Diagnosis Of MD Research Articles

Automated measurement of hydrops ratio from MRI in patients with M\xe9ni\xe8re\u2019s disease using CNN-based segmentation

Ménière’s Disease (MD) is difficult to diagnose and evaluate objectively over the course of treatment. Recently, several studies have reported MD diagnoses by MRI-based endolymphatic hydrops (EH) analysis. However, this method is time-consuming and complicated. Therefore, a fast, objective, and accurate evaluation tool is necessary. The purpose of this study was to develop an algorithm that can accurately analyze EH on intravenous (IV) gadolinium (Gd)-enhanced inner-ear MRI using artificial intelligence (AI) with deep learning. In this study, we developed a convolutional neural network (CNN)-based deep-learning model named INHEARIT (INner ear Hydrops Estimation via ARtificial InTelligence) for the automatic segmentation of the cochlea and vestibule, and calculation of the EH ratio in the segmented region. Measurement of the EH ratio was performed manually by a neuro-otologist and neuro-radiologist and by estimation with the INHEARIT model and were highly consistent (intraclass correlation coefficient = 0.971). This is the first study to demonstrate that automated EH ratio measurements are possible, which is important in the current clinical context where the usefulness of IV-Gd inner-ear MRI for MD diagnosis is increasing.

Psychological functioning in children suspected for mitochondrial disease: the need for care

BackgroundMitochondrial diseases (MD) are generally serious and progressive, inherited metabolic diseases. There is a high comorbidity of anxiety and depression and limitations in daily functioning. The complexity and duration of the diagnostic process and lack of knowledge about prognosis leads to uncertainty. In this study, we investigated the psychological well-being of children who are suspected for MD and their parents.MethodsIn total 122 children suspected for MD and their parents, received questionnaires as part of standard clinical investigation.ResultsParent proxy report revealed a lower quality of life (QoL) compared to norms and even more physical problems compared to chronically ill patients. They also reported more behavioral problems in general and more internalizing problems compared to the norms. Most frequent reported somatic complaints were tiredness and pain. Parents did not report enhanced levels of stress regarding parenting and experienced sufficient social support. At the end of the diagnostic process, 5.7% of the children received the genetically confirmed diagnosis of MD, 26% showed non-conclusive abnormalities in the muscle biopsy, 54% did not receive any diagnosis, and the remaining received other diagnoses. Strikingly, children without a diagnosis showed equally QoL and behavioral problems as children with a diagnosis, and even more internalizing problems.ConclusionsThis study highlights the psychological concerns of children with a suspicion of MD. It is important to realize that as well as children with a confirmed diagnosis, children without a diagnosis are vulnerable since explanation for their complaints is still lacking.

M\xe9n\xe9trier\u2019s disease in childhood: a case report from China

BackgroundMénétrier’s disease (MD) is a protein-losing gastropathy characterized by gastric hypertrophy, foveolar hyperplasia and hypoalbuminemia. MD is uncommon in childhood with nonspecific clinical symptoms, and the exact cause of pediatric MD is still unclear.Case presentationHere, we reported a 4 year and 10-month boy presenting with MD from China. The patient was suffered with vomiting, abdominal pain, hypoproteinemia and edema. Laboratory tests showed that the boy was infected with Clostridium difficile (CD). Gastrointestinal endoscopy revealed giant gastric folds, and histological gastric biopsies showed foveolar hyperplasia with glandular atrophy, infiltration of eosinophils in the lamina propria of the patient. Finally, the boy was recovered after supportive therapy with intravenous albumin and CD eradication.ConclusionFor the nonspecific clinical symptoms of MD, gastrointestinal endoscopic evaluations with gastric tissue biopsies are required to establish the diagnosis of MD in children with unexplained hypoalbuminemia.

