Validation of a new multiple osteochondromas classification through Switching Neural Networks

Imaging of solitary and multiple osteochondromas: From head to toe - A review

Osteochondromas account for 20%-50% of all benign bone lesions. These tumors may present as solitary non-hereditary lesions, which are the most common presentation, or as multiple tumors associated with hereditary conditions. Plain radiography is the imaging method of choice and demonstrates the typical cortical and medullary continuity of the tumor with the underlying bone. Magnetic resonance imaging is often performed to evaluate cartilage cap thickness, which correlates with malignant transformation. Other local complications include compression of adjacent neurovascular bundles, muscles, and tendons, bursitis, tendon tears, stalk fracture, and angular or rotational long bone deformities. Although the imaging features of osteochondromas are largely known, only a few papers in the literature have focused on their main complications and image-based follow-up. This paper aimed to illustrate the main complications of osteochondromas, suggest an image-based algorithm for management and follow-up and discuss differential diagnosis.

Artificial intelligence and ChatGPT in Orthopaedics and sports medicine

Artificial intelligence (AI) is looked upon nowadays as the potential major catalyst for the fourth industrial revolution. In the last decade, AI use in Orthopaedics increased approximately tenfold. Artificial intelligence helps with tracking activities, evaluating diagnostic images, predicting injury risk, and several other uses. Chat Generated Pre-trained Transformer (ChatGPT), which is an AI-chatbot, represents an extremely controversial topic in the academic community. The aim of this review article is to simplify the concept of AI and study the extent of AI use in Orthopaedics and sports medicine literature. Additionally, the article will also evaluate the role of ChatGPT in scientific research and publications.Level of evidence: Level V, letter to review.

The Impact of Artificial Intelligence in the Odyssey of Rare Diseases

Emerging machine learning (ML) technologies have the potential to significantly improve the research and treatment of rare diseases, which constitute a vast set of diseases that affect a small proportion of the total population. Artificial Intelligence (AI) algorithms can help to quickly identify patterns and associations that would be difficult or impossible for human analysts to detect. Predictive modeling techniques, such as deep learning, have been used to forecast the progression of rare diseases, enabling the development of more targeted treatments. Moreover, AI has also shown promise in the field of drug development for rare diseases with the identification of subpopulations of patients who may be most likely to respond to a particular drug. This review aims to highlight the achievements of AI algorithms in the study of rare diseases in the past decade and advise researchers on which methods have proven to be most effective. The review will focus on specific rare diseases, as defined by a prevalence rate that does not exceed 1-9/100,000 on Orphanet, and will examine which AI methods have been most successful in their study. We believe this review can guide clinicians and researchers in the successful application of ML in rare diseases.

Clinical survey of a pedigree with hereditary multiple exostoses and identification of EXT‑2 gene deletion mutation

The aim of the present study was to report a clinical survey of hereditary multiple exostoses (HME) in a large Chinese pedigree, and the identification of a novel deletion mutation of exostosin glycosyltransferase 2 (EXT‑2) gene. A patient with multiple exostoses with huge cartilage‑capped tumors in scapula, knees and ankles received surgery in Department of Orthopedics (Shanghai Changhai Hospital). A total of 20 family members were recruited to the study, with seven members (five male; two female) diagnosed as HME. The family members of the patients with HME were examined, clinical data and peripheral blood samples were collected, and their DNA was sequenced. The incidence of HME in this family pedigree was 35%. Exostoses were most frequently in the tibiae with occurrence in six patients, followed by ribs, femurs, radii, fibulae, scapulae and humeri. DNA sequencing of peripheral blood revealed a novel deletion mutation, c.824‑826delGCA, in exon 5 of the EXT‑2 gene, which was observed in all the patients with HME, but not in the healthy family members. Several characteristics of HME in the pedigree were observed, such as susceptibility of male gender, decreased average age of onset and height and increased severity of clinical symptoms with generations.

