{"doi":"10.1101/2020.08.06.20159152","title":"Artificial Intelligence-Based Analytics for Diagnosis of Small Bowel Enteropathies and Black Box Feature Detection","abstract":"Abstract Objectives Striking histopathological overlap between distinct but related conditions poses a significant disease diagnostic challenge. There is a major clinical need to develop computational methods enabling clinicians to translate heterogeneous biomedical images into accurate and quantitative diagnostics. This need is particularly salient with small bowel enteropathies; Environmental Enteropathy (EE) and Celiac Disease (CD). We built upon our preliminary analysis by developing an artificial intelligence (AI)-based image analysis platform utilizing deep learning convolutional neural networks (CNNs) for these enteropathies. Methods Data for secondary analysis was obtained from three primary studies at different sites. The image analysis platform for EE and CD was developed using convolutional neural networks (CNNs: ResNet and custom Shallow CNN). Gradient-weighted Class Activation Mappings (Grad-CAMs) were used to visualize the models’ decision making process. A team of medical experts simultaneously reviewed the stain color normalized images done for bias reduction and Grad-CAM visualizations to confirm structural preservation and biological relevance, respectively. Results 461 high-resolution biopsy images from 150 children were acquired. Median age (interquartile range) was 37·5 (19·0 to 121·5) months with a roughly equal sex distribution; 77 males (51·3%). ResNet50 and Shallow CNN demonstrated 98% and 96% case-detection accuracy, respectively, which increased to 98·3% with an ensemble. Grad-CAMs demonstrated models’ ability to learn distinct microscopic morphological features. Conclusion Our AI-based image analysis platform demonstrated high classification accuracy for small bowel enteropathies which was capable of identifying biologically relevant microscopic features, emulating human pathologist decision making process, performing in the case of suboptimal computational environment, and being modified for improving disease classification accuracy. Grad-CAMs that were employed illuminated the otherwise ‘black box’ of deep learning in medicine, allowing for increased physician confidence in adopting these new technologies in clinical practice. What is known Striking histopathological overlap exists between distinct but related conditions which poses a significant disease diagnostic challenge; such as for small bowel enteropathies including Environmental Enteropathy (EE) and Celiac Disease (CD). There is a major clinical need to develop computational [including Artificial Intelligence (AI) and deep learning] methods enabling clinicians to translate heterogeneous biomedical images into accurate and quantitative diagnostics. A major issue plaguing the use of AI in medicine is the so-called ‘black box’ of deep learning, an analogy which describes the lack of insight that humans have into how the models arrive at their decision-making What is new AI-based image analysis platform demonstrated high classification accuracy for small bowel enteropathies (EE vs. CD vs. histologically normal controls). Gradient-weighted Class Activation Mappings (Grad-CAMs) illuminated the otherwise ‘black box’ of deep learning in medicine, allowing for increased physician confidence in adopting these new technologies in clinical practice.","journal":"medRxiv","year":2020,"id":123930,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":3,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.955,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2020-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":258573,"name":"Lubaina Ehsan","orcid":"0000-0001-6307-2106","position":1,"is_corresponding":false},{"id":567579,"name":"Aman Shrivastava","orcid":"0000-0003-0085-4965","position":2,"is_corresponding":false},{"id":567580,"name":"Saurav Sengupta","orcid":"0000-0002-9748-0551","position":3,"is_corresponding":false},{"id":567581,"name":"Marium Khan","orcid":"0000-0003-3246-0047","position":4,"is_corresponding":false},{"id":315120,"name":"Kamran Kowsari","orcid":"0000-0002-6451-4786","position":5,"is_corresponding":false},{"id":557651,"name":"Shan Guleria","orcid":"0000-0002-1981-4317","position":6,"is_corresponding":false},{"id":315121,"name":"Rasoul Sali","orcid":"0000-0003-3995-0735","position":7,"is_corresponding":false},{"id":568130,"name":"Karan Kant","orcid":null,"position":8,"is_corresponding":false},{"id":568131,"name":"Sung‐Jun Kang","orcid":null,"position":9,"is_corresponding":false},{"id":567582,"name":"Kamran Sadiq","orcid":"0000-0001-5103-4575","position":10,"is_corresponding":false},{"id":231948,"name":"Najeeha Talat Iqbal","orcid":"0000-0003-4026-5655","position":11,"is_corresponding":false},{"id":567583,"name":"Lin Cheng","orcid":"0000-0002-3248-093X","position":12,"is_corresponding":false},{"id":567584,"name":"Christopher A. Moskaluk","orcid":"0000-0002-7049-681X","position":13,"is_corresponding":false},{"id":292863,"name":"Paul Kelly","orcid":"0000-0003-0844-6448","position":14,"is_corresponding":false},{"id":567585,"name":"Beatrice Amadi","orcid":"0000-0001-6363-2943","position":15,"is_corresponding":false},{"id":568132,"name":"Shahid Ali","orcid":null,"position":16,"is_corresponding":false},{"id":258574,"name":"Sean R. Moore","orcid":"0000-0003-1150-6632","position":17,"is_corresponding":false},{"id":315122,"name":"Donald Brown","orcid":"0000-0002-9140-2632","position":18,"is_corresponding":false},{"id":68454,"name":"Sana Syed","orcid":"0000-0003-0954-0583","position":0,"is_corresponding":true}],"reference_count":39,"raw_metadata":null,"created_at":"2026-07-18T23:15:03.403566Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}