The Relationship Between Tests of Hearing and Vestibular Function and the Duration of Symptoms in Patients With Unilateral Ménière's Disease

PurposeMénière's disease (MD) is a constellation of otologic symptoms that includes aural fullness, tinnitus, hearing loss, and episodic vertigo. Even though the criteria for diagnosing the disorder was set forth in 1972, the causes are still not well understood. The purpose of this study was to describe the relationships between tests of hearing and vestibular function and length of time patients diagnosed with unilateral MD have experienced symptoms.MethodThe charts of 254 patients with definite unilateral MD from the Mayo Clinic database were retrospectively reviewed. In order to be included, patients must have reported active MD diagnosis within the previous 5 years. Main outcome measures were results for audiometry, cervical vestibular evoked myogenic potentials, ocular vestibular evoked myogenic potentials, caloric test findings, video head impulse test, and sinusoidal harmonic acceleration.ResultsResults indicate there is a significant effect of the duration of MD symptoms reported by the patient and findings on some tests of hearing and vestibular function. Specifically, pure-tone average, caloric paresis, and rotational chair phase were all positively correlated with duration of symptoms. Rotational chair gain was found to have an inverse relationship with time. We did not find that video head impulse test gain or certain vestibular evoked myogenic potential measures were significantly correlated with the reported duration of patient symptoms.ConclusionsOur results suggest that, although the duration of symptoms reported by the patient does correlate with a number of vestibular and hearing tests, the relationships are relatively weak. The number of attacks and severity of symptoms should be investigated to determine if they are better predictors of laboratory testing results in the patient with MD.

Chart validation of an algorithm for identifying hereditary progressive muscular dystrophy in healthcare claims

BackgroundMuscular dystrophies (MDs) are a group of inherited conditions characterized by progressive muscle degeneration and weakness. The rarity and heterogeneity of the population with MD have hindered therapeutic developments as well as epidemiological and health outcomes research. The objective of the study was to develop and validate a case-finding algorithm utilizing administrative claims data to identify and characterize patients with MD.MethodsThis retrospective cohort study used medical chart validation to evaluate an ICD-9/10 coding algorithm in a large commercial claims database. Patients were identified who had ≥2 office visits with a diagnosis of hereditary progressive MDs from January 1, 2013 through December 31, 2016, were male, and younger than 18 years at the time of first MD diagnosis. Cases who met the algorithm were then validated against medical charts. Diagnoses of MD and specific type (Duchenne, Becker, or other MD) were confirmed by medical chart review by trained reviewers. Positive predictive value (PPV) and 95% confidence intervals (CI) were calculated using a 2 × 2 contingence table. Patient demographic, clinical, and health utilization characteristics were summarized using basic descriptive statistics.ResultsCharts were obtained and reviewed for 109 patients who met the algorithm. The PPV of the case-identifying algorithm for MD was 95% (95% CI 88–98%). Of the 103 confirmed MD cases, 87 patients (85%, 95% CI 76–91%) had Duchenne or Becker MD; 76 patients (74%, 95% CI 64–82%) had Duchenne MD, and 11 patients (11%, 95% CI 5–18%) had Becker MD. A total of 74 (67.9%) patients had ≥1 pediatric complex chronic condition (other than neurologic/neuromuscular disease); 54 (49.5%) had cardiovascular conditions; 14 (12.8%) had respiratory conditions; 50 (45.9%) had bone-related issues; 11 (10.1%) had impaired growth; and 6 (5.5%) had puberty delay.ConclusionsThe results of this study demonstrate that the case-finding algorithm accurately identified patients with MD, primarily Duchenne MD, within a large administrative database. The algorithm, which was constructed using a few items easily accessible from claims, can be used to facilitate epidemiological and health outcomes research in the Duchenne patient population.

