2,028 Hits in 6.1 sec

Doctor AI: Predicting Clinical Events via Recurrent Neural Networks [article]

Edward Choi and Mohammad Taha Bahadori and Andy Schuetz and Walter F. Stewart and Jimeng Sun
2016 arXiv   pre-print
Doctor AI is a temporal model using recurrent neural networks (RNN) and was developed and applied to longitudinal time stamped EHR data from 260K patients over 8 years.  ...  Doctor AI assesses the history of patients to make multilabel predictions (one label for each diagnosis or medication category).  ...  Doctor AI is a temporal model using recurrent neural networks (RNN) and was developed and applied to longitudinal time stamped EHR data.  ... 
arXiv:1511.05942v11 fatcat:xh6rbsli2fhd7lvqepebrw7swi

Doctor AI: Predicting Clinical Events via Recurrent Neural Networks

Edward Choi, Mohammad Taha Bahadori, Andy Schuetz, Walter F Stewart, Jimeng Sun
2016 Journal of machine learning research workshop and conference proceedings  
Doctor AI is a temporal model using recurrent neural networks (RNN) and was developed and applied to longitudinal time stamped EHR data from 260K patients over 8 years.  ...  Doctor AI assesses the history of patients to make multilabel predictions (one label for each diagnosis or medication category).  ...  Doctor AI is a temporal model using recurrent neural networks (RNN) and was developed and applied to longitudinal time stamped EHR data.  ... 
pmid:28286600 pmcid:PMC5341604 fatcat:eemrqe36bfddbbn6art33bvwcm

Medi-Care AI: Predicting Medications From Billing Codes via Robust Recurrent Neural Networks [article]

Deyin Liu, Lin Wu, Xue Li
2019 arXiv   pre-print
In this paper, we present an effective deep prediction framework based on robust recurrent neural networks (RNNs) to predict the likely therapeutic classes of medications a patient is taking, given a sequence  ...  We present a general robust framework that explicitly models the possible contamination through overtime decay mechanism on the input billing codes and noise injection into the recurrent hidden states,  ...  Robust Recurrent Neural Networks for Medication Predictions In this section, we develop a new framework for clinical medication predictions in the context of missing information and multiple errors.  ... 
arXiv:2001.10065v1 fatcat:py6eteeyvvdibllyk2rufk5iqm

When AIs Outperform Doctors: The Dangers of a Tort-Induced Over-Reliance on Machine Learning and What (Not) to Do About it

A. Michael Froomkin, Ian R. Kerr, Joelle Pineau
2018 Social Science Research Network  
This Article argues that once ML diagnosticians, such as those based on neural networks, are shown to be superior, existing medical malpractice law will require superior ML-generated medical diagnostics  ...  as the standard of care in clinical settings.  ...  See Anh Nguyen, Jason Yosinski & Jeff Clune, Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images, 4 IEEE COMP.  ... 
doi:10.2139/ssrn.3114347 fatcat:bdfdf6q7k5g4xeklo6r4ufniye

AI Techniques for COVID-19

Adedoyin A. Hussain, Ouns Bouachir, Fadi Al-Turjman, Moayad Aloqaily
2020 IEEE Access  
We classify the existing AI techniques in clinical data analysis, including neural systems, classical SVM, and edge significant learning.  ...  Motivated by the need to highlight the need for employing AI in battling the COVID-19 Crisis, this survey summarizes the current state of AI applications in clinical administrations while battling COVID  ...  Utilizing it in clinical implementation, the generally applied deep learning calculations implement CNN known as convolution neural network, also neural intermittent system, also the deep neural system  ... 
doi:10.1109/access.2020.3007939 pmid:34976554 pmcid:PMC8545328 fatcat:h7v76znrhnerdiw46lt23qbaai

Smart Entry System using IoT and AI

Dr.P.Aravind, D.Benitorichardson, G.K.Dharsan Prabu, R.Lokesh, R.Akilan
2022 Zenodo  
Hence here comes the need for artificial intelligence (AI), which is the main theme of our project.  ...  This theme consists of social distancing noticing and face mask detection for the events of disease like novel coronavirus can be solved by maintaining social distancing as well as wearing/putting on its  ...  Deep-learning architectures such as deep neural networks, deep belief networks, recurrent neural networks and convolutional neural networks have been applied to fields including computer vision, machine  ... 
doi:10.5281/zenodo.6632645 fatcat:7sixfvs3kzhxpaopmjwgcnxws4

Big Data Analytics and AI in Mental Healthcare [article]

Ariel Rosenfeld, David Benrimoh, Caitrin Armstrong, Nykan Mirchi, Timothe Langlois-Therrien, Colleen Rollins, Myriam Tanguay-Sela, Joseph Mehltretter, Robert Fratila, Sonia Israel, Emily Snook, Kelly Perlman, Akiva Kleinerman (+4 others)
2019 arXiv   pre-print
and helping to prevent mental health conditions before they reach clinical-level symptomatology, and even delivering some treatments.  ...  In this chapter we discuss the major opportunities, limitations and techniques used for improving mental healthcare through AI and big-data.  ...  The system, known as Aifred, offers a neural network model that allows for differential prediction between the four different antidepressant drug categories.  ... 
arXiv:1903.12071v1 fatcat:lxzhoy76qjaahezvq3344udn2q

AI-based Approach for Safety Signals Detection from Social Networks: Application to the Levothyrox Scandal in 2017 on Doctissimo Forum [article]

