Vesico-ureteral reflux diagnosis after initial kidney abscess: Results from a Paediatric Tertiary Hospital.

AIMS: Guidelines regarding voiding cystourethrogram (VCUG) indications following a paediatric kidney abscess are lacking. This study evaluates vesicoureteral reflux (VUR) prevalence and outcome after a first kidney abscess. METHODS: This retrospective study included all children presenting to a tertiary paediatric reference centre with de-novo kidney abscesses from 2011 to 2022, diagnosed through imaging (ultrasonography or computed tomography). VCUG's clinical utility was assessed by exploring outcomes related to interventions. RESULTS: Among the 17 patients (median age 9 months, IQR; 6 months-6 years), VCUG identified VUR in 7 (41%; 95% CI: 18-65%), including two with grade IV-V. Median abscess size was 19 mm (IQR; 14-27). 7/8 (88%) children with DMSA scan presented scars, including 4 with hypofunctioning (20%-44%), and one with a non-functioning kidney. Scarring on the DMSA scan was similar regardless of identified VUR. Six children had subsequent pyelonephritis. Three of the remaining 11 had grade I-III and two IV-V VUR. Surgery was required in four children overall: three for recurrent pyelonephritis and one for high-grade VUR and scars. CONCLUSION: Among initial kidney abscess cases, 41% had VUR, similar to children experiencing their first uncomplicated pyelonephritis. VCUG results guided antibiotic prophylaxis but not surgical decisions. We suggest considering VCUG following recurrent pyelonephritis/kidney abscess and/or kidney scarring.

Humanitarian Facial Recognition for Rare Craniofacial Malformations.

Children with congenital disorders are unfortunate collateral victims of wars and natural disasters. Improved diagnosis could help organize targeted medical support campaigns. Patient identification is a key issue in the management of life-threatening conditions in extreme situations, such as in oncology or for diabetes, and can be challenging when diagnosis requires biological or radiological investigations. Dysmorphology is a central element of diagnosis for craniofacial malformations, with high sensibility and specificity. Massive amounts of public data, including facial pictures circulate daily on news channels and social media, offering unique possibilities for automatic diagnosis based on facial recognition. Furthermore, AI-based algorithms assessing facial features are currently being developed to decrease diagnostic delays. Here, as a case study, we used a facial recognition algorithm trained on a large photographic database to assess an online picture of a family of refugees. Our aim was to evaluate the relevance of using an academic tool on a journalistic picture and discuss its potential application to large-scale screening in humanitarian perspectives. This group picture featured one child with signs of Apert syndrome, a rare condition with risks of severe complications in cases of delayed management. We report the successful automatic screening of Apert syndrome on this low-resolution picture, suggesting that AI-based facial recognition could be used on public data in crisis conditions to localize at-risk patients.

Objectivizing issues in the diagnosis of complex rare diseases: lessons learned from testing existing diagnosis support systems on ciliopathies.

BACKGROUND: There are approximately 8,000 different rare diseases that affect roughly 400 million people worldwide. Many of them suffer from delayed diagnosis. Ciliopathies are rare monogenic disorders characterized by a significant phenotypic and genetic heterogeneity that raises an important challenge for clinical diagnosis. Diagnosis support systems (DSS) applied to electronic health record (EHR) data may help identify undiagnosed patients, which is of paramount importance to improve patients' care. Our objective was to evaluate three online-accessible rare disease DSSs using phenotypes derived from EHRs for the diagnosis of ciliopathies. METHODS: Two datasets of ciliopathy cases, either proven or suspected, and two datasets of controls were used to evaluate the DSSs. Patient phenotypes were automatically extracted from their EHRs and converted to Human Phenotype Ontology terms. We tested the ability of the DSSs to diagnose cases in contrast to controls based on Orphanet ontology. RESULTS: A total of 79 cases and 38 controls were selected. Performances of the DSSs on ciliopathy real world data (best DSS with area under the ROC curve = 0.72) were not as good as published performances on the test set used in the DSS development phase. None of these systems obtained results which could be described as "expert-level". Patients with multisystemic symptoms were generally easier to diagnose than patients with isolated symptoms. Diseases easily confused with ciliopathy generally affected multiple organs and had overlapping phenotypes. Four challenges need to be considered to improve the performances: to make the DSSs interoperable with EHR systems, to validate the performances in real-life settings, to deal with data quality, and to leverage methods and resources for rare and complex diseases. CONCLUSION: Our study provides insights into the complexities of diagnosing highly heterogenous rare diseases and offers lessons derived from evaluation existing DSSs in real-world settings. These insights are not only beneficial for ciliopathy diagnosis but also hold relevance for the enhancement of DSS for various complex rare disorders, by guiding the development of more clinically relevant rare disease DSSs, that could support early diagnosis and finally make more patients eligible for treatment.

