5,493 Hits in 4.4 sec

A Fully Private Pipeline for Deep Learning on Electronic Health Records [article]

Edward Chou, Thao Nguyen, Josh Beal, Albert Haque, Li Fei-Fei
2018 arXiv   pre-print
We introduce an end-to-end private deep learning framework, applied to the task of predicting 30-day readmission from electronic health records.  ...  cost of encrypted operations using ideas from both machine learning and cryptography.  ...  , in order to provide a fully-private pipeline.  ... 
arXiv:1811.09951v1 fatcat:ew4i5sch4rc5dkujdydpggxwsi

Status and Direction of Healthcare Data in Korea for Artificial Intelligence

Yu Rang Park, Soo-Yong Shin
2017 Hanyang Medical Reviews  
For medical AI, a simple approach that accumulates massive amounts of data based on existing big data concepts cannot provide meaningful results in the healthcare field.  ...  Recent rapid advances in artificial intelligence (AI), especially in deep learning methods, have produced meaningful results in many areas.  ...  Many people believe there is a large amount of data in hospitals based on the wide adaptation of electronic medical records (EMR).  ... 
doi:10.7599/hmr.2017.37.2.86 fatcat:t3s66eaoivgbpfapelgeppme44


2016 Biocomputing 2017  
Although the establishment of biomedical data science as a career requires a complete career pipeline, from undergraduate training on up, the focus here is on the latter end of the pipeline, at the postdoc  ...  With the adoption of Electronic Health Record (EHR) data by hospitals, it is now feasible to access and mine the massive amount of clinical and phenotypic data.  ... 
doi:10.1142/9789813207813_0059 pmid:27897014 pmcid:PMC5425257 fatcat:h3nih6lzobe5bny5jvy4ndor7y

An interpretable deep-learning model for early prediction of sepsis in the emergency department

Dongdong Zhang, Changchang Yin, Katherine M. Hunold, Xiaoqian Jiang, Jeffrey M. Caterino, Ping Zhang
2021 Patterns  
In this paper, we report our top-performing method in the 2019 DII National Data Science Challenge to predict onset of sepsis 4 h before its diagnosis on electronic health records of over 100,000 unique  ...  Attention mechanism and global max pooling techniques are utilized to enable interpretation for the deep-learning model.  ...  Electronic health records (EHRs) are longitudinal electronic records of patients' health information.  ... 
doi:10.1016/j.patter.2020.100196 pmid:33659912 pmcid:PMC7892361 fatcat:umchy57axfhbhislrq4cftx6li

Converging blockchain and next-generation artificial intelligence technologies to decentralize and accelerate biomedical research and healthcare

Polina Mamoshina, Lucy Ojomoko, Yury Yanovich, Alex Ostrovski, Alex Botezatu, Pavel Prikhodko, Eugene Izumchenko, Alexander Aliper, Konstantin Romantsov, Alexander Zhebrak, Iraneus Obioma Ogu, Alex Zhavoronkov
2017 OncoTarget  
We also present a roadmap for a blockchain-enabled decentralized personal health data ecosystem to enable novel approaches for drug discovery, biomarker development, and preventative healthcare.  ...  The novel deep learning and transfer learning techniques are turning any data about the person into medical data transforming simple facial pictures and videos into powerful sources of data for predictive  ...  One of the major benefits of the digital healthcare system and electronic medical records is the improved access to the healthcare records both for health professionals and patients.  ... 
doi:10.18632/oncotarget.22345 pmid:29464026 pmcid:PMC5814166 fatcat:letjwuibxfd5tosha5qipuyiky

Would the Use of Artificial Intelligence in COVID-19 Patient Management Add Value to the Healthcare System?

Manuel Cossio, Ramiro E. Gilardino
2021 Frontiers in Medicine  
Dalia Dawood for her comments in the draft of this manuscript.  ...  FIGURE 1 | 1 General data pipeline for COVID-19 AI applications. Source: own ellaboration. References XR, x-rays; CT, computed tomography; US, ultrasound; EHR, electroninc health records.  ...  This piece aims to reflect on the value of AI during the COVID-19 pandemic, using the case of developments in medical imaging and electronic health data management.  ... 
doi:10.3389/fmed.2021.619202 pmid:33585525 pmcid:PMC7873524 fatcat:l7zoxvijb5eyvi3weehlwhdtau

Machine Learning for Clinical Outcome Prediction

Farah Shamout, Tingting Zhu, David A. Clifton
2020 IEEE Reviews in Biomedical Engineering  
health records.We also discuss limitations of prominent modeling assumptions and highlight opportunities for future research.  ...  Numerous machine learning applications have appeared in the latest clinical literature, especially for outcome prediction models, with outcomes ranging from mortality and cardiac arrest to acute kidney  ...  Here, we focus on data extracted from electronic health records (EHR), which are being increasingly deployed in hospitals worldwide.  ... 
doi:10.1109/rbme.2020.3007816 pmid:32746368 fatcat:6gqdnhefibcrhglz3kx4s3foeu

Secure and Provenance Enhanced Internet of Health Things Framework: A Blockchain Managed Federated Learning Approach

