Analysis of scoring systems for primary immunodeficiency diagnosis in adult immunology clinics

Toms, Kieran; Gkrania‐Klotsas, Effrossyni; Kumararatne, D. S.

doi:10.1111/cei.13526

Cited by 6 publications

(5 citation statements)

References 14 publications

(19 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Like most approaches based on databases of payor claims, this method did not include laboratory values. Retrospective gathering of features like we performed here has been useful in aggregating the phenotypic features of patients with IEIs into a score that can discern those with IEIs from those with secondary immunodeficiencies ( 31 ). Recent work used a Bayesian network model to score “risk” in a framework that categorized individuals into either high-, medium-, or low-risk categories of having any IEI ( 30 ).…”

Section: Discussionmentioning

confidence: 99%

Electronic health record signatures identify undiagnosed patients with common variable immunodeficiency disease

Johnson,

Stephens,

Mester

et al. 2024

Sci. Transl. Med.

View full text Add to dashboard Cite

Human inborn errors of immunity include rare disorders entailing functional and quantitative antibody deficiencies due to impaired B cells called the common variable immunodeficiency (CVID) phenotype. Patients with CVID face delayed diagnoses and treatments for 5 to 15 years after symptom onset because the disorders are rare (prevalence of ~1/25,000), and there is extensive heterogeneity in CVID phenotypes, ranging from infections to autoimmunity to inflammatory conditions, overlapping with other more common disorders. The prolonged diagnostic odyssey drives excessive system-wide costs before diagnosis. Because there is no single causal mechanism, there are no genetic tests to definitively diagnose CVID. Here, we present PheNet, a machine learning algorithm that identifies patients with CVID from their electronic health records (EHRs). PheNet learns phenotypic patterns from verified CVID cases and uses this knowledge to rank patients by likelihood of having CVID. PheNet could have diagnosed more than half of our patients with CVID 1 or more years earlier than they had been diagnosed. When applied to a large EHR dataset, followed by blinded chart review of the top 100 patients ranked by PheNet, we found that 74% were highly probable to have CVID. We externally validated PheNet using >6 million records from disparate medical systems in California and Tennessee. As artificial intelligence and machine learning make their way into health care, we show that algorithms such as PheNet can offer clinical benefits by expediting the diagnosis of rare diseases.

show abstract

Section: Discussionmentioning

confidence: 99%

Electronic health record signatures identify undiagnosed patients with common variable immunodeficiency disease

Johnson,

Stephens,

Mester

et al. 2024

Sci. Transl. Med.

View full text Add to dashboard Cite

show abstract

“…An algorithm developed by the Modell Foundation improved IEI diagnoses by using a summation of diagnostic codes [28] and another recent algorithm that summed weighted ICD codes further improved diagnoses [29]; however, these approaches did not include laboratory values. Retrospective gathering of features like we performed here has been useful in aggregating the phenotypic features of patients with IEIs into a score that can discern those with IEIs from those with secondary immunodeficiencies [30]. Recent work used a 18 Bayesian network model to score "risk" in a framework that categorized individuals into either high, medium, or low-risk categories of having any IEI [29].…”

Section: Discussionmentioning

confidence: 99%

Electronic health record signatures identify undiagnosed patients with Common Variable Immunodeficiency Disease

