• Artificial intelligence in molecular imaging

      Herskovits, Edward H (AME Publishing Company, 2021-05)
      AI has, to varying degrees, affected all aspects of molecular imaging, from image acquisition to diagnosis. During the last decade, the advent of deep learning in particular has transformed medical image analysis. Although the majority of recent advances have resulted from neural-network models applied to image segmentation, a broad range of techniques has shown promise for image reconstruction, image synthesis, differential-diagnosis generation, and treatment guidance. Applications of AI for drug design indicate the way forward for using AI to facilitate molecular-probe design, which is still in its early stages. Deep-learning models have demonstrated increased efficiency and image quality for PET reconstruction from sinogram data. Generative adversarial networks (GANs), which are paired neural networks that are jointly trained to generate and classify images, have found applications in modality transformation, artifact reduction, and synthetic-PET-image generation. Some AI applications, based either partly or completely on neural-network approaches, have demonstrated superior differential-diagnosis generation relative to radiologists. However, AI models have a history of brittleness, and physicians and patients may not trust AI applications that cannot explain their reasoning. To date, the majority of molecular-imaging applications of AI have been confined to research projects, and are only beginning to find their ways into routine clinical workflows via commercialization and, in some cases, integration into scanner hardware. Evaluation of actual clinical products will yield more realistic assessments of AI's utility in molecular imaging.
    • Artificial Intelligence May Predict Early Sepsis After Liver Transplantation

      Kamaleswaran, Rishikesan; Sataphaty, Sanjaya K; Mas, Valeria R; Eason, James D; Maluf, Daniel G (Frontiers Media S.A., 2021-09-06)
      Background: Sepsis, post-liver transplantation, is a frequent challenge that impacts patient outcomes. We aimed to develop an artificial intelligence method to predict the onset of post-operative sepsis earlier. Methods: This pilot study aimed to identify "physiomarkers" in continuous minute-by-minute physiologic data streams, such as heart rate, respiratory rate, oxygen saturation (SpO2), and blood pressure, to predict the onset of sepsis. The model was derived from a cohort of 5,748 transplant and non-transplant patients across intensive care units (ICUs) over 36 months, with 92 post-liver transplant patients who developed sepsis. Results: Using an alert timestamp generated with the Third International Consensus Definition of Sepsis (Sepsis-3) definition as a reference point, we studied up to 24 h of continuous physiologic data prior to the event, totaling to 8.35 million data points. One hundred fifty-five features were generated using signal processing and statistical methods. Feature selection identified 52 highly ranked features, many of which included blood pressures. An eXtreme Gradient Boost (XGB) classifier was then trained on the ranked features by 5-fold cross validation on all patients (n = 5,748). We identified that the average sensitivity, specificity, positive predictive value (PPV), and area under the receiver-operator curve (AUC) of the model after 100 iterations was 0.94 ± 0.02, 0.9 ± 0.02, 0.89 ± 0.01, respectively, and 0.97 ± 0.01 for predicting sepsis 12 h before meeting criteria. Conclusion: The data suggest that machine learning/deep learning can be applied to continuous streaming data in the transplant ICU to monitor patients and possibly predict sepsis.
    • Big Data Approaches to Phenotyping Acute Ischemic Stroke Using Automated Lesion Segmentation of Multi-Center Magnetic Resonance Imaging Data

