Complementing sparse vascular imaging data by physiological adaptation rules

2020 ◽  
Author(s):  
Maarten H.G. Heusinkveld ◽  
Robert J. Holtackers ◽  
Bouke P. Adriaans ◽  
Jos Op't Roodt ◽  
Theo Arts ◽  
...  
Keyword(s):  
Clinical Decision Making ◽  
Mechanical Load ◽  
Wall Stress ◽  
Clinical Decision ◽  
Physiological Adaptation ◽  
Patient Specific ◽  
Data Sets ◽  
Imaging Data ◽  
Artery Segment ◽  
Flow Waveforms

Introduction:Mathematical modeling of pressure and flow waveforms in blood vessels using pulse wave propagation (PWP)-models has tremendous potential to support clinical decision-making. For a personalized model outcome, measurements of all modeled vessel radii and wall thicknesses are required. In clinical practice, however, data sets are often incomplete. To overcome this problem, we hypothesized that the adaptive capacity of vessels in response to mechanical load could be utilized to fill in the gaps of incomplete patient-specific data sets. Methods:We implemented homeostatic feedback loops in a validated PWP model to allow adaptation of vessel geometry to maintain physiological values of wall stress and wall shear stress. To evaluate our approach, we gathered vascular MRI and ultrasound data sets of wall thicknesses and radii of central and arm arterial segments of ten healthy subjects. Reference models (i.e. termed RefModel, n=10) were simulated using complete data, whereas adapted models (AdaptModel, n=10) used data of one carotid artery segment only while the remaining geometries in this model were estimated using adaptation. We evaluated agreement between RefModel and AdaptModel geometries, as well as between pressure and flow waveforms of both models. Results:Limits of agreement (bias±2SD of difference) between AdaptModel and RefModel radii and wall thicknesses were 0.2±2.6 mm and -140±557 μm, respectively. Pressure and flow waveform characteristics of the AdaptModel better resembled those of the RefModels as compared to the model in which the vessels were not adapted.Conclusions:Our adaptation-based PWP-model enables personalization of vascular geometries even when not all required data is available.

Gallbladder Polyps: Real or Imagined?

2018 ◽  
Vol 84 (10) ◽  
pp. 1670-1674 ◽  
Author(s):  
Yiping Li ◽  
Talar Tejirian ◽  
J. Craig Collins
Keyword(s):  
Clinical Decision Making ◽  
Clinical Decision ◽  
Imaging Data ◽  
Final Pathology ◽  
Gallbladder Polyps ◽  
Imaging Results ◽  
Unreliable Method ◽  
Us Findings ◽  
Risk Of Cancer ◽  
Selection Of

The finding of gallbladder polyps on imaging studies prompts further workup. Imaging results are often discordant with final pathology. The goal of this study is to compare polypoid lesions of the gallbladder found on preoperative ultrasound (US) with final pathologic diagnosis after cholecystectomy to help guide clinical decision-making. A retrospective study was conducted identifying adult patients who were diagnosed with polyps via US and who underwent cholecystectomy from 2008 through 2015. Imaging data, final pathology, and demographics were manually reviewed. A total of 2290 cholecystectomy patients had US-based polyps. Of these, 1661 patients (73%) did not have polyps on final pathology; primarily, stones or sludge were identified. Adenomyosis was diagnosed in 61 patients (2.7%). A total of 556 patients (24.2%) had pathologic polypoid lesions with the following breakdown: 463 (20.2%) cholesterol polyps, 43 other benign polyps (1.8%), 40 adenomas (1.7%), and 10 adenocarcinomas (0.4%). All patients with adenocarcinoma were older than 40 years and 91 per cent had US findings of polyps >10 mm. Ultrasound alone is an unreliable method of detecting real gallbladder polyps. This large database study found a very low risk of cancer. Size on US and patient age should be considered in the selection of appropriate surgical candidates with sonographic “polyps.”

scholarly journals Quantifying the Impact of Patient-Specific Factors and Disease Severity on Clinical Decision Making in Cuff Tear Arthropathy: A Case-Based Survey

2019 ◽  
Vol 15 (3) ◽  
pp. 276-285
Author(s):  
Adam P. Schumaier ◽  
Yehia H. Bedeir ◽  
Joshua S. Dines ◽  
Keith Kenter ◽  
Lawrence V. Gulotta ◽  
...  
Keyword(s):  
Decision Making ◽  
Disease Severity ◽  
Clinical Decision Making ◽  
Clinical Decision ◽  
Patient Specific ◽  
Cuff Tear Arthropathy ◽  
Cuff Tear ◽  
Specific Factors ◽  
The Impact ◽  
Case Based

Combination chemotherapy versus temozolomide (TMZ) for patients with MGMT methylated (m-MGMT) glioblastoma (GBM): Results of cellworks omics biosimulation—MyCare-015.

