Clinical study applying machine learning to detect a rare disease: results and lessons learned

High disease burden and healthcare resource usage in patients with acute porphyria-A population-based analysis

BACKGROUND AND AIMS

Acute porphyria is a chronic recurrent disease with late diagnosis, heterogeneous clinical presentations and potentially devastating complications. The study aimed at providing real-world evidence on the natural course of acute porphyria, patient characteristics, disease burden, and healthcare utilization before diagnosis.

METHODS

This observational study used anonymized claims data covering 8 365 867 persons from German statutory health insurance, spanning 6 years (2015-2020). Patients with at least one diagnosis of acute porphyria during the index period (2019-2020) were classified into three groups by attack frequency. These findings were compared with two age- and sex-adjusted reference groups: the general population and fibromyalgia patients. Prevalence over the index period was calculated for all porphyria patients and those with active acute porphyria.

RESULTS

We revealed a prevalence of 79.8 per 1 000 000 for acute porphyria, with 12.9 per 1 000 000 being active cases. Acute porphyria patients, particularly with frequent attacks, demonstrated a higher comorbidity burden compared to the general population. Within the year before the recorded diagnosis, patients with acute porphyria required a median of 23.0 physician visits, significantly higher than the general population's 16.0. Additionally, 33.8% were hospitalized at least once during this period, a notably higher proportion than the general population (19.3%).

CONCLUSIONS

This study's findings, collected before the introduction of givosiran, as the first approved preventive therapy for acute porphyria in Europe, highlight the need for healthcare strategies and policies tailored to the complex needs of acute porphyria patients. The significant healthcare demands, heightened comorbidity burden, and increased healthcare system utilization emphasize the urgency of developing a comprehensive support infrastructure for these patients. Also, these acute porphyria real-world findings provide additional insights on disease characteristics in Germany.

Temporal self-attention for risk prediction from electronic health records using non-stationary kernel approximation

Effective modeling of patient representation from electronic health records (EHRs) is increasingly becoming a vital research topic. Yet, modeling the non-stationarity in EHR data has received less attention. Most existing studies follow a strong assumption of stationarity in patient representation from EHRs. However, in practice, a patient's visits are irregularly spaced over a relatively long period of time, and disease progression patterns exhibit non-stationarity. Furthermore, the time gaps between patient visits often encapsulate significant domain knowledge, potentially revealing undiscovered patterns that characterize specific medical conditions. To address these challenges, we introduce a new method which combines the self-attention mechanism with non-stationary kernel approximation to capture both contextual information and temporal relationships between patient visits in EHRs. To assess the effectiveness of our proposed approach, we use two real-world EHR datasets, comprising a total of 76,925 patients, for the task of predicting the next diagnosis code for a patient, given their EHR history. The first dataset is a general EHR cohort and consists of 11,451 patients with a total of 3,485 unique diagnosis codes. The second dataset is a disease-specific cohort that includes 65,474 pregnant patients and encompasses a total of 9,782 unique diagnosis codes. Our experimental evaluation involved nine prediction models, categorized into three distinct groups. Group 1 comprises the baselines: original self-attention with positional encoding model, RETAIN model, and LSTM model. Group 2 includes models employing self-attention with stationary kernel approximations, specifically incorporating three variations of Bochner's feature maps. Lastly, Group 3 consists of models utilizing self-attention with non-stationary kernel approximations, including quadratic, cubic, and bi-quadratic polynomials. The experimental results demonstrate that non-stationary kernels significantly outperformed baseline methods for NDCG@10 and Hit@10 metrics in both datasets. The performance boost was more substantial in dataset 1 for the NDCG@10 metric. On the other hand, stationary Kernels showed significant but smaller gains over baselines and were nearly as effective as Non-stationary Kernels for Hit@10 in dataset 2. These findings robustly validate the efficacy of employing non-stationary kernels for temporal modeling of EHR data, and emphasize the importance of modeling non-stationary temporal information in healthcare prediction tasks.

Automatically pre-screening patients for the rare disease aromatic l-amino acid decarboxylase deficiency using knowledge engineering, natural language processing, and machine learning on a large EHR population

OBJECTIVES

Electronic health record (EHR) data may facilitate the identification of rare diseases in patients, such as aromatic l-amino acid decarboxylase deficiency (AADCd), an autosomal recessive disease caused by pathogenic variants in the dopa decarboxylase gene. Deficiency of the AADC enzyme results in combined severe reductions in monoamine neurotransmitters: dopamine, serotonin, epinephrine, and norepinephrine. This leads to widespread neurological complications affecting motor, behavioral, and autonomic function. The goal of this study was to use EHR data to identify previously undiagnosed patients who may have AADCd without available training cases for the disease.

MATERIALS AND METHODS

A multiple symptom and related disease annotated dataset was created and used to train individual concept classifiers on annotated sentence data. A multistep algorithm was then used to combine concept predictions into a single patient rank value.

RESULTS

Using an 8000-patient dataset that the algorithms had not seen before ranking, the top and bottom 200 ranked patients were manually reviewed for clinical indications of performing an AADCd diagnostic screening test. The top-ranked patients were 22.5% positively assessed for diagnostic screening, with 0% for the bottom-ranked patients. This result is statistically significant at P < .0001.

CONCLUSION

This work validates the approach that large-scale rare-disease screening can be accomplished by combining predictions for relevant individual symptoms and related conditions which are much more common and for which training data is easier to create.

Meta-analysis informed machine learning: Supporting cytokine storm detection during CAR-T cell Therapy

Cytokine release syndrome (CRS), also known as cytokine storm, is one of the most consequential adverse effects of chimeric antigen receptor therapies that have shown otherwise promising results in cancer treatment. When emerging, CRS could be identified by the analysis of specific cytokine and chemokine profiles that tend to exhibit similarities across patients. In this paper, we exploit these similarities using machine learning algorithms and set out to pioneer a meta-review informed method for the identification of CRS based on specific cytokine peak concentrations and evidence from previous clinical studies. To this end we also address a widespread challenge of the applicability of machine learning in general: reduced training data availability. We do so by augmenting available (but often insufficient) patient cytokine concentrations with statistical knowledge extracted from domain literature. We argue that such methods could support clinicians in analyzing suspect cytokine profiles by matching them against the said CRS knowledge from past clinical studies, with the ultimate aim of swift CRS diagnosis. We evaluate our proposed methods under several design choices, achieving performance of more than 90% in terms of CRS identification accuracy, and showing that many of our choices outperform a purely data-driven alternative. During evaluation with real-world CRS clinical data, we emphasize the potential of our proposed method of producing interpretable results, in addition to being effective in identifying the onset of cytokine storm.