555 Hits in 17.3 sec

Opening the black box: Personalizing type 2 diabetes patients based on their latent phenotype and temporal associated complication rules

Leila Yousefi, Stephen Swift, Mahir Arzoky, Lucia Saachi, Luca Chiovato, Allan Tucker
2020 Computational intelligence  
Our extensive findings show how uncovering the latent phenotype aids in distinguishing the disparities among subgroups of patients based on their complications patterns.  ...  We further extend this idea by using a combination of temporal association rule mining and unsupervised learning in order to find explainable subgroups of patients with more personalized prediction.  ...  based on their latent phenotype.  ... 
doi:10.1111/coin.12313 fatcat:t42aoje46nfqvfwtqo4rdcwmwu

Predicting Type 2 Diabetes Complications and Personalising Patient Using Artificial Intelligence Methodology [chapter]

Leila Yousefi, Allan Tucker
2020 Type 2 Diabetes [Working Title]  
These phenotypes are explained further using Bayesian network analysis methods and temporal association rules. Overall, this chapter discussed the earlier research of the chapter's author.  ...  This is often patient-specific and will depend on what type of cohort a patient belongs to.  ...  Acknowledgements I thank the following individuals for their expertise and assistance throughout all aspects of this study and for their insightful suggestions and careful reading of the manuscript.  ... 
doi:10.5772/intechopen.94228 fatcat:dkhosuu5xbhuxp4sszjpcvpmga

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.  ...  There are lots of challenges on both steps in a scenario of complicated data and lacking of sufficient domain knowledge.  ...  As an example, in the EHRs, a patient diagnosed with 'type 2 diabetes mellitus' can be identified by laboratory values of hemoglobin A1C >7.0, presence of 250.00 ICD-9 code, 'type 2 diabetes mellitus'  ... 
doi:10.1093/bib/bbx044 pmid:28481991 fatcat:oefjv547ivazzoal3qc77d7ti4

31st Meeting of the European Association for the Study of Diabetes Eye Complications Study Group (EASDec) Odense, Denmark, 28th – 30th October 2021

2021 European Journal of Ophthalmology  
We carried out a detailed characterization of a 31st Meeting of the European Association for the Study of Diabetes Eye Complications Study Group (EASDec)  ...  The complexity of retinal structure reflects on the difficulty to describe its composite cell interactions and the pathways involved.  ...  The importance of providing interpretable AI-based predictions to open the "black box" and increase trust and clinical usability. 5.  ... 
doi:10.1177/11206721211047031 fatcat:hqnucoxjp5f2xmnmku54nnixme

DeepHealth: Review and challenges of artificial intelligence in health informatics [article]

Gloria Hyunjung Kwak, Pan Hui
2020 arXiv   pre-print
It can help clinicians diagnose disease, identify drug effects for each patient, understand the relationship between genotypes and phenotypes, explore new phenotypes or treatment recommendations, and predict  ...  This article presents a comprehensive review of research applying artificial intelligence in health informatics, focusing on the last seven years in the fields of medical imaging, electronic health records  ...  Obesity has been identified as one of the growing epidemic health problems and has been linked to many chronic diseases such as type 2 diabetes and cardiovascular disease.  ... 
arXiv:1909.00384v2 fatcat:sy7pm2c2uvdd3pal2russn4xri

Neuro-Symbolic Learning: Principles and Applications in Ophthalmology [article]

Muhammad Hassan, Haifei Guan, Aikaterini Melliou, Yuqi Wang, Qianhui Sun, Sen Zeng, Wen Liang, Yiwei Zhang, Ziheng Zhang, Qiuyue Hu, Yang Liu, Shunkai Shi (+15 others)
2022 arXiv   pre-print
This review presents a comprehensive survey on the state-of-the-art NeSyL approaches, their principles, advances in machine and deep learning algorithms, applications such as opthalmology, and most importantly  ...  Attempts have been made to overcome the challenges in neural network computing by representing and embedding domain knowledge in terms of symbolic representations.  ...  The proposed model is based on NeSyL which address the hindrance of machine learning in terms of black-box representation.  ... 
arXiv:2208.00374v1 fatcat:pktmnomj3bbwpjyj7lmu37rl7i