2020 ◽  
Vol 38 (15_suppl) ◽  
pp. e14501-e14501
Author(s):  
Michael Castro ◽  
Nirjhar Mundkur ◽  
Anusha Pampana ◽  
Aftab Alam ◽  
Aktar Alam ◽  
...  
Keyword(s):  
Combination Therapy ◽  
Clinical Decision Making ◽  
Drug Effects ◽  
Standard Of Care ◽  
Clinical Decision ◽  
Phase Iii ◽  
Patient Specific ◽  
Experimental Therapy ◽  
Newly Diagnosed ◽  
Current Standard

e14501 Background: UKT-03 evaluated TMZ plus Lomustine in a single arm phase II trial in newly diagnosed GBM patients. An overall survival of 23 months was a substantial improvement over historical experience. Patients with m-MGMT v. unmethylated tumors had a 2-yr survival of 75% and median survival not reached compared to 20% and 12.5 months, respectively. These data formed the basis for NOA-9, a randomized phase III trial in newly diagnosed, m-MGMT GBM which randomized 141 patients to standard therapy or experimental therapy with Lomustine and TMZ every 6 weeks. A superiority for the combination was observed: 48.1 v. 31.4 months for the standard arm in the ITT analysis. Nevertheless, many neurooncologists are reluctant to adopt this approach. The current standard of care uses single biomarker, m-MGMT, in contrast to comprehensive pathway analysis (CPA). We sought to determine if CPA could discriminate more effectively among each patient’s likelihood of benefiting from combination treatment. Methods: Cellworks Singula employs a novel Cellworks Omics Biology Model (CBM) to predict patient-specific biomarker and phenotype response of personalized GBM avatars to drug agents, radiation, and targeted therapies. The CBM was developed and validated using PubMed to generate protein network maps of patient-specific activated and inactivated disease pathways. CBM was used to simulate the TMZ and TMZ-Lomustine therapies for each patient in a TCGA cohort of 368 GBM patients. Omics data including methylation, whole exome sequencing, and copy number alterations were input into CBM. The Singula Composite Inhibition Score (CIS) was calculated based on the measured quantitative drug effects. Results: Though incremental gain from the combination was seen in all patients, CIS varied across the population with relative scores ranging from 32-82, with best responders have more than twice the benefit. Conclusions: CPA shows that m-MGMT is an excellent biomarker for determining the likelihood of benefit from TMZ and lomustine, with the caveat that CBM identifies 18% could be spared from TMZ exposure and would benefit from Lomustine alone. Otherwise, these data lend support for evolving the standard of care with combination therapy for patients with m-MGMT GBM and should help overcome a reluctance to employing combination therapy. Additionally, CBM has utility to individualize clinical decision making. [Table: see text]

scholarly journals Knowledge transfer to enhance the performance of deep learning models for automated classification of B-cell neoplasms

2021 ◽  
Author(s):  
Nanditha Mallesh ◽  
Max Zhao ◽  
Lisa Meintker ◽  
Alexander Höllein ◽  
Franz Elsner ◽  
...  
Keyword(s):  
Flow Cytometry ◽  
Deep Learning ◽  
Knowledge Transfer ◽  
Clinical Decision Making ◽  
Dimensional Space ◽  
Clinical Decision ◽  
Data Sets ◽  
Automated Classification ◽  
Learning Models ◽  
Hematological Disorders

AbstractMulti-parameter flow cytometry (MFC) is a cornerstone in clinical decision making for hematological disorders such as leukemia or lymphoma. MFC data analysis requires trained experts to manually gate cell populations of interest, which is time-consuming and subjective. Manual gating is often limited to a two-dimensional space. In recent years, deep learning models have been developed to analyze the data in high-dimensional space and are highly accurate. Such models have been used successfully in histology, cytopathology, image flow cytometry, and conventional MFC analysis. However, current AI models used for subtype classification based on MFC data are limited to the antibody (flow cytometry) panel they were trained on. Thus, a key challenge in deploying AI models into routine diagnostics is the robustness and adaptability of such models. In this study, we present a workflow to extend our previous model to four additional MFC panels. We employ knowledge transfer to adapt the model to smaller data sets. We trained models for each of the data sets by transferring the features learned from our base model. With our workflow, we could increase the model’s overall performance and more prominently, increase the learning rate for very small training sizes.