Histamine H4 receptor gene polymorphisms: a potential contributor to Meniere disease

BackgroundThe immune system is likely involved in the pathophysiology of Meniere’s disease (MD). However, its role of patients with MD has not been well studied. Given that histamine H4 receptors are highly expressed in immune system, we tested the hypothesis that histamine H4 receptor gene polymorphisms are a potential contributor to the risk of MD.MethodsA group of patients was enrolled with a diagnosis of definite MD based on the American Academy of Otolaryngology-Head and Neck Surgery Committee on Hearing and Equilibrium guidelines and a control group of patients without any vestibular disease. We selected one SNP, rs77485247 in HRH4 and conducted an exploratory investigation of its correlations with the symptoms of vertigo and proinflammatory cytokines levels in MD patients.ResultsHRH4 rs77485247 polymorphism may be associated with the risk of MD. Furthermore, basal levels of proinflammatory cytokines, such as IL-1β and TNF-α, in PBMCs are increased in patients with MD compared to control patients. This increased basal level of proinflammatory cytokines is prominent in MD patients with the A allele.ConclusionsThese suggested that HRH4 rs77485247 polymorphism may be an important mediator in regulating proinflammatory cytokines, which are involved in the pathogenesis of MD.

Interactions between FKBP5 variation and environmental stressors in adolescent Major Depression

ObjectiveMajor Depression (MD) results from a complex interplay between environmental stressors and biological factors. Previous studies in adults have shown that adverse life events interact with genetic variation in FKBP5, a gene implicated in the stress-response system, to predict depressive symptoms and MD. This is the first study to investigate interactions between FKBP5 variants and a range of environmental stressors in adolescents with a clinical diagnosis of MD. Method148 male and female adolescents with MD and 143 typically developing (TD) controls (13-18 years) were included in the present study. For self-reported environmental stressors, subjective severity was assessed to allow a classification of these factors as mild, moderate and severe. Sociodemographic stressors were assessed via parental-report. ResultsWith a heightened number of sociodemographic, moderate and total number of stressors, participants carrying at least one copy of the FKBP5 CATT haplotype or at least one minor allele of various FKBP5 SNPs had the highest risk for being in the MD group. No genetic main effects were found. Sociodemographic stressors as well as self-reported mild, moderate, and severe stressors were more common in depressed than in TD adolescents. ConclusionThis is the first study to show interactions between genetic variation in FKBP5 and environmental stressors in a sample of clinically depressed adolescents. The current study provides important starting-points for preventive efforts and highlights the need for a fine-grained analysis of different forms and severities of environmental stressors and their interplay with genetic variation for understanding the complex etiology of (youth) MD.

Natural outbreak of Marek's disease in indigenous chicken and Japanese quail (Coturnix coturnix japonica) in Jos, Plateau State, Nigeria.

Carcasses of an indigenous adult chicken and Japanese quail from different flocks were presented to a veterinary clinic for postmortem (PM) examination in 2014 in Jos, Plateau State, Nigeria. PM observations revealed cutaneous, hepatic, and splenic tumors in the Indigenous chicken. The quail carcass was emaciated with hepatic tumors. Histopathology revealed severe focally extensive non-encapsulated circumscribed large nodules with pleomorphic population of cells mainly composed of lymphoplasmacytic and mixed neutrophilic polymorphonuclear cells in the chicken. The pleomorphic infiltration of lymphohistioplasmacytic cells mixed with neutrophilic polymorphonuclear cells in the quail was consistent with Marek’s disease virus (MDV) infection. Polymerase chain reaction (PCR) was carried out, and the Meq oncogene of the MDV was amplified in the samples collected from the chicken and quail to confirm the presence of the virulent MDV. The samples were also subjected to PCR for detection of MDV Rispens CVI988 vaccine strain which was detected in both chicken and quail samples. The findings in this study represent the first report of confirmatory diagnosis of MD using histopathology in an indigenous chicken and Japanese quail in Nigeria. It is also the first report of the detection of MDV Rispens CVI988 vaccine strain in unvaccinated chicken and quail in Nigeria.

