Citations

Showing 10 of 108152 citations.

Deep Learning–Based Histopathologic Assessment of Kidney Tissue
Hermsen, Meyke , Bel, Thomas de , Boer, Marjolijn den, Steenbergen, Eric J., Florquin, Sandrine , Roelofs, Joris J. T. H. , Stegall, Mark D. , Alexander, Mariam P., Smeets, Bart , Laak, Jeroen van der , Stegall, Mark D , Kers, Jesper , Smith, Byron H. , Hilbrands, Luuk B.

Mayo Clinic

Journal of the American Society of Nephrology | September 5, 2019 | Volume: 30 | Issue: 10 | Pages: 1968-1979

10.1681/asn.2019020144 | PMID 31488607 Get It

Significance Statement Histopathologic assessment of kidney tissue currently relies on manual scoring or traditional image-processing techniques to quantify and classify tissue features, time-consuming approaches that have limited reproducibility. The authors present an alternative approach, featuring a convolutional neural network for multiclass segmentation of kidney tissue in sections stained by periodic acid–Schiff. Their findings demonstrate applicability of convolutional neural networks for tissue from multiple centers, for biopsies and nephrectomy samples, and for the analysis of both healthy and pathologic tissues. In addition, they validated the network’s results with components from the Banff classification system. Their convolutional neural network may have utility for quantitative studies involving kidney histopathology across centers and potential for application in routine diagnostics. Background The development of deep neural networks is facilitating more advanced digital analysis of histopathologic images. We trained a convolutional neural network for multiclass segmentation of digitized kidney tissue sections stained with periodic acid–Schiff (PAS). Methods We trained the network using multiclass annotations from 40 whole-slide images of stained kidney transplant biopsies and applied it to four independent data sets. We assessed multiclass segmentation performance by calculating Dice coefficients for ten tissue classes on ten transplant biopsies from the Radboud University Medical Center in Nijmegen, The Netherlands, and on ten transplant biopsies from an external center for validation. We also fully segmented 15 nephrectomy samples and calculated the network’s glomerular detection rates and compared network-based measures with visually scored histologic components (Banff classification) in 82 kidney transplant biopsies. Results The weighted mean Dice coefficients of all classes were 0.80 and 0.84 in ten kidney transplant biopsies from the Radboud center and the external center, respectively. The best segmented class was “glomeruli” in both data sets (Dice coefficients, 0.95 and 0.94, respectively), followed by “tubuli combined” and “interstitium.” The network detected 92.7% of all glomeruli in nephrectomy samples, with 10.4% false positives. In whole transplant biopsies, the mean intraclass correlation coefficient for glomerular counting performed by pathologists versus the network was 0.94. We found significant correlations between visually scored histologic components and network-based measures. Conclusions This study presents the first convolutional neural network for multiclass segmentation of PAS-stained nephrectomy samples and transplant biopsies. Our network may have utility for quantitative studies involving kidney histopathology across centers and provide opportunities for deep learning applications in routine diagnostics.
Assessing Nasal Soft-Tissue Envelope Thickness for Rhinoplasty
Dey, Jacob K. , Recker, Chelsey, Olson, Michael D. , Panda, Ananya , Kostandy, Petro, Lane, John I. , Recker, Chelsey A, Kostandy, Petro M, Dey, Jacob K , Bowen, Andrew J. , Hamilton, Grant

Mayo Clinic

JAMA Facial Plastic Surgery | September 5, 2019 | Volume: 21 | Issue: 6 | Pages: 511-517