Valentin Roche, Jean-Philippe Robert, Hanan Salam
2022 arXiv   pre-print
Various approaches have investigated the analysis of social media data using AI such as NLP techniques for detecting adverse drug events.  ...  Network (WC-CNN) which trains a CNN on word clouds extracted from the patients comments.  ...  Among the used architectures, we can find Recurrent Neural Network (RNN) [15] approaches. For instance, the RNN-based approach of [15] labels words in an input sequence with ADR membership tags.  ... 
arXiv:2203.03538v1 fatcat:guji5cqfy5b6jb2m4k4tv3ixtu

Explainable AI (XAI): Core Ideas, Techniques and Solutions

Rudresh Dwivedi, Devam Dave, Het Naik, Smiti Singhal, Omer Rana, Pankesh Patel, Bin Qian, Zhenyu Wen, Tejal Shah, Graham Morgan, Rajiv Ranjan
2022 ACM Computing Surveys  
In addition, the ability to explain the model generally is now the gold standard for building trust and deployment of Artificial Intelligence (AI) systems in critical domains.  ...  These post-hoc explanation schemes are being used for both single/ multilayer Neural Networks, Convolutional Neural Networks and Recurrent Neural Networks.  ...  Consider a neural network model trained for clinical prediction of Streptococcus pyogenes infection in patients.  ... 
doi:10.1145/3561048 fatcat:zmzo3gl6u5cpnnug4sydfeduc4

End-to-End AI-Based Point-of-Care Diagnosis System for Classifying Respiratory Illnesses and Early Detection of COVID-19 [article]

Abdelkader Nasreddine Belkacem, Sofia Ouhbi, Abderrahmane Lakas, Elhadj Benkhelifa, Chao Chen
2020 arXiv   pre-print
The most common of neural networks for deep learning include: Deep Neural Network (DNN), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and Fuzzy Deep Neural Network FDNN). B.  ...  Recurrent Neural Network RNNs allow cyclical connections in a feed-forward neural networks, which allows them to incorporate contextual information from previous input, and remember past inputs in the  ... 
arXiv:2006.15469v1 fatcat:3nxkfrrvafdnrlkxzvov6jjlei

From Blackbox to Explainable AI in Healthcare: Existing Tools and Case Studies

Parvathaneni Naga Srinivasu, N. Sandhya, Rutvij H. Jhaveri, Roshani Raut, Saqib Hakak
2022 Mobile Information Systems  
The role of XAI in the healthcare domain ranging from the earlier prediction of future illness to the disease's smart diagnosis is discussed.  ...  Artificial intelligence (AI) models have been employed to automate decision-making, from commerce to more critical fields directly affecting human lives, including healthcare.  ...  A neural network interpretability approach for NLP neural networks has been presented. is method attempts to provide prediction outcomes as the actual input by extracting smaller, customized parts of the  ... 
doi:10.1155/2022/8167821 fatcat:mwylmanbyfceldffi4szlyze3u

Foundations for Meaning and Understanding in Human-centric AI [article]

Steels, Luc (ed.)
2022 Zenodo  
We call this kind of AI meaningful AI in contrast to AI that rests exclusively on the use of statistically acquired pattern recognition and pattern completion.  ...  A short conclusion identifying key research topics for meaning-based human-centric AI.  ...  We call AI systems that emulate reactive intelligence reactive AI. Reactive AI is not the exclusive province of neural networks.  ... 
doi:10.5281/zenodo.6666819 fatcat:ia3wwkrfrrcmhfpxobqxvwtesi

The Third AI Summer: AAAI Robert S. Engelmore Memorial Lecture

Henry Kautz
2022 The AI Magazine  
It explores recurring themes in the history of AI, real and imagined dangers from AI, and the future of the field.  ...  Thirty years later, a groundbreaking paper he coauthored in Nature showed that spikes in neural activity could be used to predictive motor events a full halfsecond before the subject was consciously aware  ...  We shall see the potent combination of artificial neural networks and reinforcement learning reemerge in the third AI summer.  ... 
doi:10.1609/aimag.v43i1.19122 fatcat:vrymeyxjdbhr3etnvdegqxjypa

Deep Learning Application Pros And Cons Over Algorithm

Ata Jahangir Moshayedi, Atanu Shuvam Roy, Amin Kolahdooz, Yang Shuxin
2022 EAI Endorsed Transactions on AI and Robotics  
Deep Patient: unsupervised patient representatives who can be used to predict future clinical events Stacked Denoising AE [73] Predict future diseases from the patient's clinical status Stacked Denoising  ...  named CNNs, recurrent neural networks (RNNS), generative adversarial networks (GAN) and reinforcement learning (RL).  ... 
doi:10.4108/airo.v1i.19 fatcat:wmfb5cjayngmzdrv6git4o3pce

Unbox the black-box for the medical explainable AI via multi-modal and multi-centre data fusion: A mini-review, two showcases and beyond

Guang Yang, Qinghao Ye, Jun Xia
2021 Information Fusion  
This is particularly true of the most popular deep neural network approaches currently in use.  ...  The insufficient explainability and transparency in most existing AI systems can be one of the major reasons that successful implementation and integration of AI tools into routine clinical practice are  ...  CNN: Convolutional Neural Network; RNN: Recurrent Neural Network; and GAN: Generative Adversarial Network.  ... 
doi:10.1016/j.inffus.2021.07.016 pmid:34980946 pmcid:PMC8459787 fatcat:3rmzvn72dbgglcddgolce2xsfe
« Previous Showing results 1 — 15 out of 2,028 results