21 - POLYGENIC AND PLEIOTROPIC EFFECTS ON CLINICAL HETEROGENEITY IN MAJOR DEPRESSION

Background Currently, a diagnosis of MD requires that at least five of nine DSM accessory symptoms be present, although patients vary with respect to the particular combination of symptoms endorsed. These nine criteria do not appear to reflect a single underlying genetic factor; instead, concordance among 7,500 adult twin pairs was best explained by three factors representing psychomotor/cognitive, mood, and neurovegetative dimensions of MD (Kendler et al. 2013). In particular, neurovegetative and reversed neurovegetative symptoms—reflecting depression-related changes in weight, appetite, and sleep—seem to implicate energy balance, and despite numerous associations between MD and relevant, comorbid medical conditions (e.g. obesity), there has been limited research on shared liability that addresses heterogeneity in a genetically informed framework. Methods Using detailed clinical information and molecular genetic data from the CONVERGE study of MD in Han Chinese women, along with publicly available genome-wide summary statistics, we consider the evidence in support of widespread pleiotropy between MD and a range of anthropometric traits and metabolic outcomes, and compare the polygenic profiles of MD cases reporting contrasting neurovegetative and reversed neurovegetative symptoms. Results We observe significant and robust trans-ancestry genetic correlations between MD and numerous traits. Of particular interest are the directions of observed genetic correlations; for example, in the CONVERGE study, MD is negatively genetically correlated with BMI, Type 2 Diabetes, waist circumference, and fasting glucose (P Discussion We consider the evidence in support of specific and aggregate genetic influences on clinical heterogeneity. In collaboration with independent large-scale European studies, we attempt to replicate and fine-map detected loci. We discuss implications of convergent pleiotropy and comorbidity between psychiatric and metabolic outcomes for genetic studies of multifactorial traits.

8PREVALENCE OF CLINICALLY WELL-ESTABLISHED CNV SYNDROMES WITHIN A TORONTO SCHIZOPHRENIA PATIENT POPULATION

There is an increasing interest in the putative role of glucagon-like peptide 1 receptor (GLP-1R) agonists as novel therapeutic agents for mental disorders. Herein, we investigated the expressions of GLP-1R and GLP-2R genes, and its relationship with body mass index (BMI), in the post-mortem brain tissue of patients with mood (MD) and psychotic disorders. Brain samples were localized to the dorsolateral prefrontal cortex (dlPFC) (n = 459) and hippocampus (n = 378). After adjustment for age, sex, ethnicity, post-mortem interval (PMI) and BMI, we observed significant differences, between healthy controls and MD subjects, in GLP-1R and GLP-2R gene expression in the dlPFC (β = 1.504, p = 0.004; and β = 1.305, p = 0.011, respectively); whereas in the hippocampus, only GLP-1R expression was significantly associated with MD (β = −1.28, p = 0.029). No significant differences were found in relation to schizophrenia. In addition, we observed a moderating effect of MD diagnosis on the associations between BMI, GLP-1R and GLP-2R expression values in the dlPFC (β = −0.05, p = 0.003; and β = −0.04, p = 0.004, respectively). There was a similar moderating effect for GLP-1R in the hippocampus (β = 0.043, 95% CI 0.003; 0.08 p = 0.03), but in an opposite direction than observed in the dlPFC. This is the first evidence of abnormal gene expression of GLP-1R and GLP-2R in postmortem brain of individuals with MD, providing a rationale for further inquiry and proof of principle interventional studies.

S.21.01 Molecular and synaptic mechanisms underlying cognitive malfunction and cognitive enhancement

There is an increasing interest in the putative role of glucagon-like peptide 1 receptor (GLP-1R) agonists as novel therapeutic agents for mental disorders. Herein, we investigated the expressions of GLP-1R and GLP-2R genes, and its relationship with body mass index (BMI), in the post-mortem brain tissue of patients with mood (MD) and psychotic disorders. Brain samples were localized to the dorsolateral prefrontal cortex (dlPFC) (n = 459) and hippocampus (n = 378). After adjustment for age, sex, ethnicity, post-mortem interval (PMI) and BMI, we observed significant differences, between healthy controls and MD subjects, in GLP-1R and GLP-2R gene expression in the dlPFC (β = 1.504, p = 0.004; and β = 1.305, p = 0.011, respectively); whereas in the hippocampus, only GLP-1R expression was significantly associated with MD (β = −1.28, p = 0.029). No significant differences were found in relation to schizophrenia. In addition, we observed a moderating effect of MD diagnosis on the associations between BMI, GLP-1R and GLP-2R expression values in the dlPFC (β = −0.05, p = 0.003; and β = −0.04, p = 0.004, respectively). There was a similar moderating effect for GLP-1R in the hippocampus (β = 0.043, 95% CI 0.003; 0.08 p = 0.03), but in an opposite direction than observed in the dlPFC. This is the first evidence of abnormal gene expression of GLP-1R and GLP-2R in postmortem brain of individuals with MD, providing a rationale for further inquiry and proof of principle interventional studies.