Md. Abdur Rahman, M. Shamim Hossain, M. Saiful Islam, Nabil A. Alrajeh, Ghulam Muhammad
2020 IEEE Access  
ACKNOWLEDGMENT The authors extend their appreciation to the Deputyship for Research & Innovation, "Ministry of Education "in Saudi  ...  FL allows multiple private nodes containing private IoHT data to use a secure deep learning model and to retrain on local data to produce a custom model.  ...  Hence, the owner of the IoHT data, the hospital authority that co-owns the electronic health and medical records, and the governments that provide citizen's healthcare services need security and privacy  ... 
doi:10.1109/access.2020.3037474 fatcat:6il44yktnjd4pak2y2rzlnvjdm

Deep learning for healthcare: review, opportunities and challenges

Riccardo Miotto, Fei Wang, Shuang Wang, Xiaoqian Jiang, Joel T. Dudley
2017 Briefings in Bioinformatics  
Based on the analyzed work, we suggest that deep learning approaches could be the vehicle for translating big biomedical data into improved human health.  ...  In this article, we review the recent literature on applying deep learning technologies to advance the health care domain.  ...  , including variability in molecular traits, environment, electronic health records (EHRs) and lifestyle [1] [2] [3] .  ... 
doi:10.1093/bib/bbx044 pmid:28481991 fatcat:oefjv547ivazzoal3qc77d7ti4

Privacy-Preserving Collective Learning with Homomorphic Encryption

Jestine Paul, Meenatchi Sundaram Muthu Selva Annamalai, William Ming, Ahmad Al Badawi, Bharadwaj Veeravalli, Khin Mi Mi Aung
2021 IEEE Access  
We evaluate our protocol on a benchmark LSTM network trained on the Medical Information Mart for Intensive Care (MIMIC-III) dataset.  ...  Deep learning models such as long short-term memory (LSTM) are valuable classifiers for time series data like hourly clinical statistics.  ...  It combines HE and deep learning for secure collective training of the private time series ICU data.  ... 
doi:10.1109/access.2021.3114581 fatcat:nfe3whxzyje67a7zjum2ujizha

Privacy-Preserving Machine Learning: Methods, Challenges and Directions [article]

Runhua Xu, Nathalie Baracaldo, James Joshi
2021 arXiv   pre-print
Machine learning (ML) is increasingly being adopted in a wide variety of application domains.  ...  Usually, a well-performing ML model relies on a large volume of training data and high-powered computational resources.  ...  To tackle the increasing privacy concerns related to using ML in applications, in which users' privacy-sensitive data such as electronic health/medical records, location information, etc., are stored and  ... 
arXiv:2108.04417v2 fatcat:pmxmsbs2gvh6nd4jadcz4dnsrq

Interpretable Multi-Task Deep Neural Networks for Dynamic Predictions of Postoperative Complications [article]

Benjamin Shickel, Tyler J. Loftus, Shounak Datta, Tezcan Ozrazgat-Baslanti, Azra Bihorac, Parisa Rashidi
2020 arXiv   pre-print
A single multi-task deep learning model yielded greater performance than separate models trained on individual complications.  ...  Predictive performance was strongest when leveraging the full spectrum of preoperative and intraoperative physiologic time-series electronic health record data.  ...  Participants We excluded patients with intraoperative mortality or incomplete electronic health records.  ... 
arXiv:2004.12551v1 fatcat:2uhbiypihvaljetx4oatcrszle

Deep Representation Learning of Patient Data from Electronic Health Records (EHR): A Systematic Review [article]

Yuqi Si, Jingcheng Du, Zhao Li, Xiaoqian Jiang, Timothy Miller, Fei Wang, W. Jim Zheng, Kirk Roberts
2020 arXiv   pre-print
Patient representation learning refers to learning a dense mathematical representation of a patient that encodes meaningful information from Electronic Health Records (EHRs).  ...  After screening 363 articles, 49 papers were included for a comprehensive data collection.  ...  DL: Deep Learning. EHR: Electronic Health Records.  ... 
arXiv:2010.02809v2 fatcat:rtl2mqq2fzec3cusp4wo635qvm

The Role of Artificial Intelligence in Early Cancer Diagnosis

Benjamin Hunter, Sumeet Hindocha, Richard W. Lee
2022 Cancers  
Many data types are suitable for computational analysis, including electronic healthcare records, diagnostic images, pathology slides and peripheral blood, and we provide examples of how these data can  ...  Improving the proportion of patients diagnosed with early-stage cancer is a key priority of the World Health Organisation.  ...  Acknowledgments: The authors would like to thank Stan Kaye for his invaluable support and feedback on this manuscript. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/cancers14061524 pmid:35326674 pmcid:PMC8946688 fatcat:bzcgndsievgzhajxh2sumudlqe

Precision Health Data: Requirements, Challenges and Existing Techniques for Data Security and Privacy [article]

Chandra Thapa, Seyit Camtepe
2020 arXiv   pre-print
It extensively uses sensing technologies (e.g., electronic health monitoring devices), computations (e.g., machine learning), and communication (e.g., interaction between the health data centers).  ...  Secondly, this paper investigates secure and privacy-preserving machine learning methods suitable for the computation of precision health data along with their usage in relevant health projects.  ...  The algorithms were tested on a Type-2 diabetic electronic health record dataset and showed that the ensemble learning over distributed datasets is better than the learning on each dataset separately  ... 
arXiv:2008.10733v1 fatcat:oj2neoftf5hcbpatnfn7ntyhzy
« Previous Showing results 1 — 15 out of 5,493 results