[IDENTIFICATION OF A NOVEL LTBP3 GENE PATHOGENIC VARIANT IN DRUZE ARAB PATIENTS PRESENTED WITH SYNDROMIC SHORT STATURE WITH BRACHYOLMIA AND AMELOGENESIS IMPERFECTA].

BACKGROUND: Short stature is a common finding among the general population, mostly presented as an isolated phenotype. The syndromic short statute is rare and complex. Recently, we examined several patients from related families sharing both short stature and congenital dental abnormalities. OBJECTIVES: 1. Clinical characterization of syndromic short stature; 2. To find the disease mutation and evaluate the carrier state in the particular community. METHODS: Clinical characterization- by medical history, medical records and physical examination; Homozygosity mapping - by using the Single nucleotide polymorphism (SNP) chromosomal microarrays (CMA) analysis and gene mutation detection by ABI Sanger sequence. RESULTS: All patients present with short stature severe dental anomalies including enamel formation and mineralization defect, oligodontia, abnormal shape and retarded eruption. CMA analysis in 3 patients and 2 healthy members of four families was normal. One homozygote region in chromosome 11 (11p11.2- 11q13.3) was found in all patients. By using the candidate gene approach, amongst the 301 genes found within this region, only one, the LTBP3 gene (Latent Transforming Growth Factor-Beta-Binding Protein-3) has high priority for sequence. Hence, LTBP3 (OMIM-602090) pathogenic variant is responsible for "brachyolmia with amelogenesis imperfecta" also known as "Dental Anomalies and Short Stature (DASS)" (OMIM- 601216). We sequenced all 29 LTBP3 exons and a novel splice pathogenic variant, c.1346-1G>A chr11:65319629, in exon 8 was identified. The variant segregated well within healthy tested family members. We found a high carrier rate in the village (1:15). CONCLUSIONS: We identified a novel and common LTBP3 gene pathogenic variant responsible for short stature, brachyolmia and amelogenesis imperfecta in Druze Arab patients.

[THE PROGNOSTIC IMPACT OF CHROMOSOMAL ABERRATIONS IN TUMOR TISSUE BIOPSIES FROM PATIENTS WITH DIFFUSE LARGE B CELL LYMPHOMA].

INTRODUCTION: Diffuse large B-cell lymphoma (DLBCL) is the most common form of non-Hodgkin's lymphoma (NHL), and constitutes 30-40% of all cases in adults. DLBCL is heterogeneous in terms of its clinical course, and related molecular and genetic features. In the current era of appropriate chemo-immunotherapy, approximately 50%-60% of patients are cured after treatment. DLBCL is characterized by numerous chromosomal changes which are encountered in a high proportion of cases. OBJECTIVE: To examine whether the identification of chromosomal changes at time of diagnosis has prognostic significance in DLBCL. METHODS AND STUDY POPULATION: The study cohort included those patients with DLBCL, diagnosed and treated during 1996-2012 at the Hematology unit in Bnai-Zion Medical Center, Haifa, who had a cytogenetic study performed based on G-banding analysis from the original biopsy at the time of diagnosis. RESULTS: One hundred and twenty one patients with DLBCL were included and of these 59 also had chromosomal analysis performed from the tumor tissue at diagnosis. The average age of the cohort was 60.9 (21-87) years, and 59.3% were men. Average follow-up was 50.6 months (1-240 months). In 16 of the 59 biopsies (27.1%) lymphoma cells did not grow in vitro and analysis was not performed in these cases. Of the remaining 43 cases with chromosomal analysis: 36 (83.7%) had chromosomal aberrations, which most frequently involved chromosomes 14, 18, 1 and X. There was no difference in outcome between patients with chromosomal changes, including the presence of complex karyotype or hyperdiploidy (defined as > 50 chromosomes), and those with normal karyotype. CONCLUSIONS: Although complex changes in basic chromosomal structure and altered numbers of chromosomes were identified in patients with DLBCL, none of these features were of prognostic significance in terms of overall survival. In the light of these findings, we confirm that in common practice for DLBCL outside of clinical trials there appears to be no advantage to performing routine chromosomal studies on biopsy specimens obtained from patients with newly diagnosed DLBCL.

Explainable machine learning for chronic lymphocytic leukemia treatment prediction using only inexpensive tests.