Artificial intelligence-based diagnosis in fetal pathology using external ear shapes.

OBJECTIVE: Here we trained an automatic phenotype assessment tool to recognize syndromic ears in two syndromes in fetuses-=CHARGE and Mandibulo-Facial Dysostosis Guion Almeida type (MFDGA)-versus controls. METHOD: We trained an automatic model on all profile pictures of children diagnosed with genetically confirmed MFDGA and CHARGE syndromes, and a cohort of control patients, collected from 1981 to 2023 in Necker Hospital (Paris) with a visible external ear. The model consisted in extracting landmarks from photographs of external ears, in applying geometric morphometry methods, and in a classification step using machine learning. The approach was then tested on photographs of two groups of fetuses: controls and fetuses with CHARGE and MFDGA syndromes. RESULTS: The training set contained a total of 1489 ear photographs from 526 children. The validation set contained a total of 51 ear photographs from 51 fetuses. The overall accuracy was 72.6% (58.3%-84.1%, p < 0.001), and 76.4%, 74.9%, and 86.2% respectively for CHARGE, control and MFDGA fetuses. The area under the curves were 86.8%, 87.5%, and 90.3% respectively for CHARGE, controls, and MFDGA fetuses. CONCLUSION: We report the first automatic fetal ear phenotyping model, with satisfactory classification performances. Further validations are required before using this approach as a diagnostic tool.

Histological characterization of liver involvement in systemic mastocytosis.

BACKGROUND AND AIMS: Systemic mastocytosis (SM) is characterized by the accumulation of atypical mast cells (MCs) in organs. Liver histology of SM has been marginally described and accurate histological classification is critical, given the consequences of aggressive SM diagnosis. We aimed to describe the histological features associated with liver SM using updated tools. METHODS: Using the database of the French Reference Centre for Mastocytosis, we retrospectively identified patients with a liver biopsy (LB) and a diagnosis of SM. All LB procedures were performed according to the local physician in charge and centrally reviewed by an expert pathologist. RESULTS: A total of 28 patients were included: 6 had indolent SM, 9 had aggressive SM, and 13 had SM with an associated hematologic neoplasm. Twenty-five (89%) patients presented hepatomegaly, and 19 (68%) had portal hypertension. The LB frequently showed slight sinusoid dilatation (82%). Fibrosis was observed in 3/6 indolent SM and in almost all advanced SM cases (21/22), but none of them showed cirrhosis. A high MC burden (>50 MCs/high-power field) was correlated with elevated blood alkaline phosphatase levels (p = .030). The presence of portal hypertension was associated with a higher mean fibrosis grade (1.6 vs. 0.8 in its absence; p = .026). In advanced SM, the presence of nodular regenerative hyperplasia (NRH) was associated with decreased overall survival (9.5 vs. 46.3 months, p = .002). CONCLUSIONS: MC infiltration induced polymorphic hepatic lesions and the degree of fibrosis is associated with portal hypertension. NRH identifies a poor prognosis subgroup of patients with advanced SM. Assessing liver histology can aid in SM prognostic evaluation.

Performance and clinical utility of a new supervised machine-learning pipeline in detecting rare ciliopathy patients based on deep phenotyping from electronic health records and semantic similarity.

