AI, Security for Digital Health

A special issue of Algorithms (ISSN 1999-4893). This special issue belongs to the section "Algorithms for Multidisciplinary Applications".

Deadline for manuscript submissions: closed (30 April 2023) | Viewed by 2527

Special Issue Editors


E-Mail Website
Guest Editor
Artificial Intelligence & Digital Health Data Science, School of Health and Rehabilitation Sciences, The University of Queensland, Brisbane, QLD 4072, Australia
Interests: statistical models; machine learning; deep learning; medical images; neuroimaging; bioinformatics
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
InfoSec Discipline, School of Computer Science, Queensland University of Technology, Brisbane, QLD 4001, Australia
Interests: digital health; cybersecurity; internet of things; intelligent transportation & road safety; blockchain & application; artificial intelligence; biomedicals

Special Issue Information

Dear Colleagues,

Recent advances in artificial intelligence (AI) have resulted in significant improvement in digital healthcare systems, which are capable of automated diagnosis and identifying the prognosis of complex diseases. Much of the research work to improve digital healthcare systems involves interdisciplinary research including artificial intelligence, medical image processing, data mining, health informatics, data science, machine/deep learning-based algorithms, models and software tool developments and applications. Most of these technologies and models rely on the big data collected from patients, including medical signals (EEG, ECG) and imaging (MRI, fMRI), as well as data from sensor and electronic health records (HER). Since AI technology and algorithms rely heavily on collecting large amounts of data to train models, security and patient privacy concerns remain a key concern in the healthcare sector when it comes to AI.

In the last decade, there has been a surge in interest in information security. Cyber attacks in the manufacturing and consumer industries, including supply chains, have been extensively reported, and current cyber attacks in the healthcare sector are alarming. There is evidence of increasingly sophisticated attacks, but there is also evidence that the application of disruptive technologies such as AI, blockchain, and refined modelling can help.

In this Special Issue, we aim to highlight new theories and applications of artificial intelligence in digital healthcare, as well as research on digital health security. Research, review and survey articles on the following topics are encouraged for submission: 

  • Artificial intelligence;
  • Computer vision;
  • Machine learning;
  • Deep learning;
  • MRI/fMRI imaging;
  • EEG/ECG;
  • Medical image analysis;
  • Digital health;
  • Health informatics;
  • Clinical informatics
  • Data mining;
  • Text mining;
  • Natural language processing;
  • Bioinformatics;
  • Systems biology;
  • Computational biology;
  • Data science;
  • AI-based automated decision-making systems;
  • Cyber-security;
  • Digital Security;
  • Privacy and the security of health data;
  • Blockchain and trust;
  • Cyber resilience;
  • Cyber security in healthcare;
  • Policy and guidelines of security;
  • Holistic cyber security approaches

Dr. Mohammad Ali Moni
Dr. Khondokar Fida Hasan
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Algorithms is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

25 pages, 2313 KiB  
Article
Heterogeneous Treatment Effect with Trained Kernels of the Nadaraya–Watson Regression
by Andrei Konstantinov, Stanislav Kirpichenko and Lev Utkin
Algorithms 2023, 16(5), 226; https://doi.org/10.3390/a16050226 - 27 Apr 2023
Cited by 1 | Viewed by 1577
Abstract
A new method for estimating the conditional average treatment effect is proposed in this paper. It is called TNW-CATE (the Trainable Nadaraya–Watson regression for CATE) and based on the assumption that the number of controls is rather large and the number of treatments [...] Read more.
A new method for estimating the conditional average treatment effect is proposed in this paper. It is called TNW-CATE (the Trainable Nadaraya–Watson regression for CATE) and based on the assumption that the number of controls is rather large and the number of treatments is small. TNW-CATE uses the Nadaraya–Watson regression for predicting outcomes of patients from control and treatment groups. The main idea behind TNW-CATE is to train kernels of the Nadaraya–Watson regression by using a weight sharing neural network of a specific form. The network is trained on controls, and it replaces standard kernels with a set of neural subnetworks with shared parameters such that every subnetwork implements the trainable kernel, but the whole network implements the Nadaraya–Watson estimator. The network memorizes how the feature vectors are located in the feature space. The proposed approach is similar to transfer learning when domains of source and target data are similar, but the tasks are different. Various numerical simulation experiments illustrate TNW-CATE and compare it with the well-known T-learner, S-learner, and X-learner for several types of control and treatment outcome functions. The code of proposed algorithms implementing TNW-CATE is publicly available. Full article
(This article belongs to the Special Issue AI, Security for Digital Health)
Show Figures

Figure 1

Back to TopTop