scholarly journals Generative transfer learning for measuring plausibility of EHR diagnosis records

2020 ◽  
Author(s):  
Hossein Estiri ◽  
Sebastien Vasey ◽  
Shawn N Murphy
Keyword(s):  
Transfer Learning ◽  
Generative Models ◽  
Computational Approach ◽  
Specific Knowledge ◽  
Health Records ◽  
Domain Specific ◽  
Applied Machine Learning ◽  
Domain Specific Knowledge ◽  
Small Set ◽  
Joint Probabilities

Abstract Objective Due to a complex set of processes involved with the recording of health information in the Electronic Health Records (EHRs), the truthfulness of EHR diagnosis records is questionable. We present a computational approach to estimate the probability that a single diagnosis record in the EHR reflects the true disease. Materials and Methods Using EHR data on 18 diseases from the Mass General Brigham (MGB) Biobank, we develop generative classifiers on a small set of disease-agnostic features from EHRs that aim to represent Patients, pRoviders, and their Interactions within the healthcare SysteM (PRISM features). Results We demonstrate that PRISM features and the generative PRISM classifiers are potent for estimating disease probabilities and exhibit generalizable and transferable distributional characteristics across diseases and patient populations. The joint probabilities we learn about diseases through the PRISM features via PRISM generative models are transferable and generalizable to multiple diseases. Discussion The Generative Transfer Learning (GTL) approach with PRISM classifiers enables the scalable validation of computable phenotypes in EHRs without the need for domain-specific knowledge about specific disease processes. Conclusion Probabilities computed from the generative PRISM classifier can enhance and accelerate applied Machine Learning research and discoveries with EHR data.

‘I’m an expert in me and I know what I can cope with’: Patient expertise in rheumatoid arthritis

2014 ◽  
Vol 10 (3) ◽  
pp. 249-261 ◽  
Author(s):  
Tessa Sanderson ◽  
Jo Angouri
Keyword(s):  
Rheumatoid Arthritis ◽  
Meta Analysis ◽  
Healthcare Systems ◽  
Specific Knowledge ◽  
Active Involvement ◽  
Domain Specific ◽  
Access To Health ◽  
Patient Expertise ◽  
Domain Specific Knowledge ◽  
The Uk

The active involvement of patients in decision-making and the focus on patient expertise in managing chronic illness constitutes a priority in many healthcare systems including the NHS in the UK. With easier access to health information, patients are almost expected to be (or present self) as an ‘expert patient’ (Ziebland 2004). This paper draws on the meta-analysis of interview data collected for identifying treatment outcomes important to patients with rheumatoid arthritis (RA). Taking a discourse approach to identity, the discussion focuses on the resources used in the negotiation and co-construction of expert identities, including domain-specific knowledge, access to institutional resources, and ability to self-manage. The analysis shows that expertise is both projected (institutionally sanctioned) and claimed by the patient (self-defined). We close the paper by highlighting the limitations of our pilot study and suggest avenues for further research.

Domain-Specific Knowledge Systems in the Brain: The Animate-Inanimate Distinction

1998 ◽  
Vol 10 (1) ◽  
pp. 1-34 ◽  
Author(s):  
Alfonso Caramazza ◽  
Jennifer R. Shelton
Keyword(s):  
Knowledge Systems ◽  
Neural Mechanisms ◽  
Specific Knowledge ◽  
Knowledge Framework ◽  
Semantic Categories ◽  
Domain Specific ◽  
Domain Specific Knowledge ◽  
Cognitive Neuropsychological ◽  
The Brain ◽  
Selective Impairment

We claim that the animate and inanimate conceptual categories represent evolutionarily adapted domain-specific knowledge systems that are subserved by distinct neural mechanisms, thereby allowing for their selective impairment in conditions of brain damage. On this view, (some of) the category-specific deficits that have recently been reported in the cognitive neuropsychological literature—for example, the selective damage or sparing of knowledge about animals—are truly categorical effects. Here, we articulate and defend this thesis against the dominant, reductionist theory of category-specific deficits, which holds that the categorical nature of the deficits is the result of selective damage to noncategorically organized visual or functional semantic subsystems. On the latter view, the sensory/functional dimension provides the fundamental organizing principle of the semantic system. Since, according to the latter theory, sensory and functional properties are differentially important in determining the meaning of the members of different semantic categories, selective damage to the visual or the functional semantic subsystem will result in a category-like deficit. A review of the literature and the results of a new case of category-specific deficit will show that the domain-specific knowledge framework provides a better account of category-specific deficits than the sensory/functional dichotomy theory.