      Wu, O.; Winzeck, S.; Giese, A.-K. (American Heart Association, 2019)
      Background and Purpose- We evaluated deep learning algorithms' segmentation of acute ischemic lesions on heterogeneous multi-center clinical diffusion-weighted magnetic resonance imaging (MRI) data sets and explored the potential role of this tool for phenotyping acute ischemic stroke. Methods- Ischemic stroke data sets from the MRI-GENIE (MRI-Genetics Interface Exploration) repository consisting of 12 international genetic research centers were retrospectively analyzed using an automated deep learning segmentation algorithm consisting of an ensemble of 3-dimensional convolutional neural networks. Three ensembles were trained using data from the following: (1) 267 patients from an independent single-center cohort, (2) 267 patients from MRI-GENIE, and (3) mixture of (1) and (2). The algorithms' performances were compared against manual outlines from a separate 383 patient subset from MRI-GENIE. Univariable and multivariable logistic regression with respect to demographics, stroke subtypes, and vascular risk factors were performed to identify phenotypes associated with large acute diffusion-weighted MRI volumes and greater stroke severity in 2770 MRI-GENIE patients. Stroke topography was investigated. Results- The ensemble consisting of a mixture of MRI-GENIE and single-center convolutional neural networks performed best. Subset analysis comparing automated and manual lesion volumes in 383 patients found excellent correlation (ρ=0.92; P<0.0001). Median (interquartile range) diffusion-weighted MRI lesion volumes from 2770 patients were 3.7 cm3 (0.9-16.6 cm3). Patients with small artery occlusion stroke subtype had smaller lesion volumes ( P<0.0001) and different topography compared with other stroke subtypes. Conclusions- Automated accurate clinical diffusion-weighted MRI lesion segmentation using deep learning algorithms trained with multi-center and diverse data is feasible. Both lesion volume and topography can provide insight into stroke subtypes with sufficient sample size from big heterogeneous multi-center clinical imaging phenotype data sets.
    • Data Mining of Molecular Simulations Suggest Key Amino Acid Residues for Aggregation, Signaling and Drug Action

      Gurunathan, Vaibhav; Hamre, John; Klimov, Dmitri K; Jafri, Mohsin Saleet (MDPI AG, 2021-10-19)
      Alzheimer’s disease, the most common form of dementia, currently has no cure. There are only temporary treatments that reduce symptoms and the progression of the disease. Alzheimer’s disease is characterized by the prevalence of plaques of aggregated amyloid β (Aβ) peptide. Recent treatments to prevent plaque formation have provided little to relieve disease symptoms. Although there have been numerous molecular simulation studies on the mechanisms of Aβ aggregation, the signaling role has been less studied. In this study, a total of over 38,000 simulated structures, generated from molecular dynamics (MD) simulations, exploring different conformations of the Aβ42 mutants and wild-type peptides were used to examine the relationship between Aβ torsion angles and disease measures. Unique methods characterized the data set and pinpointed residues that were associated in aggregation and others associated with signaling. Machine learning techniques were applied to characterize the molecular simulation data and classify how much each residue influenced the predicted variant of Alzheimer’s Disease. Orange3 data mining software provided the ability to use these techniques to generate tables and rank the data. The test and score module coupled with the confusion matrix module analyzed data with calculations of specificity and sensi-tivity. These methods evaluating frequency and rank allowed us to analyze and predict important residues associated with different phenotypic measures. This research has the potential to help un-derstand which specific residues of Aβ should be targeted for drug development. © 2021 by the authors.
    • Evaluation of Texture Analysis for the Differential Diagnosis of Mass-Forming Pancreatitis From Pancreatic Ductal Adenocarcinoma on Contrast-Enhanced CT Images

