicine and care management. It is likely that the next generation of ...healthcare professionals will be confronted with a series of innovations that are powered by AI, and they may not have sufficient time during their professional tenure to learn about the underlying machine learning frameworks that are driving these systems. Educating the aspiring clinicians and care providers with the right foundational courses in machine learning as part of postsecondary education will likely transform them as high-tech physicians and care providers of the future.
•Artificial intelligence driven by machine learning algorithms is making impressive strides in medicine and healthcare.•Educating the healthcare providers on this exciting topic is critical but they may have less room for additional training.•Development of a machine learning curriculum during postsecondary education is an option for training the next generation.
Stent thrombosis is a lethal complication of endovascular intervention. Concern has been raised about the inherent risk associated with specific stent designs and drug-eluting coatings, yet clinical ...and animal support is equivocal.
We examined whether drug-eluting coatings are inherently thrombogenic and if the response to these materials was determined to a greater degree by stent design and deployment with custom-built stents. Drug/polymer coatings uniformly reduce rather than increase thrombogenicity relative to matched bare metal counterparts (0.65-fold; P=0.011). Thick-strutted (162 μm) stents were 1.5-fold more thrombogenic than otherwise identical thin-strutted (81 μm) devices in ex vivo flow loops (P<0.001), commensurate with 1.6-fold greater thrombus coverage 3 days after implantation in porcine coronary arteries (P=0.004). When bare metal stents were deployed in malapposed or overlapping configurations, thrombogenicity increased compared with apposed, length-matched controls (1.58-fold, P=0.001; and 2.32-fold, P<0.001). The thrombogenicity of polymer-coated stents with thin struts was lowest in all configurations and remained insensitive to incomplete deployment. Computational modeling-based predictions of stent-induced flow derangements correlated with spatial distribution of formed clots.
Contrary to popular perception, drug/polymer coatings do not inherently increase acute stent clotting; they reduce thrombosis. However, strut dimensions and positioning relative to the vessel wall are critical factors in modulating stent thrombogenicity. Optimal stent geometries and surfaces, as demonstrated with thin stent struts, help reduce the potential for thrombosis despite complex stent configurations and variability in deployment.
Deep learning is a powerful tool for whole slide image (WSI) analysis. Typically, when performing supervised deep learning, a WSI is divided into small patches, trained and the outcomes are ...aggregated to estimate disease grade. However, patch-based methods introduce label noise during training by assuming that each patch is independent with the same label as the WSI and neglect overall WSI-level information that is significant in disease grading. Here we present a Graph-Transformer (GT) that fuses a graph-based representation of an WSI and a vision transformer for processing pathology images, called GTP, to predict disease grade. We selected 4,818 WSIs from the Clinical Proteomic Tumor Analysis Consortium (CPTAC), the National Lung Screening Trial (NLST), and The Cancer Genome Atlas (TCGA), and used GTP to distinguish adenocarcinoma (LUAD) and squamous cell carcinoma (LSCC) from adjacent non-cancerous tissue (normal). First, using NLST data, we developed a contrastive learning framework to generate a feature extractor. This allowed us to compute feature vectors of individual WSI patches, which were used to represent the nodes of the graph followed by construction of the GTP framework. Our model trained on the CPTAC data achieved consistently high performance on three-label classification (normal versus LUAD versus LSCC: mean accuracy = 91.2 ± 2.5%) based on five-fold cross-validation, and mean accuracy = 82.3 ± 1.0% on external test data (TCGA). We also introduced a graph-based saliency mapping technique, called GraphCAM, that can identify regions that are highly associated with the class label. Our findings demonstrate GTP as an interpretable and effective deep learning framework for WSI-level classification.
Artificial intelligence (AI) driven by machine learning (ML) algorithms is a branch in computer science that is rapidly gaining popularity within the healthcare sector. Recent regulatory approvals of ...AI-driven companion diagnostics and other products are glimmers of a future in which these tools could play a key role by defining the way medicine will be practiced. Educating the next generation of medical professionals with the right ML techniques will enable them to become part of this emerging data science revolution.
Identification of reliable, affordable, and easy-to-use strategies for detection of dementia is sorely needed. Digital technologies, such as individual voice recordings, offer an attractive modality ...to assess cognition but methods that could automatically analyze such data are not readily available.
