Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
4 results
Search Results
Item Digital twins, digital triplets, and explainable AI, in precision health(IOS Press, 2024) Talukder, A.K.; Sarbadhikari, S.N.; Selg, E.; Haas, R.E.Precision health is about preventing, predicting, and treating diseases precisely with the principles of the right care at the right time for the right patient. Precision health is expected to help increase health equity in general. Digital Twins and Digital Triplets can significantly help in meeting the goals of precision health. In this chapter we present digital twins and digital triplets and their roles in realizing precision health. Digital twin is the digital representation of a physical object in the digital space. In the Precision Health context, digital twins are indeed enablers of machine learning and knowledge mining. It is also useful for the in-silico simulation of a person's phenotype (health states) and genotype (molecular states) to realize evidence-based medicine. Moreover, using probabilistic graph model and neuro- symbolic AI, digital twins will be useful in mitigating physician's knowledge gaps or decision gaps to achieve value-based care. In contrast to Digital twins, Digital triplet is the semantic intelligence about the object. Digital triplets capture the semantics by placing semantically similar objects close together in the vector embedding space. This semantic intelligence helps cognition and discover hidden and unknown knowledge and their interrelationships to make accurate clinical and medical predictions. We group digital twins in three major categories, namely, Person Phenotype Digital Twin, Person Genotype Digital Twin, and Physicians' Brain Digital Twin. Person phenotype digital twin relates to all observable properties of a person and a population. Person genotype digital twin helps understand the molecular properties of a person and a population. Physicians brain digital twin is the doctors' brain with actionable biomedical knowledge in the virtual space. © 2024 Akademische Verlagsgesellschaft AKA GmbH, Berlin. All rights reserved.Item Bridging the Inferential Gaps in Healthcare(Springer Science and Business Media Deutschland GmbH, 2021) Talukder, A.K.Inferential gaps are the combined effect of reading-to-cognition gaps as well as the knowledge-to-action gaps. Misdiagnoses, medical errors, prescription errors, surgical errors, under-treatments, over-treatments, unnecessary lab tests, etc. – are all caused by inferential gaps. Late diagnosis of cancer is also due to the inferential gaps at the primary care. Even the medical climate crisis caused by misuse, underuse, or overuse of antibiotics are the result of serious inferential gaps. Electronic health records (EHR) had some success in mitigating the wrong site, wrong side, wrong procedure, wrong person (WSWP) errors, and the general medical errors; however, these errors continue to be quite significant. In the last few decades the disease demography has changed from quick onset infectious diseases to slow onset non-communicable diseases (NCD). This changed the healthcare sector in terms of both training and practice. In 2020 the COVID-19 pandemic disrupted the entire healthcare system further with change in focus from NCD back to quick onset infectious disease. During COVID-19 pandemic misinformation in social media increased. In addition, COVID-19 made virtual healthcare a preferred mode of patient-physician encounter. Virtual healthcare requires higher level of audit, accuracy, and technology reliance. All these events in medical practice widened the inferential gaps further. In this position paper, we propose an architecture of digital health combined with artificial intelligence that can mitigate these challenges and increase patient safety in the post-COVID healthcare delivery. We propose this architecture in conjunction with diseasomics, patholomics, resistomics, oncolomics, allergomics, and drugomics machine interpretable knowledge graphs that will minimize the inferential gaps. Unless we pay our attention to this critical issue immediately, medical ecosystem crisis that includes medical errors, caregiver shortage, misinformation, and the inferential gaps will become the second, if not the first leading cause of death by 2050. © 2021, Springer Nature Switzerland AG.Item Physicians’ Brain Digital Twin: Holistic Clinical & Biomedical Knowledge Graphs for Patient Safety and Value-Based Care to Prevent the Post-pandemic Healthcare Ecosystem Crisis(Springer Science and Business Media Deutschland GmbH, 2022) Talukder, A.K.; Selg, E.; Haas, R.E.The ‘reading to cognition gaps’ and the ‘knowledge to action gaps’ for a physician or a care provider are the root causes of patient harm and the low- value healthcare. Rule-based symptom-checkers often fail when there are multiple co-occurring symptoms. To ensure patient safety and value-based care we have constructed nine AI-driven and evidence based interconnected holistic knowledge graphs covering the entire spectrum of medical knowledge starting from symptoms to therapeutics. These knowledge graphs are in fact the digital twin of all physicians’ brains. These nine knowledge graphs are Symptomatomics, Diseasomics, SNOMED CT, Disease-Gene Network, Multimorbidity, Resistomics, Patholomics, Oncolomics, and Drugomics. These knowledge graphs are constructed from semantic integration of biomedical ontologies like Disease Ontology, Symptom Ontology, Gene Ontology, Drug Ontology, NCI Thesaurus, DisGenomics Network, PharmGKB, ChEBI, WHO AWaRe, and WHOCC. This is further enhanced through thematic integration of the knowledge mined from PubMed, DailyMed, FAERS, Wikipedia and patient data (EHR) from hospitals and cancer registry. These knowledge graphs are interconnected through common vocabularies like SNOMED CT, ICD10, ICDO, UMLS, NCIT, DOID, HGNC, GO, LOINC, ATC, RXCUI, and RxNORM codes that helped us to construct a complete clinical, medical, therapeutic, and conflicting medication knowledge graph with 723,801 nodes and 10,657,694 edges. This knowledge graph is stored in a Neo4j property graph database which is deployed in the cloud accessible 24×7 through REST/JSON-RPC and AIoT API. On top of this integrated knowledge graph we used node2vec to construct digital triplet discovering many unknown and hidden knowledge. This integrated clinical & biomedical knowledge functions as the digital twin of all physicians’ brains. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.Item AN ONTOLOGY-DRIVEN BI-DIRECTIONAL WORKFLOW FOR INTEGRATING PROJECT MANAGEMENT DATA INTO THE IFC STANDARD(International Council for Research and Innovation in Building and Construction, 2025) Kone, V.; Mahesh, G.The evolution of Building Information Modelling (BIM) towards a data-centric paradigm is often hindered by challenges in semantic interoperability, particularly when integrating project management data with the Industry Foundation Classes (IFC) standard. While IFC enables syntactic data exchange, a persistent gap exists dynamically linking building geometry with the complex, relational information of project schedules, resources, and costs in a semantically consistent, interoperable manner. This paper presents a novel, bi-directional methodology that leverages Semantic Web technologies (RDF, OWL, SPARQL) to address this challenge. The core of the methodology is an ontology-driven workflow that uses two purpose-built ontologies: BIMOnto, a lightweight representation of the building asset derived from if cOWL, and IproK (Integrated Project Knowledge Ontology), which formally structures project management information across schedule, resource, and cost domains. The workflow enables both directions: (1) transforming IFC models into queryable knowledge graphs, and (2) programmatically generating new, enriched IFC models from unified knowledge graphs. This reverse transformation creates native, standards-compliant IFC entities for tasks (IfcTask), resources (IfcResource), costs (IfcCostItem), and their standard relationships (IfcRelAssignsToProduct, etc.), moving beyond custom property sets. The feasibility and effectiveness of this approach are validated through a case study using a multi-story residential building model, demonstrating the successful generation of a verifiable, integrated BIM artifact. The findings show that this ontology-driven framework significantly enhances data integration, creating truly interoperable models where process data becomes a first-class citizen within the BIM environment, advancing the potential for more intelligent, data-centric BIM practices throughout the project lifecycle. © © 2025 The author(s). This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.