      Ren, S.; Zhang, J.; Chen, R. (Frontiers Media S.A., 2019)
      Purpose: To investigate the potential of computed tomography (CT) imaging features and texture analysis to differentiate between mass-forming pancreatitis (MFP) and pancreatic ductal adenocarcinoma (PDAC). Materials and Methods: Thirty patients with pathologically proved MFP and 79 patients with PDAC were included in this study. Clinical data and CT imaging features of the two lesions were evaluated. Texture features were extracted from arterial and portal phase CT images using commercially available software (AnalysisKit). Multivariate logistic regression analyses were used to identify relevant CT imaging and texture parameters to discriminate MFP from PDAC. Receiver operating characteristic curves were performed to determine the diagnostic performance of predictions. Results: MFP showed a larger size compared to PDAC (p = 0.009). Cystic degeneration, pancreatic ductal dilatation, vascular invasion, and pancreatic sinistral portal hypertension were more frequent and duct penetrating sign was less frequent in PDAC compared to MFP. Arterial CT attenuation, arterial, and portal enhancement ratios of MFP were higher than PDAC (p < 0.05). In multivariate analysis, arterial CT attenuation and pancreatic duct penetrating sign were independent predictors. Texture features in arterial phase including SurfaceArea, Percentile40, InverseDifferenceMoment_angle90_offset4, LongRunEmphasis_angle45_offset4, and uniformity were independent predictors. Texture features in portal phase including LongRunEmphasis_angle135_offset7, VoxelValueSum, LongRunEmphasis_angle135_offset4, and GLCMEntropy_angle45_offset1 were independent predictors. Areas under the curve of imaging feature-based, texture feature-based in arterial and portal phases, and the combined models were 0.84, 0.96, 0.93, and 0.98, respectively. Conclusions: CT texture analysis demonstrates great potential to differentiate MFP from PDAC. Copyright 2019 The Authors.
    • Exploratory analysis using machine learning to predict for chest wall pain in patients with stage I non-small-cell lung cancer treated with stereotactic body radiation therapy

      Chao, H.-H.; Valdes, G.; Luna, J.M. (John Wiley and Sons Ltd, 2018)
      Background and purpose: Chest wall toxicity is observed after stereotactic body radiation therapy (SBRT) for peripherally located lung tumors. We utilize machine learning algorithms to identify toxicity predictors to develop dose–volume constraints. Materials and methods: Twenty‐five patient, tumor, and dosimetric features were recorded for 197 consecutive patients with Stage I NSCLC treated with SBRT, 11 of whom (5.6%) developed CTCAEv4 grade ≥2 chest wall pain. Decision tree modeling was used to determine chest wall syndrome (CWS) thresholds for individual features. Significant features were determined using independent multivariate methods. These methods incorporate out‐of‐bag estimation using Random forests (RF) and bootstrapping (100 iterations) using decision trees. Results: Univariate analysis identified rib dose to 1 cc < 4000 cGy (P = 0.01), chest wall dose to 30 cc < 1900 cGy (P = 0.035), rib Dmax < 5100 cGy (P = 0.05) and lung dose to 1000 cc < 70 cGy (P = 0.039) to be statistically significant thresholds for avoiding CWS. Subsequent multivariate analysis confirmed the importance of rib dose to 1 cc, chest wall dose to 30 cc, and rib Dmax. Using learning‐curve experiments, the dataset proved to be self‐consistent and provides a realistic model for CWS analysis. Conclusions: Using machine learning algorithms in this first of its kind study, we identify robust features and cutoffs predictive for the rare clinical event of CWS. Additional data in planned subsequent multicenter studies will help increase the accuracy of multivariate analysis. Copyright 2018 The Authors. Journal of Applied Clinical Medical Physics published by Wiley Periodicals, Inc. on behalf of American Association of Physicists in Medicine.
    • Genetic Variations in the Transforming Growth Factor-β1 Pathway May Improve Predictive Power for Overall Survival in Non-small Cell Lung Cancer