scholarly journals Toward Knowledge Management for Smart Manufacturing

2017 ◽  
Vol 17 (3) ◽  
Author(s):  
Shaw C. Feng ◽  
William Z. Bernstein ◽  
Thomas Hedberg ◽  
Allison Barnard Feeney
Keyword(s):  
Knowledge Management ◽  
Design Process ◽  
Process Planning ◽  
Smart Manufacturing ◽  
Specific Knowledge ◽  
Domain Specific ◽  
Domain Specific Knowledge ◽  
Knowledge Objects ◽  
Planning Production

The need for capturing knowledge in the digital form in design, process planning, production, and inspection has increasingly become an issue in manufacturing industries as the variety and complexity of product lifecycle applications increase. Both knowledge and data need to be well managed for quality assurance, lifecycle impact assessment, and design improvement. Some technical barriers exist today that inhibit industry from fully utilizing design, planning, processing, and inspection knowledge. The primary barrier is a lack of a well-accepted mechanism that enables users to integrate data and knowledge. This paper prescribes knowledge management to address a lack of mechanisms for integrating, sharing, and updating domain-specific knowledge in smart manufacturing (SM). Aspects of the knowledge constructs include conceptual design, detailed design, process planning, material property, production, and inspection. The main contribution of this paper is to provide a methodology on what knowledge manufacturing organizations access, update, and archive in the context of SM. The case study in this paper provides some example knowledge objects to enable SM.

scholarly journals Cross-Fertilizing Deep Web Analysis and Ontology Enrichment

2017 ◽  
Author(s):  
Marilena Oita ◽  
Antoine Amarilli ◽  
Pierre Senellart
Keyword(s):  
Domain Knowledge ◽  
Deep Web ◽  
Web Pages ◽  
Complete Understanding ◽  
Specific Knowledge ◽  
Domain Specific ◽  
Domain Specific Knowledge ◽  
Web Crawlers ◽  
New Perspective ◽  
The Impact

Deep Web databases, whose content is presented as dynamically-generated Web pages hidden behind forms, have mostly been left unindexed by search engine crawlers. In order to automatically explore this mass of information, many current techniques assume the existence of domain knowledge, which is costly to create and maintain. In this article, we present a new perspective on form understanding and deep Web data acquisition that does not require any domain-specific knowledge. Unlike previous approaches, we do not perform the various steps in the process (e.g., form understanding, record identification, attribute labeling) independently but integrate them to achieve a more complete understanding of deep Web sources. Through information extraction techniques and using the form itself for validation, we reconcile input and output schemas in a labeled graph which is further aligned with a generic ontology. The impact of this alignment is threefold: first, the resulting semantic infrastructure associated with the form can assist Web crawlers when probing the form for content indexing; second, attributes of response pages are labeled by matching known ontology instances, and relations between attributes are uncovered; and third, we enrich the generic ontology with facts from the deep Web.

scholarly journals SMILES-Based Deep Generative Scaffold Decorator for De-Novo Drug Design

2020 ◽  
Author(s):  
Josep Arús-Pous ◽  
Atanas Patronov ◽  
Esben Jannik Bjerrum ◽  
Christian Tyrchan ◽  
Jean-Louis Reymond ◽  
...  
Keyword(s):  
Data Augmentation ◽  
De Novo ◽  
Chemical Space ◽  
Generative Models ◽  
Synthetic Chemistry ◽  
Specific Knowledge ◽  
De Novo Drug Design ◽  
Wide Range ◽  
Small Set ◽  
Synthetic Approaches

Molecular generative models trained with small sets of molecules represented as SMILES strings are able to generate large regions of the chemical space. Unfortunately, due to the sequential nature of SMILES strings, these models are not able to generate molecules given a scaffold (i.e. partially-built molecules with explicit attachment points). Herein we report a new SMILES-based molecular generative architecture that generates molecules from scaffolds and can be trained from any arbitrary molecular set. This is possible thanks to a new molecular set pre-processing algorithm that exhaustively cuts all combinations of acyclic bonds of every molecule, obtaining a large number of scaffold-decorations combinations. Moreover, it serves as a data augmentation technique and can be readily coupled with randomized SMILES to obtain even better results with small sets. Two examples showcasing the potential of the architecture in medicinal and synthetic chemistry are described: First, models were trained with a training set obtained from a small set of Dopamine Receptor D2 (DRD2) active modulators and were able to meaningfully decorate a wide range of scaffolds and obtain molecular series predicted active on DRD2. Second, a larger set of drug-like molecules from ChEMBL was selectively sliced using synthetic chemistry constraints (RECAP rules). Moreover, the resulting scaffold-decorations were filtered to only allow decorations that were fragment-like. This allowed models trained with this dataset to selectively decorate diverse scaffolds with fragments that were generally predicted to be synthesizable and attachable to the scaffold using known synthetic approaches. In both cases, the models were already able to decorate molecules using specific knowledge without the need to add it with other techniques, such as reinforcement learning. We envision that this architecture will become a useful addition to the already existent architectures for de-novo molecular generation.

Sign in / Sign up

Export Citation Format

Share Document