We used 1264 voice recordings of neuropsychological examinations administered to participants from the Framingham Heart Study (FHS), a community-based longitudinal observational study. The recordings were 73 min in duration, on average, and contained at least two speakers (participant and examiner). Of the total voice recordings, 483 were of participants with normal cognition (NC), 451 recordings were of participants with mild cognitive impairment (MCI), and 330 were of participants with dementia (DE). We developed two deep learning models (a two-level long short-term memory (LSTM) network and a convolutional neural network (CNN)), which used the audio recordings to classify if the recording included a participant with only NC or only DE and to differentiate between recordings corresponding to those that had DE from those who did not have DE (i.e., NDE (NC+MCI)). Based on 5-fold cross-validation, the LSTM model achieved a mean (±std) area under the receiver operating characteristic curve (AUC) of 0.740 ± 0.017, mean balanced accuracy of 0.647 ± 0.027, and mean weighted F1 score of 0.596 ± 0.047 in classifying cases with DE from those with NC. The CNN model achieved a mean AUC of 0.805 ± 0.027, mean balanced accuracy of 0.743 ± 0.015, and mean weighted F1 score of 0.742 ± 0.033 in classifying cases with DE from those with NC. For the task related to the classification of participants with DE from NDE, the LSTM model achieved a mean AUC of 0.734 ± 0.014, mean balanced accuracy of 0.675 ± 0.013, and mean weighted F1 score of 0.671 ± 0.015. The CNN model achieved a mean AUC of 0.746 ± 0.021, mean balanced accuracy of 0.652 ± 0.020, and mean weighted F1 score of 0.635 ± 0.031 in classifying cases with DE from those who were NDE.
This proof-of-concept study demonstrates that automated deep learning-driven processing of audio recordings of neuropsychological testing performed on individuals recruited within a community cohort setting can facilitate dementia screening.
Alzheimer's disease is the primary cause of dementia worldwide, with an increasing morbidity burden that may outstrip diagnosis and management capacity as the population ages. Current methods ...integrate patient history, neuropsychological testing and MRI to identify likely cases, yet effective practices remain variably applied and lacking in sensitivity and specificity. Here we report an interpretable deep learning strategy that delineates unique Alzheimer's disease signatures from multimodal inputs of MRI, age, gender, and Mini-Mental State Examination score. Our framework linked a fully convolutional network, which constructs high resolution maps of disease probability from local brain structure to a multilayer perceptron and generates precise, intuitive visualization of individual Alzheimer's disease risk en route to accurate diagnosis. The model was trained using clinically diagnosed Alzheimer's disease and cognitively normal subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset (n = 417) and validated on three independent cohorts: the Australian Imaging, Biomarker and Lifestyle Flagship Study of Ageing (AIBL) (n = 382), the Framingham Heart Study (n = 102), and the National Alzheimer's Coordinating Center (NACC) (n = 582). Performance of the model that used the multimodal inputs was consistent across datasets, with mean area under curve values of 0.996, 0.974, 0.876 and 0.954 for the ADNI study, AIBL, Framingham Heart Study and NACC datasets, respectively. Moreover, our approach exceeded the diagnostic performance of a multi-institutional team of practicing neurologists (n = 11), and high-risk cerebral regions predicted by the model closely tracked post-mortem histopathological findings. This framework provides a clinically adaptable strategy for using routinely available imaging techniques such as MRI to generate nuanced neuroimaging signatures for Alzheimer's disease diagnosis, as well as a generalizable approach for linking deep learning to pathophysiological processes in human disease.
Abstract
Background
Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has spread worldwide and has the ability to damage multiple organs. However, information on serum SARS-CoV-2 nucleic ...acid (RNAemia) in patients affected by coronavirus disease 2019 (COVID-19) is limited.
Methods
Patients who were admitted to Zhongnan Hospital of Wuhan University with laboratory-confirmed COVID-19 were tested for SARS-COV-2 RNA in serum from 28 January 2020 to 9 February 2020. Demographic data, laboratory and radiological findings, comorbidities, and outcomes data were collected and analyzed.