Hereditary Multiple Exostoses-A Review of the Molecular Background, Diagnostics, and Potential Therapeutic Strategies

Hereditary multiple exostoses (HMEs) syndrome, also known as multiple osteochondromas, represents a rare and severe human skeletal disorder. The disease is characterized by multiple benign cartilage-capped bony outgrowths, termed exostoses or osteochondromas, that locate most commonly in the juxta-epiphyseal portions of long bones. Affected individuals usually complain of persistent pain caused by the pressure on neighboring tissues, disturbance of blood circulation, or rarely by spinal cord compression. However, the most severe complication of this condition is malignant transformation into chondrosarcoma, occurring in up to 3.9% of HMEs patients. The disease results mainly from heterozygous loss-of-function alterations in the EXT1 or EXT2 genes, encoding Golgi-associated glycosyltransferases, responsible for heparan sulfate biosynthesis. Some of the patients with HMEs do not carry pathogenic variants in those genes, hence the presence of somatic mutations, deep intronic variants, or another genes/loci is suggested. This review presents the systematic analysis of current cellular and molecular concepts of HMEs along with clinical characteristics, clinical and molecular diagnostic methods, differential diagnosis, and potential treatment options.

Opportunities and Challenges for Machine Learning in Rare Diseases

Rare diseases (RDs) are complicated health conditions that are difficult to be managed at several levels. The scarcity of available data chiefly determines an intricate scenario even for experts and specialized clinicians, which in turn leads to the so called “diagnostic odyssey” for the patient. This situation calls for innovative solutions to support the decision process via quantitative and automated tools. Machine learning brings to the stage a wealth of powerful inference methods; however, matching the health conditions with advanced statistical techniques raises methodological, technological, and even ethical issues. In this contribution, we critically point to the specificities of the dialog of rare diseases with machine learning techniques concentrating on the key steps and challenges that may hamper or create actionable knowledge and value for the patient together with some on-field methodological suggestions and considerations.

The Rizzoli Multiple Osteochondromas Classification revised: describing the phenotype to improve clinical practice

Multiple osteochondromas (MO) is a rare disorder, characterized by benign osteocartilaginous tumors (osteochondromas), arising from the perichondrium of bones. The osteochondromas increase during growth, frequently causing deformities and limitations. Our study aims to analyze the data captured by the Registry of Multiple Osteochondromas, to refine Istituto Ortopedico Rizzoli (IOR) Classification, providing a representative picture of the phenotypic manifestations throughout the lifespan. We conducted a single‐institution cross‐sectional study. Patients were categorized according to IOR Classification, which identifies three patients' classes on the presence/absence of deformities and/or limitations. The present dataset was compared with our previously published data, to refine the classification. Nine hundred sixty‐eight patients were included: 243 children (<10 years), 136 adolescents (10–15 years), and 589 adults. Of the entire population, half patients presented at least one deformity, and one quarter reported at least one limitation. Compared with our previous study, the amount of children was more than doubled and the percentage of mild/moderate cases was notably increased, giving a better disease overview throughout the lifespan and suggesting a different cut‐off for dividing Class II in subclasses. We confirmed that MO is characterized by phenotypic heterogeneity, suggesting that an early classification of the disease may offer a useful tool to follow disease pattern and evolution, to support clinical practice, and to propose timely interventions.

Mutation spectrum of EXT1 and EXT2 in the Saudi patients with hereditary multiple exostoses

BACKGROUND

Hereditary Multiple Exostoses (HME), also known as Multiple Osteochondromas (MO) is a rare genetic disorder characterized by multiple benign cartilaginous bone tumors, which are caused by mutations in the genes for exostosin glycosyltransferase 1 (EXT1) and exostosin glycosyltransferase 2 (EXT2). The genetic defects have not been studied in the Saudi patients.

AIM OF STUDY

We investigated mutation spectrum of EXT1 and EXT2 in 22 patients from 17 unrelated families.

METHODS

Genomic DNA was extracted from peripheral leucocytes. The coding regions and intron-exon boundaries of both EXT1 and EXT2 genes were screened for mutations by PCR-sequencing analysis. Gross deletions were analyzed by MLPA analysis.

RESULTS

EXT1 mutations were detected in 6 families (35%) and 3 were novel mutations: c.739G > T (p. E247*), c.1319delG (p.R440Lfs*4), and c.1786delA (p.S596Afs*25). EXT2 mutations were detected in 7 families (41%) and 3 were novel mutations: c.541delG (p.D181Ifs*89), c.583delG (p.G195Vfs*75), and a gross deletion of approximately 10 kb including promoter and exon 1. Five patients from different families had no family history and carried de novo mutations (29%, 5/17). No EXT1 and EXT2 mutations were found in the remaining four families. In total, EXT1 and EXT2 mutations were found in 77% (13/17) of Saudi HME patients.

