scholarly journals Assessment of patient specific information in the wild on fundus photography and optical coherence tomography

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Marion R. Munk ◽  
Thomas Kurmann ◽  
Pablo Márquez-Neila ◽  
Martin S. Zinkernagel ◽  
Sebastian Wolf ◽  
...  
Keyword(s):  
Deep Learning ◽  
Cross Sections ◽  
Underlying Disease ◽  
Geographic Atrophy ◽  
Clinical Population ◽  
Fundus Photography ◽  
Peak Performance ◽  
Patient Specific ◽  
Specific Information ◽  
Fundus Images

AbstractIn this paper we analyse the performance of machine learning methods in predicting patient information such as age or sex solely from retinal imaging modalities in a heterogeneous clinical population. Our dataset consists of N = 135,667 fundus images and N = 85,536 volumetric OCT scans. Deep learning models were trained to predict the patient’s age and sex from fundus images, OCT cross sections and OCT volumes. For sex prediction, a ROC AUC of 0.80 was achieved for fundus images, 0.84 for OCT cross sections and 0.90 for OCT volumes. Age prediction mean absolute errors of 6.328 years for fundus, 5.625 years for OCT cross sections and 4.541 for OCT volumes were observed. We assess the performance of OCT scans containing different biomarkers and note a peak performance of AUC = 0.88 for OCT cross sections and 0.95 for volumes when there is no pathology on scans. Performance drops in case of drusen, fibrovascular pigment epitheliuum detachment and geographic atrophy present. We conclude that deep learning based methods are capable of classifying the patient’s sex and age from color fundus photography and OCT for a broad spectrum of patients irrespective of underlying disease or image quality. Non-random sex prediction using fundus images seems only possible if the eye fovea and optic disc are visible.

Tailoring Communications for Primary Care Settings

1998 ◽  
Vol 37 (02) ◽  
pp. 171-178 ◽  
Author(s):  
B. Glassman ◽  
B. K. Rimer
Keyword(s):  
Primary Care ◽  
Health Professionals ◽  
Contact Time ◽  
Behavioral Changes ◽  
Patient Specific ◽  
Specific Information ◽  
Medical Settings ◽  
Primary Care Settings ◽  
Professional Contact ◽  
Tailored Communications

AbstractIn more and more medical settings, physicians have less and less time to be effective communicators. To be effective, they need accurate, current information about their patients. Tailored health communications can facilitate positive patient-provider communications and foster behavioral changes conducive to health. Tailored communications (TCs) are produced for an individual based on information about that person. The focus of this report is on tailored print communications (TPCs). TPCs also enhance the process of evaluation, because they require a database and the collection of patient-specific information. We present a Tailoring Model for Primary Care that describes the steps involved in creating TPCs. We also provide examples from three ongoing studies in which TPCs are being used in order to illustrate the kinds of variables used for tailoring the products that are developed and how evaluation is conducted. TPCs offer opportunities to expand the reach of health professionals and to give personalized, individualized massages in an era of shrinking professional contact time.

scholarly journals Accurate Deep Learning-Based Sleep Staging in a Clinical Population with Suspected Obstructive Sleep Apnea

2019 ◽  
pp. 1-1 ◽  
Author(s):  
Henri Korkalainen ◽  
Timo Leppanen ◽  
Juhani Aakko ◽  
Sami Nikkonen ◽  
Samu Kainulainen ◽  
...  
Keyword(s):  
Obstructive Sleep Apnea ◽  
Deep Learning ◽  
Sleep Apnea ◽  
Clinical Population ◽  
Sleep Staging ◽  
Obstructive Sleep

scholarly journals Prediction of 3D Cardiovascular hemodynamics before and after coronary artery bypass surgery via deep learning

2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Gaoyang Li ◽  
Haoran Wang ◽  
Mingzi Zhang ◽  
Simon Tupin ◽  
Aike Qiao ◽  
...  
Keyword(s):  
Deep Learning ◽  
Artery Bypass ◽  
Computational Cost ◽  
Specific Model ◽  
Arterial System ◽  
Patient Specific ◽  
Cardiovascular Hemodynamics ◽  
Before And After ◽  
Deep Learning Network ◽  
Cfd Method