10.1001/jamafacial.2019.0715 | PMID 31486840 Get It

Importance Preoperative assessment of nasal soft-tissue envelope (STE) thickness is an important component of rhinoplasty that presently lacks validated tools. Objective To measure and assess the distribution of nasal STE thickness in a large patient population and to determine if facial plastic surgery clinicians can predict nasal STE thickness based on visual examination of the nose. Design, Setting, and Participants This retrospective review and prospective assessment of 190 adult patients by 4 expert raters was conducted at an academic tertiary referral center. The patients had high-resolution maxillofacial computed tomography (CT) scans and standardized facial photographs on file and did not have a history of nasal fracture, septal perforation, rhinoplasty, or other surgery or medical conditions altering nasal form. Data were analyzed in March 2019. Main Outcomes and Measures Measure nasal STE thickness at defined anatomic subsites using high-resolution CT scans. Measure expert-predicted nasal STE thickness based on visual examination of the nose using a scale from 0 (thinnest) to 100 (thickest). Results Of the 190 patients, 78 were women and the mean (SD) age was 45 (17) years. The nasal STE was thickest at the sellion (mean [SD]) (6.7 [1.7] mm), thinnest at the rhinion (2.1 [0.7] mm), thickened over the supratip (4.8 [1.0] mm) and nasal tip (3.1 [0.6] mm), and thinned over the columella (2.6 [0.4] mm). In the study population, nasal STE thickness followed a nearly normal distribution for each measured subsite, with the majority of patients in a medium thickness range. Comparison of predicted and actual nasal STE thickness showed that experts could accurately predict nasal STE thickness, with the highest accuracy at the nasal tip ( r , 0.73; prediction accuracy, 91%). A strong positive correlation was noted among the experts’ STE estimates ( r , 0.83-0.89), suggesting a high level of agreement between individual raters. Conclusions and Relevance There is variable thickness of the nasal STE, which influences the external nasal contour and rhinoplasty outcomes. With visual analysis of the nose, experts can agree on and predict nasal STE thickness, with the highest accuracy at the nasal tip. These data can aid in preoperative planning for rhinoplasty, allowing implementation of preoperative, intraoperative, and postoperative strategies to optimize the nasal STE, which may ultimately improve patient outcomes and satisfaction. Level of Evidence NA .
Early Integrated Telehealth versus In-Person Palliative Care for Patients with Advanced Lung Cancer: A Study Protocol
Zachariah, Finly , Dale, William , Feliciano, Josephine , Hanson, Laura C. , Blackhall, Leslie , Quest, Tammie E. , Curseen, Kimberly , Grey, Carl, Rhodes, Ramona L. , Shoemaker, Laura, Silveira, Maria J. , O’Mahony, Sean , Leventakos, Kostantinos, Trotter, Chardria, Sereno, Isabella, Kamdar, Mihir , Greer, Joseph A. , Chua, Isaac S. , Fischer, Stacy M. , Temel, Jennifer S.

Mayo Clinic

Journal of Palliative Medicine | September 5, 2019 | Volume: 22 | Issue: 1_suppl | Pages: No page available

10.1089/jpm.2019.0210 | PMID 31486721 Get It

Abstract Introduction: Early palliative care (PC) integrated with oncology care improves quality of life (QOL), depression symptoms, illness understanding, and end-of-life (EOL) care for patients with advanced lung cancer. The aims of this trial are to compare the effect of delivering early integrated PC through telehealth versus in-person on patient and caregiver outcomes. We hypothesize that both modalities for delivering early PC would be equivalent for improving patient QOL, communication about EOL care preferences with their oncologist, and length of stay in hospice. Methods: For this comparative effectiveness trial, we will enroll and randomize 1250 adult patients with advanced nonsmall cell lung cancer (NSCLC), who are not being treated with curative intent, to receive either early integrated telehealth or in-person PC at 20 cancer centers throughout the United States. Patients may also invite a family caregiver to participate in the study. Patients and their caregivers in both study groups meet at least every four weeks with a PC clinician from within 12 weeks of patient diagnosis of advanced NSCLC until death. Participants complete measures of QOL, mood, and quality of communication with oncologists at baseline before randomization and at 12, 24, 36, and 48 weeks. Information on health care utilization, including length of stay in hospice, will be collected from patients' health records. To test equivalence in outcomes between study groups, we will compute analysis of covariance and mixed linear models, controlling for baseline scores and study site. Study Implementation and Stakeholder Engagement: To ensure that this comparative effectiveness trial and findings are as patient centered and meaningful as possible, we have incorporated a robust patient and stakeholder engagement plan. Our stakeholder partners include (1) patients/families, (2) PC clinicians, (3) telehealth experts and clinician users, (4) representatives from health care systems and medical insurance providers, and (5) health care policy makers and advocates. These stakeholders will inform and provide feedback about every phase of study implementation.
Efficacy of Difluoromethylornithine and Aspirin for Treatment of Adenomas and Aberrant Crypt Foci in Patients with Prior Advanced Colorectal Neoplasms
Velamala, Pruthvi, Song, Louis M. Wong Kee , Viggiano, Thomas R., Bruining, David H. , Rajan, Elizabeth , Gostout, Christopher J., Kraichely, Robert E., Buttar, Navtej , Schroeder, Kenneth W., Larson, Mark V., Sweetser, Seth , Sedlack, Robert, Sinicrope, Stephen N. , Della’Zanna, Gary , Noaeill, Joni S., Meyers, Jeffrey P., Foster, Nathan R. , Velamala, Pruthvi R, Buttar, Navtej S, Kisiel, John B , Sweetser, Seth R, Sedlack, Robert R, Richmond, Ellen S. , Umar, Asad, Della'Zanna, Gary, Sinicrope, Stephen N , Sinicrope, Frank A. , Kisiel, John B. , Umar, Asad