      Zhang, Hong; Wang, Weili; Pi, Wenhu; Bi, Nan; DesRosiers, Colleen; Kong, Fengchong; Cheng, Monica; Yang, Li; Lautenschlaeger, Tim; Jolly, Shruti; et al. (Frontiers Media S.A., 2021-07-07)
      Purpose: Transforming growth factor-β1 (TGF-β1), a known immune suppressor, plays an important role in tumor progression and overall survival (OS) in many types of cancers. We hypothesized that genetic variations of single nucleotide polymorphisms (SNPs) in the TGF-β1 pathway can predict survival in patients with non-small cell lung cancer (NSCLC) after radiation therapy. Materials and Methods: Fourteen functional SNPs in the TGF-β1 pathway were measured in 166 patients with NSCLC enrolled in a multi-center clinical trial. Clinical factors, including age, gender, ethnicity, smoking status, stage group, histology, Karnofsky Performance Status, equivalent dose at 2 Gy fractions (EQD2), and the use of chemotherapy, were first tested under the univariate Cox's proportional hazards model. All significant clinical predictors were combined as a group of predictors named "Clinical." The significant SNPs under the Cox proportional hazards model were combined as a group of predictors named "SNP." The predictive powers of models using Clinical and Clinical + SNP were compared with the cross-validation concordance index (C-index) of random forest models. Results: Age, gender, stage group, smoking, histology, and EQD2 were identified as significant clinical predictors: Clinical. Among 14 SNPs, BMP2:rs235756 (HR = 0.63; 95% CI:0.42-0.93; p = 0.022), SMAD9:rs7333607 (HR = 2.79; 95% CI 1.22-6.41; p = 0.015), SMAD3:rs12102171 (HR = 0.68; 95% CI: 0.46-1.00; p = 0.050), and SMAD4: rs12456284 (HR = 0.63; 95% CI: 0.43-0.92; p = 0.016) were identified as powerful predictors of SNP. After adding SNP, the C-index of the model increased from 84.1 to 87.6% at 24 months and from 79.4 to 84.4% at 36 months. Conclusion: Genetic variations in the TGF-β1 pathway have the potential to improve the prediction accuracy for OS in patients with NSCLC.
    • Improving the predictive potential of diffusion MRI in schizophrenia using normative models-Towards subject-level classification

      Elad, Doron; Cetin-Karayumak, Suheyla; Zhang, Fan; Cho, Kang Ik K; Lyall, Amanda E; Seitz-Holland, Johanna; Ben-Ari, Rami; Pearlson, Godfrey D; Tamminga, Carol A; Sweeney, John A; et al. (Wiley-Blackwell, 2021-07-29)
      Diffusion MRI studies consistently report group differences in white matter between individuals diagnosed with schizophrenia and healthy controls. Nevertheless, the abnormalities found at the group-level are often not observed at the individual level. Among the different approaches aiming to study white matter abnormalities at the subject level, normative modeling analysis takes a step towards subject-level predictions by identifying affected brain locations in individual subjects based on extreme deviations from a normative range. Here, we leveraged a large harmonized diffusion MRI dataset from 512 healthy controls and 601 individuals diagnosed with schizophrenia, to study whether normative modeling can improve subject-level predictions from a binary classifier. To this aim, individual deviations from a normative model of standard (fractional anisotropy) and advanced (free-water) dMRI measures, were calculated by means of age and sex-adjusted z-scores relative to control data, in 18 white matter regions. Even though larger effect sizes are found when testing for group differences in z-scores than are found with raw values (p <.001), predictions based on summary z-score measures achieved low predictive power (AUC < 0.63). Instead, we find that combining information from the different white matter tracts, while using multiple imaging measures simultaneously, improves prediction performance (the best predictor achieved AUC = 0.726). Our findings suggest that extreme deviations from a normative model are not optimal features for prediction. However, including the complete distribution of deviations across multiple imaging measures improves prediction, and could aid in subject-level classification. © 2021 The Authors.
    • Information Extraction Framework for Disability Determination Using a Mental Functioning Use-Case.