AbstractThe clinical treatment planning of coronary heart disease requires hemodynamic parameters to provide proper guidance. Computational fluid dynamics (CFD) is gradually used in the simulation of cardiovascular hemodynamics. However, for the patient-specific model, the complex operation and high computational cost of CFD hinder its clinical application. To deal with these problems, we develop cardiovascular hemodynamic point datasets and a dual sampling channel deep learning network, which can analyze and reproduce the relationship between the cardiovascular geometry and internal hemodynamics. The statistical analysis shows that the hemodynamic prediction results of deep learning are in agreement with the conventional CFD method, but the calculation time is reduced 600-fold. In terms of over 2 million nodes, prediction accuracy of around 90%, computational efficiency to predict cardiovascular hemodynamics within 1 second, and universality for evaluating complex arterial system, our deep learning method can meet the needs of most situations.

scholarly journals Deep Learning for Diabetic Retinopathy Detection and Classification Based on Fundus Images: A Review

2021 ◽  
pp. 104599
Author(s):  
Nikos Tsiknakis ◽  
Dimitris Theodoropoulos ◽  
Georgios Manikis ◽  
Emmanouil Ktistakis ◽  
Ourania Boutsora ◽  
...  
Keyword(s):  
Diabetic Retinopathy ◽  
Deep Learning ◽  
Fundus Images

scholarly journals Depression patient-derived cortical neurons reveal potential biomarkers for antidepressant response

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Yishai Avior ◽  
Shiri Ron ◽  
Dana Kroitorou ◽  
Claudia Albeldas ◽  
Vitaly Lerner ◽  
...  
Keyword(s):  
Cortical Neurons ◽  
Antidepressant Treatment ◽  
Patient Specific ◽  
Specific Gene ◽  
Specific Information ◽  
Patient Response ◽  
Patient Will ◽  
Gene Expression Alterations ◽  
Treatment Alternatives

AbstractMajor depressive disorder is highly prevalent worldwide and has been affecting an increasing number of people each year. Current first line antidepressants show merely 37% remission, and physicians are forced to use a trial-and-error approach when choosing a single antidepressant out of dozens of available medications. We sought to identify a method of testing that would provide patient-specific information on whether a patient will respond to a medication using in vitro modeling. Patient-derived lymphoblastoid cell lines from the Sequenced Treatment Alternatives to Relieve Depression study were used to rapidly generate cortical neurons and screen them for bupropion effects, for which the donor patients showed remission or non-remission. We provide evidence for biomarkers specific for bupropion response, including synaptic connectivity and morphology changes as well as specific gene expression alterations. These biomarkers support the concept of personalized antidepressant treatment based on in vitro platforms and could be utilized as predictors to patient response in the clinic.

scholarly journals Simba

2021 ◽  
Vol 64 (6) ◽  
pp. 107-116
Author(s):  
Yakun Sophia Shao ◽  
Jason Cemons ◽  
Rangharajan Venkatesan ◽  
Brian Zimmer ◽  
Matthew Fojtik ◽  
...  
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
Data Locality ◽  
Coarse Grained ◽  
Batch Size ◽  
Peak Performance ◽  
Large Scale Systems ◽  
High Area ◽  
On Chip ◽  
And Storage

Package-level integration using multi-chip-modules (MCMs) is a promising approach for building large-scale systems. Compared to a large monolithic die, an MCM combines many smaller chiplets into a larger system, substantially reducing fabrication and design costs. Current MCMs typically only contain a handful of coarse-grained large chiplets due to the high area, performance, and energy overheads associated with inter-chiplet communication. This work investigates and quantifies the costs and benefits of using MCMs with finegrained chiplets for deep learning inference, an application domain with large compute and on-chip storage requirements. To evaluate the approach, we architected, implemented, fabricated, and tested Simba, a 36-chiplet prototype MCM system for deep-learning inference. Each chiplet achieves 4 TOPS peak performance, and the 36-chiplet MCM package achieves up to 128 TOPS and up to 6.1 TOPS/W. The MCM is configurable to support a flexible mapping of DNN layers to the distributed compute and storage units. To mitigate inter-chiplet communication overheads, we introduce three tiling optimizations that improve data locality. These optimizations achieve up to 16% speedup compared to the baseline layer mapping. Our evaluation shows that Simba can process 1988 images/s running ResNet-50 with a batch size of one, delivering an inference latency of 0.50 ms.

Sign in / Sign up

Export Citation Format

Share Document