Mayo Clinic

Cancer Prevention Research | September 4, 2019 | Volume: 12 | Issue: 11 | Pages: 821-830

10.1158/1940-6207.capr-19-0167 | PMID 31484660 Get It

Abstract Difluoromethylornithine (DFMO), an inhibitor of polyamine synthesis, was shown to act synergistically with a NSAID for chemoprevention of colorectal neoplasia. We determined the efficacy and safety of DFMO plus aspirin for prevention of colorectal adenomas and regression of rectal aberrant crypt foci (ACF) in patients with prior advanced adenomas or cancer. A double-blinded, placebo-controlled trial was performed in 104 subjects (age 46–83) randomized (1:1) to receive daily DFMO (500 mg orally) plus aspirin (325 mg) or matched placebos for one year. All polyps were removed at baseline. Adenoma number (primary endpoint) and rectal ACF (index cluster and total) were evaluated at a one year colonoscopy. ACF were identified by chromoendoscopy. Toxicity was monitored, including audiometry. Eighty-seven subjects were evaluable for adenomas or ACF modulation (n = 62). At one year of treatment, adenomas were detected in 16 (38.1%) subjects in the DFMO plus aspirin arm (n = 42) versus 18 (40.9%) in the placebo arm (n = 44; P = 0.790); advanced adenomas were similar (n = 3/arm). DFMO plus aspirin was associated with a statistically significant reduction in the median number of rectal ACF compared with placebo (P = 0.036). Total rectal ACF burden was also reduced in the treatment versus the placebo arm relative to baseline (74% vs. 45%, P = 0.020). No increase in adverse events, including ototoxicity, was observed in the treatment versus placebo arms. While adenoma recurrence was not significantly reduced by one year of DFMO plus aspirin, the drug combination significantly reduced rectal ACF number consistent with a chemopreventive effect.
Abstract P2050: The Pcornet Blood Pressure Control Laboratory
Shaw, Kathryn, Smith, Myra, Todd, Jonathan , O’Brien, Emily C. , Faulkner, Madelaine, Maeztu, Carlos , Shay, Christine, DeHoff, Rhonda M Cooper, Pletcher, Mark J. , Fontil, Valy , Carton, Thomas W. , Shaw, Kathryn, Chamberlain, Alanna M. , Wozniak, Gregory , Rakotz, Michael

Mayo Clinic

Hypertension | September 4, 2019 | Volume: 74 | Issue: Suppl_1 | Pages: No page available

10.1161/hyp.74.suppl_1.p2050 Get It

Background: New technology and healthcare delivery approaches may help improve blood pressure (BP) control. Randomized controlled trials (RCTs) can demonstrate effectiveness of these emerging approaches, both overall and especially within underserved populations, but RCTs are expensive. Our objective is to establish a national platform to support BP control surveillance and efficient RCTs. Methods: The PCORnet BP Control Laboratory, designed and launched in partnership with the American Heart Association (AHA) and the American Medical Association (AMA), leverages electronic health record (EHR) systems throughout the US, the National Patient-Centered Outcomes Research Network (PCORnet), and the NIH-funded Eureka Research Platform, which enables direct-to-participant research including collection of patient-reported outcomes and mHealth data from wearable devices and smartphones. We will use these resources to 1) Conduct national surveillance through quarterly EHR data queries to calculate and track institution- and clinic-level BP control metrics across 23 PCORnet institutions, overall and within key subgroups, and support participation in the AHA/AMA’s Target:BP recognition program (BP Track); 2) Compare effectiveness of a Full Support versus Self-Guided version of the AMA’s Measure Accurately, Act Rapidly, and Partner with Patients (MAP) program at improving BP control in a cluster randomized trial of 24 safety net clinics (BP MAP); and 3) Compare effectiveness of Smartphone-linked versus standard home BP monitoring at reducing systolic BP in an individual-level, direct-to-participant RCT of 2000 patients with uncontrolled BP (BP Home). Results: Preliminary BP Track queries demonstrate an overall BP control rate of 56%, lower control in Black patients (51%), substantial heterogeneity in clinic-level metrics (e.g., 33% vs. 64% BP control), and low rates of medication intensification (9% prescribed a new medication class when BP was high). BP Track will launch PCORnet-wide queries in June; BP MAP in May; and BP Home in August 2019. Conclusions: Feasibility testing is underway to determine if the PCORnet BP Control Laboratory will be useful for investigators interested in conducting efficient RCTs of BP control interventions.
Abstract P143: Multifaceted Roles of Gut Microbiome and Bacterial Metabolites in Pulmonary Arterial Hypertension
Kim, Seungbum S, Walejko, Jacquelyn M., Ray, Jordan , Richards, Elaine M. , Shapiro, Brian P. , Raizada, Mohan K. , Rigatto, Katya , Gazzana, Marcelo Basso , Knorst, Marli Maria , Pepine, Carl J.