CONCLUSION

EXT1 and EXT2 mutations contribute significantly to the pathogenesis of HME in the Saudi population. In contrast to high mutation rate in EXT 1 (65%) and low mutation rate in EXT2 (25%) in other populations, the frequency of EXT2 mutations are much higher (41%) and comparable to that of EXT1 among Saudi patients. De novo mutations are also common and the six novel EXT1/EXT2 mutations further expands the mutation spectrum of HME.

An unusual example of hereditary multiple exostoses: a case report and review of the literature

Background

Hereditary multiple exostoses (HME) is a rare skeletal disorder characterised by a widespread.

distribution of osteochondromas originating from the metaphyses of long bones.

Case presentation

This case study examines a 55-year-old male cadaver bequeathed to the University of Liverpool who suffered from HME, thus providing an exceptionally rare opportunity to examine the anatomical changes associated with this condition.

Conclusions

Findings from imaging and dissection indicated that this was a severe case of HME in terms of the quantity and distribution of the osteochondromas and the number of synostoses present. In addition, the existence of enchondromas and the appearance of gaps within the trabeculae of affected bones make this a remarkable case. This study provides a comprehensive overview of the morbidity of the disease as well as adding to the growing evidence that diseases concerning benign cartilaginous tumours may be part of a spectrum rather than distinct entities.

Hereditary multiple osteochondromas in Jordanian patients: Mutational and immunohistochemical analysis of EXT1 and EXT2 genes

The aim of the present study was to investigate the molecular characteristics of hereditary multiple osteochondromas (HMO) in a subset of Jordanian patients with a focus on the genetic variants of exostosin (EXT1)/(EXT2) and their protein expression. Patients with HMO and their family members were included. Recorded clinical characteristics included age, sex, tumors number and location, joint deformities and associated functional limitations. Mutational analysis of EXT1 and EXT2 exonic regions was performed. Immunohistochemical staining for EXT1 and EXT2 was performed manually using two different commercially available rabbit anti-human EXT1 and EXT2 antibodies. A total of 16 patients with HMO from nine unrelated families were included, with a mean age of 13.9 years. A total of 75% (12/16) of the patients were male and (69%) (11/16) had a mild disease (class I). EXT mutation analysis revealed only EXT1 gene mutations in 13 patients. Seven variants were detected, among which three were novel: c.1019G>A, p. (Arg340His), c.962+1G>A and c.1469del, p. (Leu490Argfs*9). Of the 16 patients, 3 did not harbor any mutations for either EXT1 or EXT2. Immunohistochemical examination revealed decreased expression of EXT1 protein in all patients with EXT1 mutation. Surprisingly, EXT2 protein was not detected in these patients, although none had EXT2 mutations. The majority of Jordanian patients with HMO, who may represent an ethnic group that is infrequently investigated, were males and had a mild clinical disease course; whereas most patients with EXT1 gene mutations were not necessarily associated with a severe clinical disease course. The role of EXT2 gene remains a subject of debate, since patients with EXT1 mutations alone did not express the non-mutated EXT2 gene.

The natural history of multiple osteochondromas in a large Italian cohort of pediatric patients

IMPORTANCE

Multiple osteochondromas is a rare hereditary skeletal disorder, characterized by bony protrusions arising from growth plates on long bones during skeletal development. The disorder frequently leads to diminished stature, deformities and functional limitations. Understanding of the natural history of multiple osteochondromas and its evolution in children and adolescents is limited.

OBJECTIVE

To provide valuable information on the natural history of multiple osteochondromas, to inform recommendations for treatment and prevent impairments caused by osteochondromas.

DESIGN

This retrospective cohort study in children with multiple osteochondromas includes longitudinal data collected from first to last follow-up visit for patient demographics, and over 36 months for disease evolution.

SETTING

Data were collected from the Registry of Multiple Osteochondromas, which includes data from circa 1200 patients with multiple osteochondromas treated from 2003 to 2017 at IRCCS Istituto Ortopedico Rizzoli in Bologna.

PARTICIPANTS

Patients ≤18 years with multiple osteochondromas, who provided written informed consent and had data for ≥1 12-month follow-up visit.

MAIN OUTCOME(S) AND MEASUREMENT(S)

Demographics, clinical features, incidence of surgeries, and disease evolution (progression or regression) were assessed. Results were summarized using descriptive statistics, annual rates of new clinical features and surgeries, and Kaplan-Meier estimates. Patient height was evaluated following Italian growth charts.