      Zirikly, Ayah; Desmet, Bart; Newman-Griffis, Denis; Marfeo, Elizabeth E; McDonough, Christine; Goldman, Howard; Chan, Leighton (JMIR Publications, 2022-03-18)
      Natural language processing (NLP) in health care enables transformation of complex narrative information into high value products such as clinical decision support and adverse event monitoring in real time via the electronic health record (EHR). However, information technologies for mental health have consistently lagged because of the complexity of measuring and modeling mental health and illness. The use of NLP to support management of mental health conditions is a viable topic that has not been explored in depth. This paper provides a framework for the advanced application of NLP methods to identify, extract, and organize information on mental health and functioning to inform the decision-making process applied to assessing mental health. We present a use-case related to work disability, guided by the disability determination process of the US Social Security Administration (SSA). From this perspective, the following questions must be addressed about each problem that leads to a disability benefits claim: When did the problem occur and how long has it existed? How severe is it? Does it affect the person's ability to work? and What is the source of the evidence about the problem? Our framework includes 4 dimensions of medical information that are central to assessing disability-temporal sequence and duration, severity, context, and information source. We describe key aspects of each dimension and promising approaches for application in mental functioning. For example, to address temporality, a complete functional timeline must be created with all relevant aspects of functioning such as intermittence, persistence, and recurrence. Severity of mental health symptoms can be successfully identified and extracted on a 4-level ordinal scale from absent to severe. Some NLP work has been reported on the extraction of context for specific cases of wheelchair use in clinical settings. We discuss the links between the task of information source assessment and work on source attribution, coreference resolution, event extraction, and rule-based methods. Gaps were identified in NLP applications that directly applied to the framework and in existing relevant annotated data sets. We highlighted NLP methods with the potential for advanced application in the field of mental functioning. Findings of this work will inform the development of instruments for supporting SSA adjudicators in their disability determination process. The 4 dimensions of medical information may have relevance for a broad array of individuals and organizations responsible for assessing mental health function and ability. Further, our framework with 4 specific dimensions presents significant opportunity for the application of NLP in the realm of mental health and functioning beyond the SSA setting, and it may support the development of robust tools and methods for decision-making related to clinical care, program implementation, and other outcomes.
    • Inhibition Ability of Natural Compounds on Receptor-Binding Domain of SARS-CoV2: An In Silico Approach.

      Nedyalkova, Miroslava; Vasighi, Mahdi; Sappati, Subrahmanyam; Kumar, Anmol; Madurga, Sergio; Simeonov, Vasil (MDPI AG, 2021-12-18)
      The lack of medication to treat COVID-19 is still an obstacle that needs to be addressed by all possible scientific approaches. It is essential to design newer drugs with varied approaches. A receptor-binding domain (RBD) is a key part of SARS-CoV-2 virus, located on its surface, that allows it to dock to ACE2 receptors present on human cells, which is followed by admission of virus into cells, and thus infection is triggered. Specific receptor-binding domains on the spike protein play a pivotal role in binding to the receptor. In this regard, the in silico method plays an important role, as it is more rapid and cost effective than the trial and error methods using experimental studies. A combination of virtual screening, molecular docking, molecular simulations and machine learning techniques are applied on a library of natural compounds to identify ligands that show significant binding affinity at the hydrophobic pocket of the RBD. A list of ligands with high binding affinity was obtained using molecular docking and molecular dynamics (MD) simulations for protein-ligand complexes. Machine learning (ML) classification schemes have been applied to obtain features of ligands and important descriptors, which help in identification of better binding ligands. A plethora of descriptors were used for training the self-organizing map algorithm. The model brings out descriptors important for protein-ligand interactions.
    • MRI Radiomic Signature of White Matter Hyperintensities Is Associated With Clinical Phenotypes

      Bretzner, Martin; Bonkhoff, Anna K; Schirmer, Markus D; Hong, Sungmin; Dalca, Adrian V; Donahue, Kathleen L; Giese, Anne-Katrin; Etherton, Mark R; Rist, Pamela M; Nardin, Marco; et al. (Frontiers Media S.A., 2021-07-12)
      Objective: Neuroimaging measurements of brain structural integrity are thought to be surrogates for brain health, but precise assessments require dedicated advanced image acquisitions. By means of quantitatively describing conventional images, radiomic analyses hold potential for evaluating brain health. We sought to: (1) evaluate radiomics to assess brain structural integrity by predicting white matter hyperintensities burdens (WMH) and (2) uncover associations between predictive radiomic features and clinical phenotypes. Methods: We analyzed a multi-site cohort of 4,163 acute ischemic strokes (AIS) patients with T2-FLAIR MR images with total brain and WMH segmentations. Radiomic features were extracted from normal-appearing brain tissue (brain mask–WMH mask). Radiomics-based prediction of personalized WMH burden was done using ElasticNet linear regression. We built a radiomic signature of WMH with stable selected features predictive of WMH burden and then related this signature to clinical variables using canonical correlation analysis (CCA). Results: Radiomic features were predictive of WMH burden (R2 = 0.855 ± 0.011). Seven pairs of canonical variates (CV) significantly correlated the radiomics signature of WMH and clinical traits with respective canonical correlations of 0.81, 0.65, 0.42, 0.24, 0.20, 0.15, and 0.15 (FDR-corrected p-valuesCV1–6 < 0.001, p-valueCV7 = 0.012). The clinical CV1 was mainly influenced by age, CV2 by sex, CV3 by history of smoking and diabetes, CV4 by hypertension, CV5 by atrial fibrillation (AF) and diabetes, CV6 by coronary artery disease (CAD), and CV7 by CAD and diabetes. Conclusion: Radiomics extracted from T2-FLAIR images of AIS patients capture microstructural damage of the cerebral parenchyma and correlate with clinical phenotypes, suggesting different radiographical textural abnormalities per cardiovascular risk profile. Further research could evaluate radiomics to predict the progression of WMH and for the follow-up of stroke patients’ brain health.
    • Using Administrative Data to Predict Suicide After Psychiatric Hospitalization in the Veterans Health Administration System