Mayo Clinic

Hypertension | September 4, 2019 | Volume: 74 | Issue: Suppl_1 | Pages: No page available

10.1161/hyp.74.suppl_1.p143 Get It

Objectives: Pulmonary arterial hypertension (PAH) is a deadly disease without any effective cure. Identification of the PAH-associated gut microbiome may shift conceptual paradigms of the disease that could lead to new therapeutic advancement. We tested the hypothesis that PAH patients have distinct gut microbiome composition contributing to PAH that predicts the disease. Methods: A total of 71 participants were recruited. Fecal microbiomes of 18 type 1 PAH patients (mean pulmonary arterial pressure [mPAP] 57.4±16.7 mmHg) and 13 reference subjects were compared by shotgun metagenomics methods. Plasma from 22 PAH patients (mPAP 48.3± 18.4 mmHg) and 18 reference subjects was used in untargeted metabolomic analysis. Results: Significant taxonomic and functional changes in the microbiome of the PAH cohort were observed. PAH patients had increased gut barrier dysfunction and inflammation as evidenced by plasma markers and metagenomics. A random forest model predicted PAH from gut microbiome composition with 82.6% accuracy. Changes in the gut microbiome were associated with purine metabolism, arginine biosynthesis, trimethylamine production and tryptophan biosynthesis, all previously associated with PAH. Area under the curve of the multi-variate receiver operating characteristics (ROC) plot for metabolites of these pathways had a predictive accuracy of 0.965. Conclusions: The gut microbiome/metabolites of PAH patients predict disease in random forest models and ROC analyses. The unique PAH gut microbiome influences carnitine, arginine and purine metabolisms contributing to pathophysiology. These highlight previously unknown roles of gut bacteria and their metabolites in PAH that could lead to new therapeutic or management paradigms.
Middle-aged Man With Exertional Dyspnea and Neck Fullness
Vogt, J , Newman, Darrell B. , Vogt, Joshua C, Newman, D Brian, Nishimura, Rick A.

Mayo Clinic

JAMA Cardiology | September 4, 2019 | Volume: 4 | Issue: 10 | Pages: 1045

10.1001/jamacardio.2019.1677 | PMID 31483435 Get It

Editorial Comment
Lyon, Timothy D. , Lyon, Timothy D

Mayo Clinic

Journal of Urology | September 4, 2019 | Volume: 202 | Issue: 6 | Pages: 1149-1149

10.1097/01.ju.0000581892.73481.1f | PMID 31483712 Get It

Implementation and 2‐year outcomes of the first FDA‐approved implantable apheresis vascular access device
Gray, Kristin L., Steidley, Isabella G., Benson, Hollie L., Pearce, Christine L., Bachman, Amy M., Adamski, Jill , Adamksi, Jill , Steidley, Isabella G

Mayo Clinic

Transfusion | September 4, 2019 | Volume: 59 | Issue: 11 | Pages: 3461-3467

10.1111/trf.15512 | PMID 31483876 Get It

BACKGROUNDPatients requiring chronic apheresis treatments typically lack sufficient peripheral venous access to support long‐term therapy. Historically, central venous tunneled catheters, septum‐bearing subcutaneous ports, and fistulas were used to obtain required blood flow rates for apheresis procedures. In 2017, the US Food and Drug Administration approved the first intravascular device specifically designed for apheresis therapy, the PowerFlow Implantable Apheresis IV Port.METHODSSeveral preimplementation meetings with key hospital stakeholders were held to determine the most efficient and safest strategy for integrating the PowerFlow device into our practice. Interventional radiologists implanted the apheresis port in patients meeting specified criteria. Performance metrics and adverse events were evaluated over a 2‐year period, July 2017 through June 2019.RESULTSEighteen patients underwent apheresis therapy using the PowerFlow port. The most common apheresis therapy provided was extracorporeal photopheresis, followed by therapeutic plasma exchange and low‐density lipoprotein apheresis. Flow rates up to 90 mL/min were obtained; the rates were limited by patient tolerance for the apheresis procedure. Complications included infection, obstruction due to fibroblastic sleeve, and migration of the vascular device. The estimated risk of PowerFlow‐associated bloodstream infection in the study population was 0.18 per 1000 intravascular device days.CONCLUSIONThe PowerFlow Implantable Apheresis IV Port can achieve flow rates necessary for all apheresis therapies and is a promising alternative vascular access device for patients undergoing apheresis.