S.05.04 RNA processing impairments in neurodegeneration syndromes

There is an increasing interest in the putative role of glucagon-like peptide 1 receptor (GLP-1R) agonists as novel therapeutic agents for mental disorders. Herein, we investigated the expressions of GLP-1R and GLP-2R genes, and its relationship with body mass index (BMI), in the post-mortem brain tissue of patients with mood (MD) and psychotic disorders. Brain samples were localized to the dorsolateral prefrontal cortex (dlPFC) (n = 459) and hippocampus (n = 378). After adjustment for age, sex, ethnicity, post-mortem interval (PMI) and BMI, we observed significant differences, between healthy controls and MD subjects, in GLP-1R and GLP-2R gene expression in the dlPFC (β = 1.504, p = 0.004; and β = 1.305, p = 0.011, respectively); whereas in the hippocampus, only GLP-1R expression was significantly associated with MD (β = −1.28, p = 0.029). No significant differences were found in relation to schizophrenia. In addition, we observed a moderating effect of MD diagnosis on the associations between BMI, GLP-1R and GLP-2R expression values in the dlPFC (β = −0.05, p = 0.003; and β = −0.04, p = 0.004, respectively). There was a similar moderating effect for GLP-1R in the hippocampus (β = 0.043, 95% CI 0.003; 0.08 p = 0.03), but in an opposite direction than observed in the dlPFC. This is the first evidence of abnormal gene expression of GLP-1R and GLP-2R in postmortem brain of individuals with MD, providing a rationale for further inquiry and proof of principle interventional studies.

Characteristic Diagnostic Clues of Metatropic Dysplasia: The Lumbothoracic Humpback with Dumbbell Appearance of the Long Bones.

Metatropic dysplasia (MD) is a rare skeletal dysplasia associated with heterozygous mutations in the TRPV4 gene. We describe a 28-month-old boy with knock-knees referred for metabolic investigation suspected of carrying vitamin D-resistant rickets. He has received regular vitamin D prophylaxis at the usual dose. Laboratory investigations revealed normal values for calcium, phosphorus and alkaline phosphatase. He was short (-3.5 SDS), his mental development was normal, and he started to walk at the age of 22 months. The diagnostic clue for the diagnosis of metatropic dysplasia was the presence of the hump back in the upper lumbar and lower thoracic vertebrae, in addition to a long and narrow chest. An X-ray survey of the skeleton revealed platyspondyly, dysplastic metaphyses with dumbbell appearance of the long bones, kyphoscoliosis, and narrow and elongated thorax with short ribs. This is the first patient with MD in the Republic of Macedonia. Knock-knees were the cause of his referral, as a peculiarity of his phenotype. The very presence of the hump back, and the dumbbell appearance of the long bones distinguished the MD from other bone dysplasias with similar characteristics. We believe that the presence of those two features can shorten the path to accurate diagnosis in the crowded field of overlapping skeletal dysplasias. The diagnosis of MD in this patient was further confirmed by the discovery of the mutation c.2396C>T; p.Pro799Leu (P799L) of the TRPV4 gene.