scholarly journals Artificial intelligence in arthroplasty

Arthroplasty ◽  
2021 ◽  
Vol 3 (1) ◽  
Author(s):  
Glen Purnomo ◽  
Seng-Jin Yeo ◽  
Ming Han Lincoln Liow
Keyword(s):  
Artificial Intelligence ◽  
Clinical Decision Making ◽  
Recent Literature ◽  
Improve Patient Care ◽  
Clinical Decision ◽  
Patient Specific ◽  
Allocation Decision ◽  
Medical Specialties ◽  
Future Direction ◽  
Improve Patient

AbstractArtificial intelligence (AI) is altering the world of medicine. Given the rapid advances in technology, computers are now able to learn and improve, imitating humanoid cognitive function. AI applications currently exist in various medical specialties, some of which are already in clinical use. This review presents the potential uses and limitations of AI in arthroplasty to provide a better understanding of the existing technology and future direction of this field.Recent literature demonstrates that the utilization of AI in the field of arthroplasty has the potential to improve patient care through better diagnosis, screening, planning, monitoring, and prediction. The implementation of AI technology will enable arthroplasty surgeons to provide patient-specific management in clinical decision making, preoperative health optimization, resource allocation, decision support, and early intervention. While this technology presents a variety of exciting opportunities, it also has several limitations and challenges that need to be overcome to ensure its safety and effectiveness.

scholarly journals Radiogenomics and Radiomics in Liver Cancers

Diagnostics ◽  
2018 ◽  
Vol 9 (1) ◽  
pp. 4 ◽  
Author(s):  
Aman Saini ◽  
Ilana Breen ◽  
Yash Pershad ◽  
Sailendra Naidu ◽  
M. Knuttinen ◽  
...  
Keyword(s):  
Clinical Decision Making ◽  
Clinical Information ◽  
Clinical Decision ◽  
Molecular Profile ◽  
Imaging Features ◽  
Imaging Data ◽  
Prognostic Information ◽  
Cross Sectional ◽  
Related Field ◽  
Liver Cancers

Radiogenomics is a computational discipline that identifies correlations between cross-sectional imaging features and tissue-based molecular data. These imaging phenotypic correlations can then potentially be used to longitudinally and non-invasively predict a tumor’s molecular profile. A different, but related field termed radiomics examines the extraction of quantitative data from imaging data and the subsequent combination of these data with clinical information in an attempt to provide prognostic information and guide clinical decision making. Together, these fields represent the evolution of biomedical imaging from a descriptive, qualitative specialty to a predictive, quantitative discipline. It is anticipated that radiomics and radiogenomics will not only identify pathologic processes, but also unveil their underlying pathophysiological mechanisms through clinical imaging alone. Here, we review recent studies on radiogenomics and radiomics in liver cancers, including hepatocellular carcinoma, intrahepatic cholangiocarcinoma, and metastases to the liver.

scholarly journals Inpatient Palliative Care Utilization for Patients with Brain Metastases

2021 ◽  
Author(s):  
Meghan Price ◽  
Elizabeth P Howell ◽  
Tara Dalton ◽  
Luis Ramirez ◽  
Claire Howell ◽  
...  
Keyword(s):  
Palliative Care ◽  
Brain Metastases ◽  
Clinical Decision Making ◽  
Symptom Burden ◽  
Retrospective Chart Review ◽  
Clinical Decision ◽  
Patient Specific ◽  
Care Utilization ◽  
Black African ◽  
Patient Race

Abstract Introduction Given the high symptom burden and complex clinical decision making associated with a diagnosis of brain metastases (BM), specialty Palliative Care (PC) can meaningfully improve patient quality of life. However, no prior study has formally evaluated patient-specific factors associated with PC consultation among BM patients. Methods We examined the rates of PC consults in a cohort of 1303 patients with brain metastases admitted to three tertiary medical centers from October 2015 to December 2018. Patient demographics, surgical status, 30-day readmission, and death data were collected via retrospective chart review. PC utilization was assessed by identifying encounters for which an inpatient consult to PC was placed. Statistical analyses were performed to compare characteristics and outcomes between patients who did and did not receive PC consults. Results We analyzed 1303 patients admitted to the hospital with brain metastases. The average overall rate of inpatient PC consultation was 19.6%. Rates of PC utilization differed significantly by patient race (17.5% in White/Caucasian vs. 26.0% in Black/African American patients, p = 0.0014). Patients who received surgery during their admission had significantly lower rates of PC consultation (3.9% vs 22.4%, p < 0.0001). Patients who either died during their admission or were discharged to hospice had significantly higher rates of PC than those who were discharged home or to rehabilitation (p < 0.0001). Conclusions In our dataset, PC consultation rates varied by patient demographic, surgical status, discharging service and practice setting. Further work is needed to identify the specific barriers to optimally utilizing specialty PC in this population.