BACKGROUND: Chronic lymphocytic leukemia (CLL) is one of the most common types of leukemia in the western world which affects mainly the elderly population. Progress of the disease is very heterogeneous both in terms of necessity of treatment and life expectancy. The current scoring system for prognostic evaluation of patients with CLL is called CLL-IPI and predicts the general progress of the disease but is not a measure or a decision aid for the necessity of treatment. Due to the heterogeneous behavior of CLL it is important to develop tools that will identify if and when patients will necessitate treatment for CLL. Recently, Machine Learning (ML) has spread to many public health fields including diagnosis and prognosis of diseases. OBJECTIVE: Existing machine learning methods for CLL treatment prediction rely on expensive tests, such as genetic tests, rendering them useless in peripheral or low-resource clinics such as those in developing countries. We aim to develop a model for predicting whether a patient will need treatment for CLL within two years of diagnosis using a machine learning model based on only on demographic data and routine laboratory tests. METHOD: We conducted a single center study that included adult patients (above the age of 18) that were diagnosed with CLL according to the IWCLL criteria and were under observation at the hematology unit of the Bnai-Zion medical center between 2009 and 2019. Patient data include demographic, clinical and laboratory measures that were extracted from patients' medical records anonymously. All laboratory results, during the observation period, were extracted for the entire cohort. Multiple ML approaches for classifying whether a patient will require treatment during a predetermined period of 2 years were evaluated. Performance of the ML models was measured using repeated cross validation. We evaluated the use of SHapley Additive exPlanation (SHAP) for explaining what influences the models decision. Additionally, we employ a method for extracting a single decision tree from the ML model which enables the doctor to understand the main logic governing the model prediction. RESULTS: The study included 109 patients of them 67 males (61%). Patients were under observation for a median of 44 months and the median age was 65 (age range: 45-87). 64% of the cohort received therapy during follow-up. A Gradient Boosting Model (GBM) model using all of the extracted variables to identify the need for treatment in the coming two years among patients with CLL achieved the AUPRC of 0.78 (±0.08). An identical GBM model, without genetic/FISH and flowcytometry (FACS) data, such that it can be used in peripheral clinics, scored an AUPRC of 0.7686 (±0.0837). A Generalized Linear Model (GLM) using the same features, scored an AUPRC of 0.7535 (±0.0995). All the models described above surpassed the performance of CLL-IPI that was evaluated using the CLL-TIM model. According to the SHAP results, red blood cell (RBC) count was the most predictive value for the necessity for treatment, where a high value is associated with a low probability of requiring treatment in the coming two years. Additionally, the SHAP method was used for estimating the personal risk of a random patient and showed sensible results. A simple Decision Tree classifier showed that patients who had a hemoglobin level of less than 13 gm/dL and a Neutrophil to Lymphocyte Ratio (NLR) less than 0.063, which constituted 34% percent of the patients included in our study, had a high probability (76%) of requiring treatment. CONCLUSIONS: Machine Learning algorithms that were evaluated in this work for predicting the necessity of treatment for patients with CLL achieved reasonable accuracy which surpassed that of CLL-IPI which was evaluated using the CLL-TIM model. Furthermore, we found that a machine learning model trained exclusively using inexpensive features only incurred a modest decrease in performance compared to the model trained using all of the features. Due to the small number of patients in this study it is necessary to validate the results on a larger population.

Deletions and amplifications of the IGH variable and constant regions:a novel prognostic parameter in patients with multiple myeloma.

Cytogenetic abnormalities are a recognized factor in the pathogenesis of multiple myeloma (MM). While chromosomal translocations involving the IGH gene have been investigated and reported, the implications of deletions or amplifications in the IGH gene have been less frequently examined. We conducted a retrospective analysis of 260 patients with MM from Northern Israel. Fluorescent in situ hybridization (FISH) analysis of separated CD-138 positive cells was done on bone marrow samples collected between 2016 and 2018. We used IGH break apart probes to identify IGH abnormalities and performed statistical analysis of clinical and prognostic features, comparing the different cytogenetic groups. Deletions in the variable region of the IGH (IGHv) were found in 17.3 % (n = 45) of patients and correlated with significantly worse progression free survival (PFS) after two years of follow up (p = 0.008), as well as with a worse response to 1st line treatment (p = 0.037). The median PFS was 7.1 and 17.7 months in patients with and without IGHv deletion, respectively. PFS differences remained significant (p = 0.017) in subgroup analysis of patients with high-risk cytogenetics (n = 108, 19 with IGHv deletion). Overall survival was not significantly different in the two groups. Constant region (IGHc) amplifications, were less frequently found (6.15 %, n = 16), yet significantly correlated with worse PFS after two years of follow up (p = 0.023). This difference remained valid in the high-risk subgroup (p = 0.001). In Conclusion, we identified that deletion of the IGH variable region and amplification in the IGH constant region, are both associated with poor prognosis and inferior outcome in MM.