A retrospective analysis of health care utilization for patients with mitochondrial disease in the United States: 2008\u20132015

BackgroundMitochondrial disease (MD) is a heterogeneous group of disorders characterized by impaired energy production caused by abnormal oxidative phosphorylation. Diagnosis of MD is challenging given the variability in how the disease can affect an individual’s neurologic, cardiovascular, ophthalmologic, or gastroenterological systems. This study describes the health care utilization and cost in patients diagnosed with MD.MethodsThis study was a retrospective claims analysis based on data from the Truven Health Analytics MarketScan Database and Milliman’s Consolidated Health Cost Guidelines Sources Database. For the purpose of this study the diagnosis of MD was defined by ICD-9-CM (prior to October 2015), and ICD-10-CM (October 2015 or later), and included patients identified between January 1, 2008 to December 31, 2015. ICD-9-CM code of 277.87 (disorders of mitochondrial metabolism) and the ICD-10-CM codes of E88.40, E88.41, E88.42 and E88.49 (mitochondrial metabolism disorders) were used as inclusive criteria. Patients were included if they had at least six months of exposure after the first MD-related claim occurrence, and either one MD claim in the inpatient setting OR two MD claims in an outpatient setting. Claims of MD patients are compared to those of a general insured total member population, as well as to those from multiple sclerosis (MS) and amyotrophic lateral sclerosis (ALS) patients.ResultsDuring the study period, 3825 patients between the ages of 0 and 15 (pediatric) and 4358 patients 16 years of age and greater (adult) were identified. Total allowed per member per month (PMPM) cost for pediatric patients was $4829 and $3100 for adults, compared with an average of $202 and $486, respectively, for the total member population. The greatest drivers of costs based on allowed claims came from inpatient, surgery, and prescription medications. In the adult population, MD imposes a PMPM cost burden that was comparable to that observed for multiple sclerosis ($3518) and ALS ($3460) patients.ConclusionsThis retrospective claim study highlights the significant differences in the cost of medical care for MD patients compared to those of a general population. Mitochondrial disorders are associated with multisystem disease manifestations and a greater care and cost burden similar to other devastating neuromuscular diseases.

The effect of body mass index on glucagon-like peptide receptor gene expression in the post mortem brain from individuals with mood and psychotic disorders

There is an increasing interest in the putative role of glucagon-like peptide 1 receptor (GLP-1R) agonists as novel therapeutic agents for mental disorders. Herein, we investigated the expressions of GLP-1R and GLP-2R genes, and its relationship with body mass index (BMI), in the post-mortem brain tissue of patients with mood (MD) and psychotic disorders. Brain samples were localized to the dorsolateral prefrontal cortex (dlPFC) (n = 459) and hippocampus (n = 378). After adjustment for age, sex, ethnicity, post-mortem interval (PMI) and BMI, we observed significant differences, between healthy controls and MD subjects, in GLP-1R and GLP-2R gene expression in the dlPFC (β = 1.504, p = 0.004; and β = 1.305, p = 0.011, respectively); whereas in the hippocampus, only GLP-1R expression was significantly associated with MD (β = −1.28, p = 0.029). No significant differences were found in relation to schizophrenia. In addition, we observed a moderating effect of MD diagnosis on the associations between BMI, GLP-1R and GLP-2R expression values in the dlPFC (β = −0.05, p = 0.003; and β = −0.04, p = 0.004, respectively). There was a similar moderating effect for GLP-1R in the hippocampus (β = 0.043, 95% CI 0.003; 0.08 p = 0.03), but in an opposite direction than observed in the dlPFC. This is the first evidence of abnormal gene expression of GLP-1R and GLP-2R in postmortem brain of individuals with MD, providing a rationale for further inquiry and proof of principle interventional studies.

Divertículo de Meckel volvulado asociado a brida como causa de obstrucción en intestino delgado

Introduction: Meckel’s diverticulum is the most frequent gastrointestinal anomaly. It’s more frequently seen in children less than 2 years of age. It´s caused by the incomplete obliteration of the omphalomesenteric conduct. Case report: 19 year old male patient with no previous medical history presents sudden onset of high intensity abdominal pain, initially located in the periumbilical region, radiating to right lower quadrant associated with emesis, fever and tachycardia. Physical examination showed abdominal guarding, rebound tenderness and decreased bowel sounds. During McBurney laparotomy a large volume of viscous free fluid was found and signs of small bowel obstruction, deciding close McBurney laparotomy and performing sub-umbilical midline laparotomy. Meckel diverticulum is founded, twisted and strangled, with a bridle adhesion to the mesenteric root, compromising the small bowel. The adherence and the MD are resected, obtaining appropriate peristaltic activity and color. Appendectomy and peritoneal lavage are performed without complications. Discussion: preoperatory diagnosis of MD is unfrequented and its need surgical exploration. MD’s volvulus is infrequent and in our case, intestinal obstruction it´s secondary to an adherence between the volvulated MD and the mesentery.