Deep learning in systems medicine

Haiying Wang, Estelle Pujos-Guillot, Blandine Comte, Joao Luis de Miranda, Vojtech Spiwok, Ivan Chorbev, Filippo Castiglione, Paolo Tieri, Steven Watterson, Roisin McAllister, Tiago de Melo Malaquias, Massimiliano Zanin (+2 others)
2020 Briefings in Bioinformatics  
We used some prototypical examples to highlight the relevance and significance of the adoption of DL in SM, one of them is involving the creation of a model for personalized Parkinson's disease.  ...  It discusses how DL can be applied to SM with an emphasis on the applications to predictive, preventive and precision medicine.  ...  Hazard ratios among people with type 2 diabetes, compared with those without it, were around 1.9 [50] .  ... 
doi:10.1093/bib/bbaa237 pmid:33197934 pmcid:PMC8382976 fatcat:bjhlu5jaubci3lm4j3vxiofehu

Machine Learning and Decision Support in Critical Care

Alistair E. W. Johnson, Mohammad M. Ghassemi, Shamim Nemati, Katherine E. Niehaus, David Clifton, Gari D. Clifford
2016 Proceedings of the IEEE  
This paper discusses the issues of compartmentalization, corruption, and complexity involved in collection and preprocessing of critical care data.  ...  DBNs have the desirable property that they allow for interpretation of the interactions between different variables, which is not the case for "black box" methods such as SVMs and the traditional ANNs.  ...  Both detectors are run simultaneously on the ECG signals, the first one being based on the detection of the ECG peak's energy [50] , [51] and the second being based on the length transform [52] .  ... 
doi:10.1109/jproc.2015.2501978 pmid:27765959 pmcid:PMC5066876 fatcat:7i6wi65qgjbapjjznk2nioz32y

Neural Natural Language Processing for Unstructured Data in Electronic Health Records: a Review [article]

Irene Li, Jessica Pan, Jeremy Goldwasser, Neha Verma, Wai Pan Wong, Muhammed Yavuz Nuzumlalı, Benjamin Rosand, Yixin Li, Matthew Zhang, David Chang, R. Andrew Taylor, Harlan M. Krumholz (+1 others)
2021 arXiv   pre-print
Recently, however, newer neural network and deep learning approaches to Natural Language Processing (NLP) have made considerable advances, outperforming traditional statistical and rule-based systems on  ...  We focus on a broad scope of tasks, namely, classification and prediction, word embeddings, extraction, generation, and other topics such as question answering, phenotyping, knowledge graphs, medical dialogue  ...  However, in many fields, they are often treated as black boxes [230, 273] .  ... 
arXiv:2107.02975v1 fatcat:nayhw7gadfdzrovycdkvzy75pi

RetainVis: Visual Analytics with Interpretable and Interactive Recurrent Neural Networks on Electronic Medical Records

Bum Chul Kwon, Min-Je Choi, Joanne Taery Kim, Edward Choi, Young Bin Kim, Soonwook Kwon, Jimeng Sun, Jaegul Choo
2018 IEEE Transactions on Visualization and Computer Graphics  
Such black-box nature of RNNs can impede its wide adoption in clinical practice.  ...  events, in order to predict the current and future states of patients.  ...  The Sasang typology is a traditional Korean personalized medicine, which aims to cluster patients into four groups based on patient's phenotypic characteristics [5] .  ... 
doi:10.1109/tvcg.2018.2865027 pmid:30136973 fatcat:cl7zr7muhncfvpxqaxkh23pdhi

Predictive Modeling of Hospital Readmission: Challenges and Solutions [article]