BACKGROUND: Rare diseases affect approximately 400 million people worldwide. Many of them suffer from delayed diagnosis. Among them, NPHP1-related renal ciliopathies need to be diagnosed as early as possible as potential treatments have been recently investigated with promising results. Our objective was to develop a supervised machine learning pipeline for the detection of NPHP1 ciliopathy patients from a large number of nephrology patients using electronic health records (EHRs). METHODS AND RESULTS: We designed a pipeline combining a phenotyping module re-using unstructured EHR data, a semantic similarity module to address the phenotype dependence, a feature selection step to deal with high dimensionality, an undersampling step to address the class imbalance, and a classification step with multiple train-test split for the small number of rare cases. The pipeline was applied to thirty NPHP1 patients and 7231 controls and achieved good performances (sensitivity 86% with specificity 90%). A qualitative review of the EHRs of 40 misclassified controls showed that 25% had phenotypes belonging to the ciliopathy spectrum, which demonstrates the ability of our system to detect patients with similar conditions. CONCLUSIONS: Our pipeline reached very encouraging performance scores for pre-diagnosing ciliopathy patients. The identified patients could then undergo genetic testing. The same data-driven approach can be adapted to other rare diseases facing underdiagnosis challenges.

Next generation phenotyping for diagnosis and phenotype-genotype correlations in Kabuki syndrome.

The field of dysmorphology has been changed by the use Artificial Intelligence (AI) and the development of Next Generation Phenotyping (NGP). The aim of this study was to propose a new NGP model for predicting KS (Kabuki Syndrome) on 2D facial photographs and distinguish KS1 (KS type 1, KMT2D-related) from KS2 (KS type 2, KDM6A-related). We included retrospectively and prospectively, from 1998 to 2023, all frontal and lateral pictures of patients with a molecular confirmation of KS. After automatic preprocessing, we extracted geometric and textural features. After incorporation of age, gender, and ethnicity, we used XGboost (eXtreme Gradient Boosting), a supervised machine learning classifier. The model was tested on an independent validation set. Finally, we compared the performances of our model with DeepGestalt (Face2Gene). The study included 1448 frontal and lateral facial photographs from 6 centers, corresponding to 634 patients (527 controls, 107 KS); 82 (78%) of KS patients had a variation in the KMT2D gene (KS1) and 23 (22%) in the KDM6A gene (KS2). We were able to distinguish KS from controls in the independent validation group with an accuracy of 95.8% (78.9-99.9%, p < 0.001) and distinguish KS1 from KS2 with an empirical Area Under the Curve (AUC) of 0.805 (0.729-0.880, p < 0.001). We report an automatic detection model for KS with high performances (AUC 0.993 and accuracy 95.8%). We were able to distinguish patients with KS1 from KS2, with an AUC of 0.805. These results outperform the current commercial AI-based solutions and expert clinicians.

Inflammatory rebound and postinfectious inflammatory response in children with pleural infection: A single-center retrospective study.

INTRODUCTION: As pleural inflammation plays a central role in pleural infection (PI), corticosteroids are increasingly being considered as a potential therapy. However, the timing of treatment and the identification of patients who might benefit most remain unresolved. The aim of this study was therefore to investigate the inflammatory trajectories of children with PI. METHODS: This retrospective single-center study included children aged 3 months to 17 years and 11 months hospitalized for PI due to Streptococcus pyogenes, Streptococcus pneumonia, and Staphylococcus aureus over 10 years. An inflammatory rebound was defined biologically as a reincrease in C-reactive protein (CRP) of at least 50 mg/L after an initial decrease in CRP of at least 50 mg/L. RESULTS: We included 53 cases of PI, including 16 due to S. pyogenes, 27 due to S. pneumonia, and 10 due to S. aureus. An inflammatory rebound occurred in 20 patients (38%) after a median of 4.5 (3-6) days. This inflammatory rebound occurred in 9 (56%) children with S. pyogenes, 8 (30%) children with S. pneumonia, and 3 (30%) children with S. aureus. Children with an inflammatory rebound also had a higher rate of persistent fever after Day 7 and a longer length of stay (p = .01 for both). CONCLUSION: We postulate that the inflammatory rebound identified in nearly 40% of our patients corresponds to an early postinfectious inflammatory response, and thus that corticosteroids may be most beneficial for children with PI if administered early (between Days 2 and 5).