scholarly journals Interpreting patient-Specific risk prediction using contextual decomposition of BiLSTMs: application to children with asthma

2019 ◽  
Vol 19 (1) ◽  
Author(s):  
Rawan AlSaad ◽  
Qutaibah Malluhi ◽  
Ibrahim Janahi ◽  
Sabri Boughorbel
Keyword(s):  
Decision Making ◽  
Clinical Decision Making ◽  
Short Term Memory ◽  
Clinical Decision ◽  
Patient Specific ◽  
Great Promise ◽  
Short Term ◽  
Children With Asthma ◽  
Correct Pattern ◽  
Long Short Term Memory

Abstract Background Predictive modeling with longitudinal electronic health record (EHR) data offers great promise for accelerating personalized medicine and better informs clinical decision-making. Recently, deep learning models have achieved state-of-the-art performance for many healthcare prediction tasks. However, deep models lack interpretability, which is integral to successful decision-making and can lead to better patient care. In this paper, we build upon the contextual decomposition (CD) method, an algorithm for producing importance scores from long short-term memory networks (LSTMs). We extend the method to bidirectional LSTMs (BiLSTMs) and use it in the context of predicting future clinical outcomes using patients’ EHR historical visits. Methods We use a real EHR dataset comprising 11071 patients, to evaluate and compare CD interpretations from LSTM and BiLSTM models. First, we train LSTM and BiLSTM models for the task of predicting which pre-school children with respiratory system-related complications will have asthma at school-age. After that, we conduct quantitative and qualitative analysis to evaluate the CD interpretations produced by the contextual decomposition of the trained models. In addition, we develop an interactive visualization to demonstrate the utility of CD scores in explaining predicted outcomes. Results Our experimental evaluation demonstrate that whenever a clear visit-level pattern exists, the models learn that pattern and the contextual decomposition can appropriately attribute the prediction to the correct pattern. In addition, the results confirm that the CD scores agree to a large extent with the importance scores generated using logistic regression coefficients. Our main insight was that rather than interpreting the attribution of individual visits to the predicted outcome, we could instead attribute a model’s prediction to a group of visits. Conclusion We presented a quantitative and qualitative evidence that CD interpretations can explain patient-specific predictions using CD attributions of individual visits or a group of visits.

scholarly journals A machine learning framework for automated diagnosis and computer-assisted planning in plastic and reconstructive surgery

2019 ◽  
Vol 9 (1) ◽  
Author(s):  
Paul G. M. Knoops ◽  
Athanasios Papaioannou ◽  
Alessandro Borghi ◽  
Richard W. F. Breakey ◽  
Alexander T. Wilson ◽  
...  
Keyword(s):  
Machine Learning ◽  
Decision Making ◽  
Reconstructive Surgery ◽  
Clinical Decision Making ◽  
Specific Treatment ◽  
Operation Time ◽  
Clinical Decision ◽  
Patient Specific ◽  
Computer Assisted ◽  
Plastic And Reconstructive Surgery

Abstract Current computational tools for planning and simulation in plastic and reconstructive surgery lack sufficient precision and are time-consuming, thus resulting in limited adoption. Although computer-assisted surgical planning systems help to improve clinical outcomes, shorten operation time and reduce cost, they are often too complex and require extensive manual input, which ultimately limits their use in doctor-patient communication and clinical decision making. Here, we present the first large-scale clinical 3D morphable model, a machine-learning-based framework involving supervised learning for diagnostics, risk stratification, and treatment simulation. The model, trained and validated with 4,261 faces of healthy volunteers and orthognathic (jaw) surgery patients, diagnoses patients with 95.5% sensitivity and 95.2% specificity, and simulates surgical outcomes with a mean accuracy of 1.1 ± 0.3 mm. We demonstrate how this model could fully-automatically aid diagnosis and provide patient-specific treatment plans from a 3D scan alone, to help efficient clinical decision making and improve clinical understanding of face shape as a marker for primary and secondary surgery.

Sign in / Sign up

Export Citation Format

Share Document