RESULTS

158 patients were included in these analyses. Throughout follow-up, 80.4% of patients developed new osteochondromas, 57.6% developed new deformities, 23.4% developed new functional limitation(s). New osteochondroma(s) were developed by 28.5% patients by Month 12, 39.9% at Month 24, 50% at Month 36. Most new osteochondromas were detected in the younger population; patients aged 0-4 years underwent a significantly higher number of lesions within 12, 24 and 36 months of follow-up. The overall incidence of patients with ≥1 new deformity within 12 months was 17.7%, with incidences decreasing with increasing age (p = .023). In addition, the analyses on height highlight that 13 years is a cut off age for slow growth of the stature (p < .0005). At last follow-up visit, 46.2% of patients had disease progression, while regression (spontaneous and surgical) occurred in 7.6% (p = .007).

CONCLUSIONS AND RELEVANCE

This natural history study reports the main set of clinically relevant data for patients with multiple osteochondromas during skeletal development, providing insight for patient management and development of therapeutic interventions.

Identification of Novel EXT Mutations in Patients with Hereditary Multiple Exostoses Using Whole-Exome Sequencing

Objective

To find novel potential gene mutations other than EXT1 and EXT2 mutations, to expand the mutational spectrum of EXT and to explore the correlation between clinical outcome and genotype in patients with hereditary multiple exostoses (HME).

Methods

The study recruited seven families diagnosed with multiple osteochondromas (MO). Family histories and clinical information were collected in detail through comprehensive physical and image examination. Patients with deformities and functional limitations were classified as “severe” and the remaining without functional limitations were classified as “mild,” in accordance with previous study. Whole‐exome sequencing (WES) was performed on a total of 13 affected individuals, 1 available unaffected relative, and 10 healthy unrelated individuals. Sanger sequencing was used to validate the screened mutations. Finally, the structural change in protein caused by pathogenic mutations was analyzed using information from the relevant database online and we attempted to correlate clinical phenotype with genotype in patients with HME.

Results

Other than EXT1 and EXT2, no novel potential gene mutations were found through WES. We identified nine heterozygous mutations in EXT1 or EXT2. Of these mutations, four have not been reported previously. These are c.996delT in exon 2 of EXT1 (family 1), c.544C > T in exon 3 of EXT2 (family 2), c.1171C > T in exon 7 of EXT2 (family 5), and c.823_–824delAA in exon 5 of EXT1 (family 7). The other five mutations have already been reported in previous works. It was surprising that we found two mutation sites, in exon 2 and exon 5, respectively, of EXT1 in 1 patient diagnosed with MO, when his father had two mutation sites, in exon 6 and exon 5, respectively, of EXT1 and EXT2 (family 4). In addition, 1 patient showed degeneration, while his father only exhibited slight symptoms (family 7). In our study, among 51 affected patients in seven families, the sex ratio (male vs female) was 58.9% (n = 30) vs 41.2% (n = 21). Male patients seemed to show more severe symptoms compared to females, but because the sample was small, we did not obtain statistically significance results.

Conclusion

Whole‐exome sequencing to screen pathogenic gene mutations was applied successfully. Although no third‐gene mutation associated with HME was found, a total of nine mutations across EXT1 and EXT2 were identified, four of which are novel. Our results expand the mutational spectrum of EXT and can be used in genetic counseling and prenatal diagnosis for patients with MO.

Hereditary Multiple Exostoses: Current Insights

Hereditary multiple exostoses (HME), also called hereditary multiple osteochondromas, is a rare genetic disorder characterized by multiple osteochondromas that grow near the growth plates of bones such as the ribs, pelvis, vertebrae and especially long bones. The disease presents with various clinical manifestations including chronic pain syndromes, restricted range of motion, limb deformity, short stature, scoliosis and neurovascular alteration. Malignant transformation of exostosis is rarely seen. The disease has no medical treatment and surgery is only recommended in symptomatic exostoses or in cases where a malignant transformation is suspected. HME is mainly caused by mutations and functional loss of the EXT1 and EXT2 genes which encode glycosyltransferases, an enzyme family involved in heparan sulfate (HS) synthesis. However, the peculiar molecular mechanism that leads to the structural changes of the cartilage and to osteochondroma formation is still being studied. Basic science studies have recently shown new insights about altering the molecular and cellular mechanism caused by HS deficiency. Pediatricians, geneticists and orthopedic surgeons play an important role in the study and treatment of this severe pathology. Despite the recent significant advances, we still need novel insights to better specify the role of HS in signal transduction. The purpose of this review was to analyze the most relevant aspects of HME from the literature review, give readers an important tool to understand its clinical features and metabolic-pathogenetic mechanism, and to identify an effective treatment method. We focused on the aspects of the disease related to clinical management and surgical treatment in order to give up-to-date information that could be useful for following best clinical practice.

