Simulation of undiagnosed patients with novel genetic conditions

Alsentzer, Emily; Finlayson, Samuel G.; Li, Michelle M.; Kobren, Shilpa Nadimpalli; Kohane, Isaac S.

doi:10.1101/2022.08.22.22279073

Cited by 4 publications

(35 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The fake news early detection task is classifying the genuineness of news by initial nodes. EM-User (Users in En-doMondo; unordered) [2,38] is a fitness network of workouts (G), users as subgraphs (S), and their gender (𝑦), where the task is to profile a user's gender with only a few logs. The global graph G of HPO-Metab (Metabolic disease in Human Phenotype Ontology; unordered) [2,15,26,37] is a knowledge graph of symptoms.…”

Section: Methodsmentioning

confidence: 99%

“…Problem formulation. We formulate the 'partial subgraph learning' by relaxing the complete observation assumption of Alsentzer et al [2], considering a subset of nodes or edges of the subgraph, as in Figure 1. We define a partial subgraph S obs of S as S obs = (V obs , A obs ) where V obs ⊂ V sub and A obs ⊂ A sub .…”

Section: Partial Subgraph Learning Problemmentioning

confidence: 99%

“…Here, nodes are observed according to the order in which the information is propagated, and a partial subgraph would contain only nodes of the early propagation. Another example is a noisy diagnosis task of diseases (as subgraphs) based on a knowledge graph of symptoms (as nodes) [2]. In some cases, not all symptoms of the disease may appear or be seen, and a diagnosis is made based solely on the observed ones.…”

Section: Partial Subgraph Learning Problemmentioning

confidence: 99%

“…The graph neural network (GNN) has become a major framework to learn representations of nodes, edges, and graphs [3,8,11,19]. In addition, subgraphs can express various real-world data: news propagation in a social network or disease in a graph of symptoms [2].…”

Section: Introductionmentioning

confidence: 99%

“…The current formulation of subgraph representation learning by Alsentzer et al [2] assumes full observation of nodes and edges in a subgraph, and that assumption often does not hold in the real world. If so, existing models may learn suboptimal representations because of inaccurate message-passing with missing nodes or edges.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Models and Benchmarks for Representation Learning of Partially Observed Subgraphs

Kim¹,

Jin²,

Ahn³

et al. 2022

Preprint

View full text Add to dashboard Cite

Subgraphs are rich substructures in graphs, and their nodes and edges can be partially observed in real-world tasks. Under partial observation, existing node-or subgraph-level message-passing produces suboptimal representations. In this paper, we formulate a novel task of learning representations of partially observed subgraphs. To solve this problem, we propose Partial Subgraph InfoMax (PSI) framework and generalize existing InfoMax models, including DGI, InfoGraph, MVGRL, and GraphCL, into our framework. These models maximize the mutual information between the partial subgraph's summary and various substructures from nodes to full subgraphs. In addition, we suggest a novel two-stage model with 𝑘-hop PSI, which reconstructs the representation of the full subgraph and improves its expressiveness from different local-global structures. Under training and evaluation protocols designed for this problem, we conduct experiments on three real-world datasets and demonstrate that PSI models outperform baselines. CCS CONCEPTS• Computing methodologies → Learning latent representations; Neural networks; Supervised learning by classification.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Partial Subgraph Learning Problemmentioning

confidence: 99%

Section: Partial Subgraph Learning Problemmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Models and Benchmarks for Representation Learning of Partially Observed Subgraphs

Kim¹,

Jin²,

Ahn³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

Assessment of Natural Language Processing of Electronic Health Records to Measure Goals-of-Care Discussions as a Clinical Trial Outcome