Results
Eighty-five patients were included in the analysis. The viral load of throat swabs was significantly higher than of serum samples. The highest detection of SARS-CoV-2 RNA in serum samples was between 11 and 15 days after symptom onset. Analysis to compare patients with and without RNAemia provided evidence that computed tomography and some laboratory biomarkers (total protein, blood urea nitrogen, lactate dehydrogenase, hypersensitive troponin I, and D-dimer) were abnormal and that the extent of these abnormalities was generally higher in patients with RNAemia than in patients without RNAemia. Organ damage (respiratory failure, cardiac damage, renal damage, and coagulopathy) was more common in patients with RNAemia than in patients without RNAemia. Patients with vs without RNAemia had shorter durations from serum testing SARS-CoV-2 RNA. The mortality rate was higher among patients with vs without RNAemia.
Conclusions
In this study, we provide evidence to support that SARS-CoV-2 may have an important role in multiple organ damage. Our evidence suggests that RNAemia has a significant association with higher risk of in-hospital mortality.
Size and contact angle of liquid drops are fundamental parameters in interfacial science. Accurate estimation of these parameters can provide objective information regarding several properties of the ...contacting surface. We leveraged principles of texture analysis to estimate the contact angle and the drop diameter from videos of evaporating sessile liquid drops deposited on solid surfaces. Specifically, we used a Harris corner detector to locate the corners and dynamically estimate the changing size and a Gabor wavelet-based approach to estimate the varying contact angle of the evaporating sessile drop. We demonstrated the ability of our approach to accurately estimate size and contact angles of drops deposited on a hydrophilic glass slide and on a paraffin film representing a hydrophobic surface. We also estimated the contact angle and size of drops deposited on horizontal and tilted surfaces to generate symmetric and asymmetric drop shapes, respectively. A software application that has the ability to analyze videos of sessile liquid drops as inputs is provided, and this tool can generate plots of the estimated contact angle and the drop diameter as a function of frame number.
Epithelial wound healing requires the coordination of cells to migrate as a unit over the basement membrane after injury. To understand the process of this coordinated movement, it is critical to ...study the dynamics of cell-cell communication. We developed a method to characterize the injury-induced sustained Ca2+ mobilizations that travel between cells for periods of time up to several hours. These events of communication are concentrated along the wound edge and are reduced in cells further away from the wound. Our goal was to delineate the role and contribution of these sustained mobilizations and using MATLAB analyses, we determined the probability of cell-cell communication events in both in vitro models and ex vivo organ culture models. We demonstrated that the injury response was complex and represented the activation of a number of receptors. In addition, we found that pannexin channels mediated the cell-cell communication and motility. Furthermore, the sustained Ca2+ mobilizations are associated with changes in cell morphology and motility during wound healing. The results demonstrate that both purinoreceptors and pannexins regulate the sustained Ca2+ mobilization necessary for cell-cell communication in wound healing.
Interstitial fibrosis and tubular atrophy (IFTA) on a renal biopsy are strong indicators of disease chronicity and prognosis. Techniques that are typically used for IFTA grading remain manual, ...leading to variability among pathologists. Accurate IFTA estimation using computational techniques can reduce this variability and provide quantitative assessment. Using trichrome-stained whole-slide images (WSIs) processed from human renal biopsies, we developed a deep-learning framework that captured finer pathologic structures at high resolution and overall context at the WSI level to predict IFTA grade. WSIs (n = 67) were obtained from The Ohio State University Wexner Medical Center. Five nephropathologists independently reviewed them and provided fibrosis scores that were converted to IFTA grades: ≤10% (none or minimal), 11% to 25% (mild), 26% to 50% (moderate), and >50% (severe). The model was developed by associating the WSIs with the IFTA grade determined by majority voting (reference estimate). Model performance was evaluated on WSIs (n = 28) obtained from the Kidney Precision Medicine Project. There was good agreement on the IFTA grading between the pathologists and the reference estimate (κ = 0.622 ± 0.071). The accuracy of the deep-learning model was 71.8% ± 5.3% on The Ohio State University Wexner Medical Center and 65.0% ± 4.2% on Kidney Precision Medicine Project data sets. Our approach to analyzing microscopic- and WSI-level changes in renal biopsies attempts to mimic the pathologist and provides a regional and contextual estimation of IFTA. Such methods can assist clinicopathologic diagnosis.