Videira P, Valadão G. Artificial Intelligence (AI) in Rare Diseases: Is the Future Brighter?

The amount of data collected and managed in (bio)medicine is ever-increasing. Thus, there is a need to rapidly and efficiently collect, analyze, and characterize all this information. Artificial intelligence (AI), with an emphasis on deep learning, holds great promise in this area and is already being successfully applied to basic research, diagnosis, drug discovery, and clinical trials. Rare diseases (RDs), which are severely underrepresented in basic and clinical research, can particularly benefit from AI technologies. Of the more than 7000 RDs described worldwide, only 5% have a treatment. The ability of AI technologies to integrate and analyze data from different sources (e.g., multi-omics, patient registries, and so on) can be used to overcome RDs’ challenges (e.g., low diagnostic rates, reduced number of patients, geographical dispersion, and so on). Ultimately, RDs’ AI-mediated knowledge could significantly boost therapy development. Presently, there are AI approaches being used in RDs and this review aims to collect and summarize these advances. A section dedicated to congenital disorders of glycosylation (CDG), a particular group of orphan RDs that can serve as a potential study model for other common diseases and RDs, has also been included.

Analyzing gene expression data for pediatric and adult cancer diagnosis using logic learning machine and standard supervised methods

Background

Logic Learning Machine (LLM) is an innovative method of supervised analysis capable of constructing models based on simple and intelligible rules.

In this investigation the performance of LLM in classifying patients with cancer was evaluated using a set of eight publicly available gene expression databases for cancer diagnosis.

LLM accuracy was assessed by summary ROC curve (sROC) analysis and estimated by the area under an sROC curve (sAUC). Its performance was compared in cross validation with that of standard supervised methods, namely: decision tree, artificial neural network, support vector machine (SVM) and k-nearest neighbor classifier.

Results

LLM showed an excellent accuracy (sAUC = 0.99, 95%CI: 0.98–1.0) and outperformed any other method except SVM.

Conclusions

LLM is a new powerful tool for the analysis of gene expression data for cancer diagnosis. Simple rules generated by LLM could contribute to a better understanding of cancer biology, potentially addressing therapeutic approaches.

Identification of a novel mutation in EXT2 in a fourth-generation Korean family with multiple osteochondromas and overview of mutation spectrum

Multiple osteochondromas (MOs) or hereditary multiple exostoses is a rare autosomal-dominant disease characterized by growths of MOs, which are benign cartilage-capped bone tumors that grow away from the growth plates. Almost 90% of MOs have a molecular explanation and 10% are unexplained. MOs are genetically heterogeneous with two causal genes on 8q24.11 (EXT1) and 11p12 (EXT2), with a higher frequency in EXT1. MO is a very rare genetic disorder, and the genotype-phenotype of MO with EXT2 mutation has not been well investigated in Korea. We present the clinical radiographic and molecular analysis of a four-generation Korean family with 11 MO-affected members (seven males and four females). The affected members from the third generation available for molecular analysis and their detailed medical histories showed moderate-to-severe phenotypes (clinical classes II-III), including bony deformities and limb misalignment with pain requiring surgical correction. The x-rays showed MOs in multiple sites. A novel EXT2 frameshift mutation (c.590delC, p.P197Qfs*73) was revealed by targeted exome sequencing in the affected members of this family. In this article, we not only expand the phenotypic-genotypic spectrum of MOs but also highlight the phenotypic heterogeneity in a family with the same mutation. In addition, we compiled the mutation spectrum of EXT2 from a literature review and identified that exon 2 of EXT2 is a mutation hot spot. Early medical attention with diagnosis of MO through careful examination of the clinical manifestations and genetic analysis can provide the opportunity to establish coordinated multispecialty management of the patient.