Pathophysiologic implications of elevated prevalence of hereditary alpha-tryptasemia in all mastocytosis subtypes.

BACKGROUND: Mastocytosis and monoclonal mast cell (MC) activation syndrome (MMAS) are heterogeneous conditions characterized by the accumulation of atypical MCs. Despite the recurrent involvement of KIT mutations, the pathophysiologic origin of mastocytosis and MMAS is unclear. Although hereditary α-tryptasemia (HαT, related to TPSAB1 gene duplication) is abnormally frequent in these diseases, it is not known whether the association is coincidental or causal. OBJECTIVE: We evaluated the prevalence of HαT in all mastocytosis subtypes and MMAS and assessed the pathophysiologic association with HαT. METHODS: Clinical data, laboratory data, KIT mutations, TPSAB1 duplication (assessed by droplet digital PCR), and HαT prevalence were retrospectively recorded for all patients with mastocytosis and MMAS registered in the French national referral center database and compared to a control cohort. To increase the power of our analysis for advanced systemic mastocytosis (advSM), we pooled our cohort with literature cases. RESULTS: We included 583 patients (27 with MMAS and 556 with mastocytosis). The prevalence of HαT in mastocytosis was 12.6%, significantly higher than in the general population (5.7%, P = .002) and lower than in MMAS (33.3%, P = .02). HαT+ patients were more likely to have anaphylactic reactions and less likely to have cutaneous lesions than HαT- patients (43.0% vs 24.4%, P = .006; 57.7% vs 75.6%, respectively, P = .006). In the pooled analysis, the prevalence of HαT was higher in advSM (11.5%) than in control cohorts (5.2%, P = .01). CONCLUSION: Here we confirm the increase incidence of anaphylaxis in HαT+ mastocytosis patients. The increased prevalence of HαT in all subtypes of systemic mastocytosis (including advSM) is suggestive of pathophysiologic involvement.

Severe adult hemophagocytic lymphohistiocytosis (HLHa) correlates with HLH-related gene variants.

BACKGROUND: The contribution of genetic factors to the severity of adult hemophagocytic lymphohistiocytosis (HLHa) remains unclear. OBJECTIVE: We sought to assess a potential link between HLHa outcomes and HLH-related gene variants. METHODS: Clinical characteristics of 130 HLHa patients (age ≥ 18 years and HScore ≥ 169) and genotype of 8 HLH-related genes (LYST, PRF1, UNC13-D, STX11, STXBP2, RAB27A, XIAP, and SAP) were collected. A total of 34 variants found in only 6 genes were selected on the basis of their frequency and criteria predicted to impair protein function. Severity was defined by refractory disease to HLH treatment, death, or transfer to an intensive care unit. RESULTS: HLHa-associated diseases (ADs) were neoplasia (n = 49 [37.7%]), autoimmune/inflammatory disease (n = 33 [25.4%]), or idiopathic when no AD was identified (n = 48 [36.9%]). Infectious events occurred in 76 (58.5%) patients and were equally distributed in all ADs. Severe and refractory HLHa were observed in 80 (61.5%) and 64 (49.2%) patients, respectively. HScore, age, sex ratio, AD, and infectious events showed no significant association with HLHa severity. Variants were identified in 71 alleles and were present in 56 (43.1%) patients. They were distributed as follows: 44 (34.4%), 9 (6.9%), and 3 (2.3%) patients carrying 1, 2, and 3 variant alleles, respectively. In a logistic regression model, only the number of variants was significantly associated with HLHa severity (1 vs 0: 3.86 [1.73-9.14], P = .0008; 2-3 vs 0: 29.4 [3.62-3810], P = .0002) and refractoriness (1 vs 0: 2.47 [1.17-5.34], P = .018; 2-3 vs 0: 13.2 [2.91-126.8], P = .0003). CONCLUSIONS: HLH-related gene variants may be key components to the severity and refractoriness of HLHa.