Prognostic Value of Combined Clinical and Myocardial Perfusion Imaging Data Using Machine Learning

ObjectivesThis study evaluated the added predictive value of combining clinical information and myocardial perfusion single-photon emission computed tomography (SPECT) imaging (MPI) data using machine learning (ML) to predict major adverse cardiac events (MACE). BackgroundTraditionally, prognostication by MPI has relied on visual or quantitative analysis of images without objective consideration of the clinical data. ML permits a large number of variables to be considered in combination and at a level of complexity beyond the human clinical reader. MethodsA total of 2,619 consecutive patients (48% men; 62 ± 13 years of age) who underwent exercise (38%) or pharmacological stress (62%) with high-speed SPECT MPI were monitored for MACE. Twenty-eight clinical variables, 17 stress test variables, and 25 imaging variables (including total perfusion deficit [TPD]) were recorded. Areas under the receiver-operating characteristic curve (AUC) for MACE prediction were compared among: 1) ML with all available data (ML-combined); 2) ML with only imaging data (ML-imaging); 3) 5-point scale visual diagnosis (physician [MD] diagnosis); and 4) automated quantitative imaging analysis (stress TPD and ischemic TPD). ML involved automated variable selection by information gain ranking, model building with a boosted ensemble algorithm, and 10-fold stratified cross validation. ResultsDuring follow-up (3.2 ± 0.6 years), 239 patients (9.1%) had MACE. MACE prediction was significantly higher for ML-combined than ML-imaging (AUC: 0.81 vs. 0.78; p < 0.01). ML-combined also had higher predictive accuracy compared with MD diagnosis, automated stress TPD, and automated ischemic TPD (AUC: 0.81 vs. 0.65 vs. 0.73 vs. 0.71, respectively; p < 0.01 for all). Risk reclassification for ML-combined compared with visual MD diagnosis was 26% (p < 0.001). ConclusionsML combined with both clinical and imaging data variables was found to have high predictive accuracy for 3-year risk of MACE and was superior to existing visual or automated perfusion assessments. ML could allow integration of clinical and imaging data for personalized MACE risk computations in patients undergoing SPECT MPI.

Efficacy of an active implementation process of a computerized CPG of major depression disorder in primary care

IntroductionThe application of scientific evidence in clinical practice management of Major Depressive Disorder (MDD) is complex. Generally, the usual dissemination process and implementation of Clinical Practice Guidelines (CPG) induce modest changes. A computerized version of a Clinical Practice Guideline for Major Depression (e-CPG-MD) has been integrated in Electronic Clinical Records of Primary Care in Catalonia (Spain). It offers an opportunity to improve clinical results. The design allows access to precise help in the visit itself, improving diagnosis, treatment and follow-up.ObjectivesTo evaluate the effects of a multifaceted implementation process of e-CPG-MD, analysing their use and changes in MDD diagnosis.MethodsA cluster randomized clinical trial was performed in 10 primary care centers (PCC) in Barcelona. In five of ten centers, a multifaceted implementation process of the e-CPG-MD was developed during 6 month. The active process includes: interactive training program, regular feedback audit, educational outreach visits and periodic reminders.ResultsThe multifaceted implementation of e-CPG-MD was associated with a significant increase in use during the first 6 months (4.1% + 3.1% vs. 52.7% + 7.3%, P &lt; 0.001). In the active centers, the MD diagnosis increased significantly (rate quotient = 1.56, P &lt; 0.001) and the proportion of moderate and severe MD increased (13.6% vs 41.1%, P = 0.002).ConclusionsA multifaceted implementation method of e-CPG-MD increased significantly its use in active centers at 6 months. Diagnosis of MDD and the proportion of moderate and severe cases also increased significantly.Disclosure of interestThe authors have not supplied their declaration of competing interest.