Shuwen Wang, Xingquan Zhu
2021 arXiv   pre-print
2) data imbalance, locality and privacy; (3) model interpretability; and (4) model implementation.  ...  Hospital readmission prediction is a study to learn models from historical medical data to predict probability of a patient returning to hospital in a certain period, 30 or 90 days, after the discharge  ...  In general, eleven popular predictive model types are considered such as clinical rule based method, case-based reasoning, regression based method and deep learning methods.  ... 
arXiv:2106.08488v1 fatcat:g5hk5feahrgjfkixu4ep2qdlbq

Study of Plasmid-Mediated Extended-Spectrum β-Lactamase-Producing Strains of Enterobacteriaceae, Isolated from Diabetic Foot Infections in a North Indian Tertiary-Care Hospital

Mohammad Zubair, Abida Malik, Jamal Ahmad
2012 Diabetes Technology & Therapeutics  
size >4cm 2 (O.R. 3.30) but not with patients characteristic, type of diabetes and type of diabetes, or duration of hospital stay.  ...  Among the diabetic foot patients, 73.6% were males and 15% were females. 77.1% had T2DM whereas only 24.4% patients had T1DM.  ...  Idrees Mubarak, Senior Resident, Center for Diabetes and Endocrinology, for clinical evaluation of DFU patients. The authors would also like to thank Dr.  ... 
doi:10.1089/dia.2011.0197 pmid:22225456 fatcat:lvm52fx5u5flvkvv7o5wjyzehi

Towards deep phenotyping pregnancy: a systematic review on artificial intelligence and machine learning methods to improve pregnancy outcomes

Lena Davidson, Mary Regina Boland
2021 Briefings in Bioinformatics  
Future research should focus on less-studied pregnancy domain areas, including postnatal and postpartum care (n = 2).  ...  The purpose of this study is to systematically review the ways that artificial intelligence (AI) and machine learning (ML), including deep learning (DL), methodologies can inform patient care during pregnancy  ...  method Zhang and SVM, NLP Demner-Fushman (2017) Klein et al. (2018) NLP, rule-based, boot-strapping Table 2 . 2 ML methods and their applications to the pregnancy domain ML techniques Table 2 . 2  ... 
doi:10.1093/bib/bbaa369 pmid:33406530 pmcid:PMC8424395 fatcat:rgsf4pdmbvdcdmcwz4zf3hwaca

The Revival of the Notes Field: Leveraging the Unstructured Content in Electronic Health Records

Michela Assale, Linda Greta Dui, Andrea Cina, Andrea Seveso, Federico Cabitza
2019 Frontiers in Medicine  
In particular, we focused on four selected application domains, namely: data quality, information extraction, sentiment analysis and predictive models, and automated patient cohort selection.  ...  Aim: Our aim is to demonstrate the potential of the above techniques, but also raise awareness of the still open challenges that the scientific communities of IT and medical practitioners must jointly  ...  Pedro Berjano, and Dr. Michele Ulivi for their advice in regard to the medical aspects of our research.  ... 
doi:10.3389/fmed.2019.00066 pmid:31058150 pmcid:PMC6478793 fatcat:6koblecrsnbabld6y6qwukwxgy

Informatics for Health 2017: Advancing both science and practice

Philip J. Scott, Ronald Cornet, Colin McCowan, Niels Peek, Paolo Fraccaro, Nophar Geifman, Wouter T. Gude, William Hulme, Glen P. Martin, Richard Williams
2017 Journal of Innovation in Health Informatics  
The goal is multi-level Learning Health Systems that consume and intelligently act upon both patient data and organizational intervention outcomes.Conclusions: Informatics for Health demonstrated the art  ...  of the possible, seen in the breadth and depth of our contributions.  ...  generalization (five versions)), for the categorization of patients according to their diabetic status (diabetics, not diabetics and inconclusive Diabetes of any type) using information extracted from  ... 
doi:10.14236/jhi.v24i1.939 pmid:28665785 fatcat:fj7cg7o6h5c3hnd5x7b2cfo2te
« Previous Showing results 1 — 15 out of 555 results