Natural history of rare diseases using natural language processing of narrative unstructured electronic health records: The example of Dravet syndrome.

OBJECTIVE: The increasing implementation of electronic health records allows the use of advanced text-mining methods for establishing new patient phenotypes and stratification, and for revealing outcome correlations. In this study, we aimed to explore the electronic narrative clinical reports of a cohort of patients with Dravet syndrome (DS) longitudinally followed at our center, to identify the capacity of this methodology to retrace natural history of DS during the early years. METHODS: We used a document-based clinical data warehouse employing natural language processing to recognize the phenotype concepts in the narrative medical reports. We included patients with DS who have a medical report produced before the age of 2 years and a follow-up after the age of 3 years ("DS cohort," 56 individuals). We selected two control populations, a "general control cohort" (275 individuals) and a "neurological control cohort" (281 individuals), with similar characteristics in terms of gender, number of reports, and age at last report. To find concepts specifically associated with DS, we performed a phenome-wide association study using Cox regression, comparing the reports of the three cohorts. We then performed a qualitative analysis of the surviving concepts based on their median age at first appearance. RESULTS: A total of 76 concepts were prevalent in the reports of children with DS. Concepts appearing during the first 2 years were mostly related with the epilepsy features at the onset of DS (convulsive and prolonged seizures triggered by fever, often requiring in-hospital care). Subsequently, concepts related to new types of seizures and to drug resistance appeared. A series of non-seizure-related concepts emerged after the age of 2-3 years, referring to the nonseizure comorbidities classically associated with DS. SIGNIFICANCE: The extraction of clinical terms by narrative reports of children with DS allows outlining the known natural history of this rare disease in early childhood. This original model of "longitudinal phenotyping" could be applied to other rare and very rare conditions with poor natural history description.

Unclassifiable interstitial lung disease and autoimmunity: Towards IPAF in children?

INTRODUCTION: Interstitial pneumonia with autoimmune features (IPAF) has been defined for adults with interstitial lung disease (ILD) and autoimmunity who do not meet the criteria for a specific connective tissue disease (CTD). We aimed to determine whether IPAF criteria could apply to children. METHODS: We retrospectively studied patients with ILD and autoimmunity followed at Necker Hospital between 2008 and 2019. Children were classified according to specific CTD and IPAF criteria. The epidemiology and course of the disease were studied according to the final diagnosis. RESULTS: Among 27 patients, 6 fulfilled the criteria for IPAF and represented 4.5% of all patients with ILD during the study period. Other diagnoses included juvenile dermatomyositis (30%), overlap syndromes (19%), systemic lupus erythematosus (15%), systemic sclerosis (7%), mixed CTD (4%), and rheumatoid arthritis (4%). IPAF patients were more frequently boys versus CTD-ILD patients (67% vs. 14%, p = .02). Two patients had severe respiratory distress that led to death for one of them. The course was favorable for the others, with a good response to steroids. The course tended to be more favorable for IPAF patients than for those with CTD-ILD (0% lung fibrosis in the IPAF group vs. 43% in the CTD-ILD group, p = .07). CONCLUSION: We confirmed the existence of IPAF in children. Its prevalence was lower than in adults but comparable to that found for other pediatric series. Boys were more highly represented than in CTD-ILD. The course was favorable for most cases. Larger and more prospective studies are needed to confirm these results.

AI-based diagnosis in mandibulofacial dysostosis with microcephaly using external ear shapes.