Is Routine Spine MRI Necessary in Skeletally Immature Patients With MHE? Identifying Patients at Risk for Spinal Osteochondromas

BACKGROUND

Multiple hereditary exostoses (MHE) is an autosomal dominant condition leading to development of osteochondromas throughout the body. Although long bones are most often affected, spine involvement may occur and usually requires advanced imaging for diagnosis. However, the high cost of detection, infrequent occurrence, and very low likelihood of spinal cord compression and neurological injury, create a management conundrum. The purpose of our investigation is to identify patients at greatest risk for spinal lesions and refine indications for advanced imaging.

METHODS

All MHE patients in a 24-year period were retrospectively reviewed. Skeletally immature patients with advanced imaging of the spine were further evaluated. The demographic characteristics, family history, clinical presentation, past surgical history, tumor burden, and distribution of patients with spinal lesions were compared with those without.

RESULTS

In total, 227 MHE patients were identified and 21 underwent advanced spinal imaging. Spinal lesions were found in 8 of the 21 screened patients (38.1%, 3.5% overall), of which 4 were intracanal and 1 was symptomatic (4.8%, 0.4% overall). Only the symptomatic patient underwent excision of the spinal lesion. Patients with spinal lesions had higher tumor burden than those without (median, 28.5 vs. 19 locations; P=0.010). There was a significant association with rib (P=0.018) and pelvic (P=0.007) lesions, which may serve as "harbinger" lesions. The presence of both a rib and a pelvic lesion used as a screening tool for spinal lesions produces a sensitivity of 100% and specificity of 69%.

CONCLUSIONS

Symptomatic spinal involvement in children with MHE is rare and tends to occur in patients with higher tumor burden. We recommend limiting advanced spine imaging to children with neurological symptoms or with rib and pelvic "harbinger" lesions. Patients without these findings are unlikely to have spine involvement needing intervention. This approach offers an opportunity to avoid unnecessary testing and substantially reduce costs of diagnostic imaging.

LEVEL OF EVIDENCE

Level III.

Machine Learning in Orthopedics: A Literature Review

In this paper we present the findings of a systematic literature review covering the articles published in the last two decades in which the authors described the application of a machine learning technique and method to an orthopedic problem or purpose. By searching both in the Scopus and Medline databases, we retrieved, screened and analyzed the content of 70 journal articles, and coded these resources following an iterative method within a Grounded Theory approach. We report the survey findings by outlining the articles' content in terms of the main machine learning techniques mentioned therein, the orthopedic application domains, the source data and the quality of their predictive performance.

Identifying Environmental and Social Factors Predisposing to Pathological Gambling Combining Standard Logistic Regression and Logic Learning Machine

Identifying potential risk factors for problem gambling (PG) is of primary importance for planning preventive and therapeutic interventions. We illustrate a new approach based on the combination of standard logistic regression and an innovative method of supervised data mining (Logic Learning Machine or LLM). Data were taken from a pilot cross-sectional study to identify subjects with PG behaviour, assessed by two internationally validated scales (SOGS and Lie/Bet). Information was obtained from 251 gamblers recruited in six betting establishments. Data on socio-demographic characteristics, lifestyle and cognitive-related factors, and type, place and frequency of preferred gambling were obtained by a self-administered questionnaire. The following variables associated with PG were identified: instant gratification games, alcohol abuse, cognitive distortion, illegal behaviours and having started gambling with a relative or a friend. Furthermore, the combination of LLM and LR indicated the presence of two different types of PG, namely: (a) daily gamblers, more prone to illegal behaviour, with poor money management skills and who started gambling at an early age, and (b) non-daily gamblers, characterised by superstitious beliefs and a higher preference for immediate reward games. Finally, instant gratification games were strongly associated with the number of games usually played. Studies on gamblers habitually frequently betting shops are rare. The finding of different types of PG by habitual gamblers deserves further analysis in larger studies. Advanced data mining algorithms, like LLM, are powerful tools and potentially useful in identifying risk factors for PG.