      Kessler, R.C.; Bauer, M.S.; Kreyenbuhl, J. (Frontiers Media S.A., 2020)
      There is a very high suicide rate in the year after psychiatric hospital discharge. Intensive postdischarge case management programs can address this problem but are not cost-effective for all patients. This issue can be addressed by developing a risk model to predict which inpatients might need such a program. We developed such a model for the 391,018 short-term psychiatric hospital admissions of US veterans in Veterans Health Administration (VHA) hospitals 2010-2013. Records were linked with the National Death Index to determine suicide within 12 months of hospital discharge (n=771). The Super Learner ensemble machine learning method was used to predict these suicides for time horizon between 1 week and 12 months after discharge in a 70% training sample. Accuracy was validated in the remaining 30% holdout sample. Predictors included VHA administrative variables and small area geocode data linked to patient home addresses. The models had AUC=.79-.82 for time horizons between 1 week and 6 months and AUC=.74 for 12 months. An analysis of operating characteristics showed that 22.4%-32.2% of patients who died by suicide would have been reached if intensive case management was provided to the 5% of patients with highest predicted suicide risk. Positive predictive value (PPV) at this higher threshold ranged from 1.2% over 12 months to 3.8% per case manager year over 1 week. Focusing on the low end of the risk spectrum, the 40% of patients classified as having lowest risk account for 0%-9.7% of suicides across time horizons. Variable importance analysis shows that 51.1% of model performance is due to psychopathological risk factors accounted, 26.2% to social determinants of health, 14.8% to prior history of suicidal behaviors, and 6.6% to physical disorders. The paper closes with a discussion of next steps in refining the model and prospects for developing a parallel precision treatment model. Copyright 2020 Kessler, et. al.
    • WGEVIA: A Graph Level Embedding Method for Microcircuit Data.

      Wu, Xiaomin; Bhattacharyya, Shuvra S; Chen, Rong (Frontiers Media S.A., 2021-01-06)
      Functional microcircuits are useful for studying interactions among neural dynamics of neighboring neurons during cognition and emotion. A functional microcircuit is a group of neurons that are spatially close, and that exhibit synchronized neural activities. For computational analysis, functional microcircuits are represented by graphs, which pose special challenges when applied as input to machine learning algorithms. Graph embedding, which involves the conversion of graph data into low dimensional vector spaces, is a general method for addressing these challenges. In this paper, we discuss limitations of conventional graph embedding methods that make them ill-suited to the study of functional microcircuits. We then develop a novel graph embedding framework, called Weighted Graph Embedding with Vertex Identity Awareness (WGEVIA), that overcomes these limitations. Additionally, we introduce a dataset, called the five vertices dataset, that helps in assessing how well graph embedding methods are suited to functional microcircuit analysis. We demonstrate the utility of WGEVIA through extensive experiments involving real and simulated microcircuit data.