M
Mohammed Khalilia
Researcher at Amazon.com
Publications - 26
Citations - 995
Mohammed Khalilia is an academic researcher from Amazon.com. The author has contributed to research in topics: Named-entity recognition & Fuzzy logic. The author has an hindex of 11, co-authored 24 publications receiving 711 citations. Previous affiliations of Mohammed Khalilia include Georgia Institute of Technology & University of Missouri.
Papers
More filters
Journal ArticleDOI
Predicting disease risks from highly imbalanced data using random forest
TL;DR: Overall, the RF ensemble learning method outperformed SVM, bagging and boosting in terms of the area under the receiver operating characteristic (ROC) curve (AUC), and has the advantage of computing the importance of each variable in the classification process.
Journal ArticleDOI
The Digital Slide Archive: A Software Platform for Management, Integration, and Analysis of Histology for Cancer Research.
David A. Gutman,Mohammed Khalilia,Sanghoon Lee,Michael Nalisnik,Zach Mullen,Jonathan D. Beezley,Deepak Roy Chittajallu,David E. Manthey,Lee Cooper +8 more
TL;DR: The Digital Slide Archive (DSA) is described, an open-source web-based platform for digital pathology that allows investigators to manage large collections of histologic images and integrate them with clinical and genomic metadata.
Posted Content
Improving Hospital Mortality Prediction with Medical Named Entities and Multimodal Learning
Mengqi Jin,Mohammad Taha Bahadori,Aaron Colak,Parminder Bhatia,Busra Celikkaya,Ram Bhakta,Selvan Senthivel,Mohammed Khalilia,Daniel Navarro,Borui Zhang,Tiberiu Doman,Arun Ravi,Matthieu Liger,Taha A. Kass-Hout +13 more
TL;DR: This study uses an internal medical natural language processing service to perform named entity extraction and negation detection on clinical notes and compose selected entities into a new text corpus to train document representations, and proposes a multimodal neural network to jointly train time series signals and unstructured clinical text representations.
Proceedings ArticleDOI
Comprehend Medical: A Named Entity Recognition and Relationship Extraction Web Service
TL;DR: Comprehend Medical as discussed by the authors is a stateless and Health Insurance Portability and Accountability Act (HIPAA) eligible Named Entity Recognition (NER) and Relationship Extraction (RE) service launched under Amazon Web Services (AWS) trained using state-of-the-art deep learning models.
Journal ArticleDOI
Improvements to the relational fuzzy c-means clustering algorithm
TL;DR: This article compares five methods for Euclideanizing D to D and concludes that the subdominant ultrametric transformation is a clear winner, producing much better partitions of D ˜ than the other four methods.