Introduction: Mandibulo-Facial Dysostosis with Microcephaly (MFDM) is a rare disease with a broad spectrum of symptoms, characterized by zygomatic and mandibular hypoplasia, microcephaly, and ear abnormalities. Here, we aimed at describing the external ear phenotype of MFDM patients, and train an Artificial Intelligence (AI)-based model to differentiate MFDM ears from non-syndromic control ears (binary classification), and from ears of the main differential diagnoses of this condition (multi-class classification): Treacher Collins (TC), Nager (NAFD) and CHARGE syndromes. Methods: The training set contained 1,592 ear photographs, corresponding to 550 patients. We extracted 48 patients completely independent of the training set, with only one photograph per ear per patient. After a CNN-(Convolutional Neural Network) based ear detection, the images were automatically landmarked. Generalized Procrustes Analysis was then performed, along with a dimension reduction using PCA (Principal Component Analysis). The principal components were used as inputs in an eXtreme Gradient Boosting (XGBoost) model, optimized using a 5-fold cross-validation. Finally, the model was tested on an independent validation set. Results: We trained the model on 1,592 ear photographs, corresponding to 1,296 control ears, 105 MFDM, 33 NAFD, 70 TC and 88 CHARGE syndrome ears. The model detected MFDM with an accuracy of 0.969 [0.838-0.999] (p < 0.001) and an AUC (Area Under the Curve) of 0.975 within controls (binary classification). Balanced accuracies were 0.811 [0.648-0.920] (p = 0.002) in a first multiclass design (MFDM vs. controls and differential diagnoses) and 0.813 [0.544-0.960] (p = 0.003) in a second multiclass design (MFDM vs. differential diagnoses). Conclusion: This is the first AI-based syndrome detection model in dysmorphology based on the external ear, opening promising clinical applications both for local care and referral, and for expert centers.

Determinants of dental care use in patients with rare diseases: a qualitative exploration.

BACKGROUND: Oral health is an inherent part of overall health as an important physiological crossroad of functions such as mastication, swallowing or phonation; and plays a central role in the life of relationships facilitating social and emotional expression.Our hypothesis was that in patients with rare diseases, access to dental care could be difficult because of the lack of professionals who know the diseases and accept to treat the patients, but also because some patients with cognitive and intellectual disabilities could not find adequate infrastructure to assist in managing their oral health. METHODS: This study employed a qualitative descriptive design including semi-structured interviews using guiding themes. The transcripts were reviewed to identify key themes and interviews were performed until the data were saturated and no further themes emerged. RESULTS: Twenty-nine patients from 7 to 24 years old were included in the study of which 15 patients had an intellectual delay. The results show that access to care is complicated more by aspects concerning intellectual disability than by the fact that the disease is rare. Oral disorders are also an obstacle to the maintenance of their oral health. CONCLUSION: The oral health of patients with rare diseases, can be greatly enhanced by a pooling of knowledge between health professionals in the various sectors around the patient's care. It is essential that this becomes a focus of national public health action that promotes transdisciplinary care for the benefit of these patients.

Deep Learning on Bone Scintigraphy to Detect Abnormal Cardiac Uptake at Risk of Cardiac Amyloidosis.

BACKGROUND: Cardiac uptake on technetium-99m whole-body scintigraphy (WBS) is almost pathognomonic of transthyretin cardiac amyloidosis. The rare false positives are often related to light-chain cardiac amyloidosis. However, this scintigraphic feature remains largely unknown, leading to misdiagnosis despite characteristic images. A retrospective review of all WBSs in a hospital database to detect those with cardiac uptake may allow the identification of undiagnosed patients. OBJECTIVES: The authors sought to develop and validate a deep learning-based model that automatically detects significant cardiac uptake (Perugini grade ≥2) on WBS from large hospital databases in order to retrieve patients at risk of cardiac amyloidosis. METHODS: The model is based on a convolutional neural network with image-level labels. The performance evaluation was performed with C-statistics using a 5-fold cross-validation scheme stratified so that the proportion of positive and negative WBSs remained constant across folds and using an external validation data set. RESULTS: The training data set consisted of 3,048 images: 281 positives (Perugini grade ≥2) and 2,767 negatives. The external validation data set consisted of 1,633 images: 102 positives and 1,531 negatives. The performance of the 5-fold cross-validation and external validation was as follows: 98.9% (± 1.0) and 96.1% for sensitivity, 99.5% (± 0.4) and 99.5% for specificity, and 0.999 (SD = 0.000) and 0.999 for the area under the curve of the receiver-operating characteristic curves. Sex, age <90 years, body mass index, injection-acquisition delay, radionuclides, and the indication of WBS only slightly affected performances. CONCLUSIONS: The authors' detection model is effective at identifying patients with cardiac uptake Perugini grade ≥2 on WBS and may help in the diagnosis of patients with cardiac amyloidosis.