et al. 2023

View full text Add to dashboard Cite

ImportanceMany clinical trial outcomes are documented in free-text electronic health records (EHRs), making manual data collection costly and infeasible at scale. Natural language processing (NLP) is a promising approach for measuring such outcomes efficiently, but ignoring NLP-related misclassification may lead to underpowered studies.ObjectiveTo evaluate the performance, feasibility, and power implications of using NLP to measure the primary outcome of EHR-documented goals-of-care discussions in a pragmatic randomized clinical trial of a communication intervention.Design, Setting, and ParticipantsThis diagnostic study compared the performance, feasibility, and power implications of measuring EHR-documented goals-of-care discussions using 3 approaches: (1) deep-learning NLP, (2) NLP-screened human abstraction (manual verification of NLP-positive records), and (3) conventional manual abstraction. The study included hospitalized patients aged 55 years or older with serious illness enrolled between April 23, 2020, and March 26, 2021, in a pragmatic randomized clinical trial of a communication intervention in a multihospital US academic health system.Main Outcomes and MeasuresMain outcomes were natural language processing performance characteristics, human abstractor-hours, and misclassification-adjusted statistical power of methods of measuring clinician-documented goals-of-care discussions. Performance of NLP was evaluated with receiver operating characteristic (ROC) curves and precision-recall (PR) analyses and examined the effects of misclassification on power using mathematical substitution and Monte Carlo simulation.ResultsA total of 2512 trial participants (mean [SD] age, 71.7 [10.8] years; 1456 [58%] female) amassed 44 324 clinical notes during 30-day follow-up. In a validation sample of 159 participants, deep-learning NLP trained on a separate training data set from identified patients with documented goals-of-care discussions with moderate accuracy (maximal F1 score, 0.82; area under the ROC curve, 0.924; area under the PR curve, 0.879). Manual abstraction of the outcome from the trial data set would require an estimated 2000 abstractor-hours and would power the trial to detect a risk difference of 5.4% (assuming 33.5% control-arm prevalence, 80% power, and 2-sided α = .05). Measuring the outcome by NLP alone would power the trial to detect a risk difference of 7.6%. Measuring the outcome by NLP-screened human abstraction would require 34.3 abstractor-hours to achieve estimated sensitivity of 92.6% and would power the trial to detect a risk difference of 5.7%. Monte Carlo simulations corroborated misclassification-adjusted power calculations.Conclusions and RelevanceIn this diagnostic study, deep-learning NLP and NLP-screened human abstraction had favorable characteristics for measuring an EHR outcome at scale. Adjusted power calculations accurately quantified power loss from NLP-related misclassification, suggesting that incorporation of this approach into the design of studies using NLP would be beneficial.

show abstract

Few shot learning for phenotype-driven diagnosis of patients with rare genetic diseases

Alsentzer

Kobren

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

There are more than 7,000 rare diseases, some of which affect 3,500 or fewer patients in the US. Due to clinicians' limited experience with such diseases and the considerable heterogeneity of their clinical presentations, many patients with rare genetic diseases remain undiagnosed. While artificial intelligence has demonstrated success in assisting diagnosis, its success is usually contingent on the availability of large labeled datasets. Here, we present SHEPHERD, a deep learning approach for multi-faceted rare disease diagnosis. SHEPHERD is guided by existing knowledge of diseases, phenotypes, and genes to learn novel connections between a patient's clinico-genetic information and phenotype and gene relationships. We train SHEPHERD exclusively on simulated patients and evaluate on a cohort of 465 patients representing 299 diseases (79% of genes and 83% of diseases are represented in only a single patient) in the Undiagnosed Diseases Network. SHEPHERD excels at several diagnostic facets: performing causal gene discovery (causal genes are predicted at rank = 3.52 on average), retrieving "patients-like-me" with the same gene or disease, and providing interpretable characterizations of novel disease presentations. SHEPHERD demonstrates the potential of artificial intelligence to accelerate the diagnosis of rare disease patients and has implications for the use of deep learning on medical datasets with very few labels.

show abstract

Simulation of undiagnosed patients with novel genetic conditions

Cited by 4 publications

References 35 publications

Models and Benchmarks for Representation Learning of Partially Observed Subgraphs

Models and Benchmarks for Representation Learning of Partially Observed Subgraphs

Assessment of Natural Language Processing of Electronic Health Records to Measure Goals-of-Care Discussions as a Clinical Trial Outcome

Few shot learning for phenotype-driven diagnosis of patients with rare genetic diseases

Contact Info

Product

Resources

About