Predictive diagnosis of major depression using NMR-based metabolomics and least-squares support vector machine

BackgroundMajor depressive (MD) disorder is a serious psychiatric disorder that can result in suicidal behavior if not treated. The MD diagnosis using a standardized instrument instead of a structured interview will be advantageous for treatment and management of the MD, but so far no such technique exists. We developed an integrated analytical method of NMR-based metabolomics and least squares-support vector machine (LS-SVM) for predictive diagnosis of the MD. MethodsThe metabolite profiles in clinical plasma samples obtained from 72 depressive patients and 54 healthy subjects were analyzed by NMR spectroscopy. Then, LS-SVM models with different kernels were trained and tested using 80% and 20% of samples, respectively. ResultsWe found that the best performance for the MD prediction was achieved by LS-SVM equipped with RBF kernel. Moreover, the predictive performance of the MD using multi-biomarkers was largely improved as compared with that using a single biomarker. In this study, the LS-SVM-RBF using glucose-lipid signaling can achieve the MD prediction with the AUC values of 0.94 (0.89–0.99) in the training set and 0.96 (0.92–1.00) in the test set. ConclusionThe LS-SVM-RBF using glucose-lipid signaling obtained from NMR spectroscopy can be used as an auxiliary diagnostic tool for the MD.

Assessment of a Revised Management Strategy for Patients With Intraductal Papillary Mucinous Neoplasms Involving the Main Pancreatic Duct

According to the 2012 International Consensus Guidelines, the diagnostic criterion of intraductal papillary mucinous neoplasms (IPMNs) involving the main duct (MD IPMNs) or the main and branch ducts (mixed IPMNs) of the pancreatic system is a main pancreatic duct (MPD) diameter of 5.0 mm or greater on computed tomography (CT) or magnetic resonance imaging (MRI). However, surgical resection is recommended for patients with an MPD diameter of 10.0 mm or greater, which is characterized as a high-risk stigma. An MPD diameter of 5.0 to 9.0 mm is not an indication for immediate resection. To determine an appropriate cutoff (ie, one with high sensitivity and negative predictive value) of the MPD diameter on CT or MRI as a prognostic factor for malignant disease and to propose a new management algorithm for patients with MD or mixed IPMNs. This retrospective cohort study included 103 patients who underwent surgical resection for a preoperative diagnosis of MD or mixed IPMN and in whom IPMN was confirmed by surgical pathologic findings at a single institution from July 1, 1996, to December 31, 2015. Malignant disease was defined as high-grade dysplasia or invasive adenocarcinoma on results of surgical pathologic evaluation. An appropriate MPD diameter on preoperative CT or MRI to predict malignant disease was determined using a receiver operating characteristic curve analysis. The prognostic value of the new management algorithm that incorporated the new MPD diameter cutoff was evaluated. Among the 103 patients undergoing resection for an MD or mixed IPMN (59 men [57.3%]; 44 women [42.7%]; median [range] age, 71 [48-86] years), 64 (62.1%) had malignant disease. Diagnostic accuracy for malignant neoplasms was highest at an MPD diameter cutoff of 7.2 mm (area under the receiver operating characteristic curve, 0.70; 95% CI, 0.59-0.81). An MPD diameter of 7.2 mm or greater was also an independent prognostic factor for malignant neoplasms (odds ratio, 12.76; 95% CI, 2.43-66.88; P = .003) on logistic regression analysis after controlling for preoperative variables. The new management algorithm, which included an MPD diameter of 7.2 mm or greater as one of the high-risk stigmata, had a higher sensitivity (100%), negative predictive value (100%), and accuracy (66%) for malignant disease than the 2012 version of the International Consensus Guidelines (95%, 57%, and 63%, respectively). In this single-center, retrospective analysis, an MPD diameter of 7.2 mm was identified as an optimal cutoff for a prognostic factor for malignant disease in MD or mixed IPMN. These data support lowering the accepted criteria for MPD diameter when selecting patients for resection vs surveillance so as not to overlook cancer in IPMN.