Hereditary Multiple Exostoses: a review of clinical appearance and metabolic pattern

Hereditary multiple exostoses (HME) is an inherited genetic condition characterized by the presence of multiple exostoses (osteochondromas). MHE is a relatively rare autosomal dominant disorder, mainly caused by loss of function mutations in two genes: exostosin-1 (EXT1) and exostosin-2 (EXT2). These genes are linked to heparan sulfate (HS) synthesis, but the specific molecular mechanism leading to the disruption of the cartilage structure and the consequent exostoses formation is still not resolved. The aim of this paper is to encounter the main aspects of HME reviewing the literature, in order to improve clinical features and evolution, and the metabolic-pathogenetic mechanisms underlying. Although MHE may be asymptomatic, a wide spectrum of clinical manifestations is found in paediatric patients with this disorder. Pain is experienced by the majority of patients, even restricted motion of the joint is often encountered. Sometimes exostoses can interfere with normal development of the growth plate, giving rise to limb deformities, low stature and scoliosis. Other many neurovascular and associated disorders can lead to surgery. The most feared complication is the malignant transformation of an existing osteochondroma into a secondary peripheral chondrosarcoma, during adulthood. The therapeutic approach to HME is substantially surgical, whereas the medical one is still at an experimental level. In conclusion, HME is a complex disease where the paediatrician, the geneticist and the orthopaedic surgeon play an interchangeable role in diagnosis, research and therapy. We are waiting for new studies able to explain better the role of HS in signal transduction, because it plays a role in other bone and cartilage diseases (in particular malignant degeneration) as well as in skeletal embryology.

Differential diagnosis of pleural mesothelioma using Logic Learning Machine

BACKGROUND

Tumour markers are standard tools for the differential diagnosis of cancer. However, the occurrence of nonspecific symptoms and different malignancies involving the same cancer site may lead to a high proportion of misclassifications. Classification accuracy can be improved by combining information from different markers using standard data mining techniques, like Decision Tree (DT), Artificial Neural Network (ANN), and k-Nearest Neighbour (KNN) classifier. Unfortunately, each method suffers from some unavoidable limitations. DT, in general, tends to show a low classification performance, whereas ANN and KNN produce a "black-box" classification that does not provide biological information useful for clinical purposes.

METHODS

Logic Learning Machine (LLM) is an innovative method of supervised data analysis capable of building classifiers described by a set of intelligible rules including simple conditions in their antecedent part. It is essentially an efficient implementation of the Switching Neural Network model and reaches excellent classification accuracy while keeping low the computational demand. LLM was applied to data from a consecutive cohort of 169 patients admitted for diagnosis to two pulmonary departments in Northern Italy from 2009 to 2011. Patients included 52 malignant pleural mesotheliomas (MPM), 62 pleural metastases (MTX) from other tumours and 55 benign diseases (BD) associated with pleurisies. Concentration of three tumour markers (CEA, CYFRA 21-1 and SMRP) was measured in the pleural fluid of each patient and a cytological examination was also carried out. The performance of LLM and that of three competing methods (DT, KNN and ANN) was assessed by leave-one-out cross-validation.

RESULTS

LLM outperformed all other considered methods. Global accuracy was 77.5% for LLM, 72.8% for DT, 54.4% for KNN, and 63.9% for ANN, respectively. In more details, LLM correctly classified 79% of MPM, 66% of MTX and 89% of BD. The corresponding figures for DT were: MPM = 83%, MTX = 55% and BD = 84%; for KNN: MPM = 58%, MTX = 45%, BD = 62%; for ANN: MPM = 71%, MTX = 47%, BD = 76%. Finally, LLM provided classification rules in a very good agreement with a priori knowledge about the biological role of the considered tumour markers.

CONCLUSIONS

LLM is a new flexible tool potentially useful for the differential diagnosis of pleural mesothelioma.

Scoliosis in patients with multiple hereditary exostoses

PURPOSE

To investigate the prevalence of and to identify independent predictors associated with scoliosis in patients with multiple hereditary exostoses (MHE).

METHODS

Fifty patients with MHE were clinically examined, and the diagnosis of scoliosis was made based on radiographs. To classify disease severity, three classes based on the presence of deformities and functional limitations were defined. Significant independent predictors of scoliosis in MHE were statistically analyzed.

RESULTS

Scoliosis was present in 36 patients (MHE-scoliosis) (72 %). In the MHE-scoliosis group, the mean primary curve was 15.3° ± 5.7° (range 10°-34°) and the mean minor curve was 10.6° ± 7° (range 6°-32°). Left curve was predominant (72 %), and the apex was located in the thoracolumbar or lumbar spine in 64 % of patients. Univariable and multivariable analyses confirmed that MHE severity was a significant predictor of moderate scoliosis (≥20°).

CONCLUSIONS

Our study confirmed that scoliosis is a common feature of MHE and disease severity is a predictor of moderate scoliosis (≥20°).