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.

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.

The genetic landscape and clinical spectrum of nephronophthisis and related ciliopathies.

Nephronophthisis (NPH) is an autosomal-recessive ciliopathy representing one of the most frequent causes of kidney failure in childhood characterized by a broad clinical and genetic heterogeneity. Applied to one of the worldwide largest cohorts of patients with NPH, genetic analysis encompassing targeted and whole exome sequencing identified disease-causing variants in 600 patients from 496 families with a detection rate of 71%. Of 788 pathogenic variants, 40 known ciliopathy genes were identified. However, the majority of patients (53%) bore biallelic pathogenic variants in NPHP1. NPH-causing gene alterations affected all ciliary modules defined by structural and/or functional subdomains. Seventy six percent of these patients had progressed to kidney failure, of which 18% had an infantile form (under five years) and harbored variants affecting the Inversin compartment or intraflagellar transport complex A. Forty eight percent of patients showed a juvenile (5-15 years) and 34% a late-onset disease (over 15 years), the latter mostly carrying variants belonging to the Transition Zone module. Furthermore, while more than 85% of patients with an infantile form presented with extra-kidney manifestations, it only concerned half of juvenile and late onset cases. Eye involvement represented a predominant feature, followed by cerebellar hypoplasia and other brain abnormalities, liver and skeletal defects. The phenotypic variability was in a large part associated with mutation types, genes and corresponding ciliary modules with hypomorphic variants in ciliary genes playing a role in early steps of ciliogenesis associated with juvenile-to-late onset NPH forms. Thus, our data confirm a considerable proportion of late-onset NPH suggesting an underdiagnosis in adult chronic kidney disease.

An automatic facial landmarking for children with rare diseases.

Two to three thousand syndromes modify facial features: their screening requires the eye of an expert in dysmorphology. A widely used tool in shape characterization is geometric morphometrics based on landmarks, which are precise and reproducible anatomical points. Landmark positioning is user dependent and time consuming. Many automatic landmarking tools are currently available but do not work for children, because they have mainly been trained using photographic databases of healthy adults. Here, we developed a method for building an automatic landmarking pipeline for frontal and lateral facial photographs as well as photographs of external ears. We evaluated the algorithm on patients diagnosed with Treacher Collins (TC) syndrome as it is the most frequent mandibulofacial dysostosis in humans and is clinically recognizable although highly variable in severity. We extracted photographs from the photographic database of the maxillofacial surgery and plastic surgery department of Hôpital Necker-Enfants Malades in Paris, France with the diagnosis of TC syndrome. The control group was built from children admitted for craniofacial trauma or skin lesions. After testing two methods of object detection by bounding boxes, a Haar Cascade-based tool and a Faster Region-based Convolutional Neural Network (Faster R-CNN)-based tool, we evaluated three different automatic annotation algorithms: the patch-based active appearance model (AAM), the holistic AAM, and the constrained local model (CLM). The final error corresponding to the distance between the points placed by automatic annotation and those placed by manual annotation was reported. We included, respectively, 1664, 2044, and 1375 manually annotated frontal, profile, and ear photographs. Object recognition was optimized with the Faster R-CNN-based detector. The best annotation model was the patch-based AAM (p < 0.001 for frontal faces, p = 0.082 for profile faces and p < 0.001 for ears). This automatic annotation model resulted in the same classification performance as manually annotated data. Pretraining on public photographs did not improve the performance of the model. We defined a pipeline to create automatic annotation models adapted to faces with congenital anomalies, an essential prerequisite for research in dysmorphology.

Phenotypic similarity for rare disease: Ciliopathy diagnoses and subtyping.

Rare diseases are often hard and long to be diagnosed precisely, and most of them lack approved treatment. For some complex rare diseases, precision medicine approach is further required to stratify patients into homogeneous subgroups based on the clinical, biological or molecular features. In such situation, deep phenotyping of these patients and comparing their profiles based on subjacent similarities are thus essential to help fast and precise diagnoses and better understanding of pathophysiological processes in order to develop therapeutic solutions. In this article, we developed a new pipeline of using deep phenotyping to define patient similarity and applied it to ciliopathies, a group of rare and severe diseases caused by ciliary dysfunction. As a French national reference center for rare and undiagnosed diseases, the Necker-Enfants Malades Hospital (Necker Children's Hospital) hosts the Imagine Institute, a research institute focusing on genetic diseases. The clinical data warehouse contains on one hand EHR data, and on the other hand, clinical research data. The similarity metrics were computed on both data sources, and were evaluated with two tasks: diagnoses with EHRs and subtyping with ciliopathy specific research data. We obtained a precision of 0.767 in the top 30 most similar patients with diagnosed ciliopathies. Subtyping ciliopathy patients with phenotypic similarity showed concordances with expert knowledge. Similarity metrics applied to rare disease offer new perspectives in a translational context that may help to recruit patients for research, reduce the length of the diagnostic journey, and better understand the mechanisms of the disease.

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.

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.

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.

Using Deep Learning to Improve Phenotyping from Clinical Reports.

With the development of clinical databases and the ubiquity of EHRs, physicians and researchers alike have access to an unprecedented amount of data. Complexity of the available data has also increased since clinical reports are also included and require frameworks with natural language processing capabilities in order to process them and extract information not found in other types of documents. In the following work we implement a data processing pipeline performing phenotyping, disambiguation, negation and subject prediction on such reports. We compare it to an existing solution routinely used in a children's hospital with special focus on genetic diseases. We show that by replacing components based on rules and pattern matching with components leveraging deep learning models and fine-tuned word embeddings we obtain performance improvements of 7%, 10% and 27% in terms of F1 measure for each task. The solution we devised will help build more reliable decision support systems.