Pediatric Tumors and Developmental Anomalies: A French Nationwide Cohort Study.

OBJECTIVE: To assess the associations between congenital abnormalities and pediatric malignancies and evaluate the potential underlying molecular basis by collecting information on pediatric patients with cancer and congenital abnormalities. STUDY DESIGN: Tumeur Et Développement is a national, prospective, and retrospective multicenter study recording data of children with cancer and congenital abnormalities. When feasible, blood and tumoral samples are collected for virtual biobanking. RESULTS: From June 2013 to December 2019, 679 associations between pediatric cancers and congenital abnormalities were recorded. The most represented cancers were central nervous system tumors (n = 139; 20%), leukemia and myelodysplastic syndromes (n = 123; 18.1%), and renal tumors (n = 101; 15%). Congenital abnormalities were not related to any known genetic disorder in 66.5% of cases. In this group, the most common anomaly was intellectual disability (22.3%), followed by musculoskeletal (14.2%) and genitourinary anomalies (12.4%). Intellectual disability was mostly associated with hematologic malignancies. Embryonic tumors (neuroblastoma, Wilms tumor, and rhabdomyosarcoma) were associated with consistent abnormalities, sometimes with a close anatomical neighborhood between the abnormality and the neoplasm. CONCLUSIONS: In the first Tumeur Et Développement analysis, 3 major themes have been identified: (1) germline mutations with or without known cancer predisposition, (2) postzygotic events responsible for genomic mosaicism, (3) coincidental associations. New pathways involved in cancer development need to be investigated to improve our understanding of childhood cancers.

Improving Patient Similarity Using Different Modalities of Phenotypes Extracted from Clinical Narratives.

In the context of medical concept extraction, it is critical to determine if clinical signs or symptoms mentioned in the text were present or absent, experienced by the patient or their relatives. Previous studies have focused on the NLP aspect but not on how to leverage this supplemental information for clinical applications. In this paper, we aim to use the patient similarity networks framework to aggregate different phenotyping modalities. NLP techniques were applied to extract phenotypes and predict their modalities from 5470 narrative reports of 148 patients with ciliopathies (a group of rare diseases). Patient similarities were computed using each modality separately for aggregation and clustering. We found that aggregating negated phenotypes improved patient similarity, but further aggregating relatives' phenotypes worsened the result. We suggest that different modalities of phenotypes can contribute to patient similarity, but they should be aggregated carefully and with appropriate similarity metrics and aggregation models.

The Smart Data Extractor, a Clinician Friendly Solution to Accelerate and Improve the Data Collection During Clinical Trials.

In medical research, the traditional way to collect data, i.e. browsing patient files, has been proven to induce bias, errors, human labor and costs. We propose a semi-automated system able to extract every type of data, including notes. The Smart Data Extractor pre-populates clinic research forms by following rules. We performed a cross-testing experiment to compare semi-automated to manual data collection. 20 target items had to be collected for 79 patients. The average time to complete one form was 6'81" for manual data collection and 3'22" with the Smart Data Extractor. There were also more mistakes during manual data collection (163 for the whole cohort) than with the Smart Data Extractor (46 for the whole cohort). We present an easy to use, understandable and agile solution to fill out clinical research forms. It reduces human effort and provides higher quality data, avoiding data re-entry and fatigue induced errors.