Johnson

Stephens

Knyazev

et al. 2022

Preprint

View full text Add to dashboard Cite

One of the most common human inborn errors of immunity (IEI) is Common Variable Immunodeficiency (CVID), a heterogeneous group of disorders characterized by a state of functional and/or quantitative antibody deficiency and impaired B-cell responses. Although over 30 genes have been associated with the CVID phenotype, over half the CVID patients have no identified monogenic variant. There are currently no existing laboratory or genetic tests to definitively diagnose CVID and none are expected to be available in the near future. The extensive heterogeneity of CVID phenotypes causes patients with CVID to face a 5 to 15 years of delay in diagnosis and initiation of treatment, leading to a critical diagnosis odyssey. In this work, we present PheNet, an algorithm that identifies patients with CVID from their electronic health record data (EHR). PheNet computes the likelihood of a patient having CVID by learning phenotypic patterns, EHR-signatures, from a high-quality, clinically curated list of bona fide CVID patients identified from the UCLA Health system (N=197). The prediction model attains superior accuracy versus state-of-the-art methods, where we find that 57% of cases could be detected within the top 10% of individuals ranked by the algorithm compared to 37% identified by previous phenotype risk scores. In a retrospective analysis, we show that 64% of CVID patients at UCLA Health could have been identified by PheNet more than 8 months earlier than they had been clinically diagnosed. We validate our approach using a discovery dataset of ~880K patients in the UCLA Health system to identify 74 of the top 100 patients ranked by PheNet score (top 0.01% PheNet percentile) as highly probable to have CVID in a clinical blinded chart review by an immune specialist.

show abstract

“…A family history of primary immunodeficiency More recent observations indicate that the JMF warning signs are not ideal [18,19] due to one third of patients with IEI not fulfilling any criteria from the list [16] and some symptoms such as failure to thrive are not adapted to adults [20]. In the case of a first child with IEI in a family or some severe IEI, the 10 warning signs may not be useful [16].…”

Section: Introductionmentioning

confidence: 99%

Extended List of Warning Signs in Qualification to Diagnosis and Treatment of Inborn Errors of Immunity in Children and Young Adults

Dąbrowska

Grześk

Urbańczyk

et al. 2023

JCM

View full text Add to dashboard Cite

Background and Objectives: Inborn errors of immunity (IEI) refer to genetically determined disorders presenting with recurrent infections, autoimmunity, allergies, and malignancies. IEI is now commonly used, replacing the previously used term primary immunodeficiencies (PID). The 10 warning signs of IEI are widely used in the identification patients with IEI. The aim of the study was to determine and compare the utility of the 10 and 14 warning signs in IEI diagnosing. Methods: A retrospective analysis of 2851 patients was performed (98.17% were subjects under 18 years old and 1.83% were adults). All patients were questioned about the 10 warning signs and four additional signs: severe eczema, allergies, hemato-oncologic disorders and autoimmunity. Sensitivity, specificity, positive and negative predictive values, and odds ratio were calculated for the 10 and 14 warning signs. Results: IEI were diagnosed in a total of 896 (31.4%) patients and excluded in 1955 (68.6%). The strongest predictors of IEI were hemato-oncologic disorders (OR = 11.25; p < 0.001) and autoimmunity (OR = 7.74; p < 0.001). The strongest predictors of severe IEI were hemato-oncologic disorders (OR = 89.26; p < 0.001), positive family history (OR = 25.23; p < 0.001), and autoimmunity (OR = 16.89; p < 0.001). There were 20.4% and 14% of IEI patients without any signs from the 10 and 14 warnings signs, respectively (p < 0.001). 20.3% and 6.8% of patients with severe PIDs had no presence of any signs from 10 and 14 signs, respectively (p = 0.012). Conclusions: The 10 warning signs have limited usefulness in identifying IEI. The modified list of 14 warning signs seems to represent an effective diagnostic method for the detection of IEI patients, especially those with severe PIDs.

show abstract

Analysis of scoring systems for primary immunodeficiency diagnosis in adult immunology clinics

Cited by 6 publications

References 14 publications

Electronic health record signatures identify undiagnosed patients with common variable immunodeficiency disease

Electronic health record signatures identify undiagnosed patients with common variable immunodeficiency disease

Electronic health record signatures identify undiagnosed patients with Common Variable Immunodeficiency Disease

Extended List of Warning Signs in Qualification to Diagnosis and Treatment of Inborn Errors of Immunity in Children and Young Adults

Contact Info

Product

Resources

About