Prediction of diagnosis and diastolic filling pressure by AI-enhanced cardiac MRI: a modelling study of hospital data.

BACKGROUND: With increasing numbers of patients and novel drugs for distinct causes of systolic and diastolic heart failure, automated assessment of cardiac function is important. We aimed to provide a non-invasive method to predict diagnosis of patients undergoing cardiac MRI (cMRI) and to obtain left ventricular end-diastolic pressure (LVEDP). METHODS: For this modelling study, patients who had undergone cardiac catheterisation at University Hospital Heidelberg (Heidelberg, Germany) between July 15, 2004 and March 16, 2023, were identified, as were individual left ventricular pressure measurements. We used existing patient data from routine cardiac diagnostics. From this initial group, we extracted patients who had been diagnosed with ischaemic cardiomyopathy, dilated cardiomyopathy, hypertrophic cardiomyopathy, or amyloidosis, as well as control individuals with no structural phenotype. Data were pseudonymised and only processed within the university hospital's AI infrastructure. We used the data to build different models to predict either demographic (ie, AI-age and AI-sex), diagnostic (ie, AI-coronary artery disease and AI-cardiomyopathy [AI-CMP]), or functional parameters (ie, AI-LVEDP). We randomly divided our datasets via computer into training, validation, and test datasets. AI-CMP was not compared with other models, but was validated in a prospective setting. Benchmarking was also done. FINDINGS: 66 936 patients who had undergone cardiac catheterisation at University Hospital Heidelberg were identified, with more than 183 772 individual left ventricular pressure measurements. We extracted 4390 patients from this initial group, of whom 1131 (25·8%) had been diagnosed with ischaemic cardiomyopathy, 1064 (24·2%) had been diagnosed with dilated cardiomyopathy, 816 (18·6%) had been diagnosed with hypertrophic cardiomyopathy, 202 (4·6%) had been diagnosed with amyloidosis, and 1177 (26·7%) were control individuals with no structural phenotype. The core cohort only included patients with cardiac catherisation and cMRI within 30 days, and emergency cases were excluded. AI-sex was able to predict patient sex with areas under the receiver operating characteristic curves (AUCs) of 0·78 (95% CI 0·77-0·78) and AI-age was able to predict patient age with a mean absolute error of 7·86 years (7·77-7·95), with a Pearson correlation of 0·57 (95% CI 0·56-0·57). The AUCs for the classification tasks ranged between 0·82 (95% CI 0·79-0·84) for ischaemic cardiomyopathy and 0·92 (0·91-0·94) for hypertrophic cardiomyopathy. INTERPRETATION: Our AI models could be easily integrated into clinical practice and provide added value to the information content of cMRI, allowing for disease classification and prediction of diastolic function. FUNDING: Informatics for Life initiative of the Klaus-Tschira Foundation, German Center for Cardiovascular Research, eCardiology section of the German Cardiac Society, and AI Health Innovation Cluster Heidelberg.

Improving sudden cardiac death risk stratification in hypertrophic cardiomyopathy using established clinical variables and genetic information.

BACKGROUND AND AIMS: The cardiac societies of Europe and the United States have established different risk models for preventing sudden cardiac death (SCD) in hypertrophic cardiomyopathy (HCM). The aim of this study is to validate current SCD risk prediction methods in a German HCM cohort and to improve them by the addition of genotype information. METHODS: HCM patients without prior SCD or equivalent arrhythmic events ≥ 18 years of age were enrolled in an expert cardiomyopathy center in Germany. The primary endpoint was defined as SCD/-equivalent within 5 years of baseline evaluation. 5-year SCD-risk estimates and recommendations for ICD implantations, as defined by the ESC and AHA/ACC guidelines, were analyzed. Multivariate cox proportional hazards analyses were integrated with genetic findings as additive SCD risk. RESULTS: 283 patients were included and followed for in median 5.77 years (2.92; 8.85). A disease-causing variant was found in 138 (49%) patients. 14 (5%) patients reached the SCD endpoint (5-year incidence 4.9%). Kaplan-Meier survival analysis shows significantly lower overall SCD event-free survival for patients with an identified disease-causing variant (p < 0.05). The ESC HCM Risk-SCD model showed an area-under-the-curve (AUC) of 0.74 (95% CI 0.68-0.79; p < 0.0001) with a sensitivity of 0.29 (95% CI 0.08-0.58) and specificity of 0.83 (95% CI 0.78-0.88) for a risk estimate ≥ 6%/5-years. By comparison, the AHA/ACC HCM SCD risk stratification model showed an AUC of 0.70 (95% CI 0.65-0.76; p = 0.003) with a sensitivity of 0.93 (95% CI, 0.66-0.998) and specificity of 0.28 (95% CI 0.23-0.34) at the respective cut-off. The modified SCD Risk Score with genetic information yielded an AUC of 0.76 (95% CI 0.71-0.81; p < 0.0001) with a sensitivity of 0.86 (95% CI 0.57-0.98) and specificity of 0.69 (95% CI 0.63-0.74). The number-needed-to-treat (NNT) to prevent 1 SCD event by prophylactic ICD-implantation is 13 for the ESC model, 28 for AHA/ACC and 9 for the modified Genotype-model. CONCLUSION: This study confirms the performance of current risk models in clinical decision making. The integration of genetic findings into current SCD risk stratification methods seem feasible and can add in decision making, especially in borderline risk-groups. A subgroup of patients with high SCD risk remains unidentified by current risk scores.

New Air-Jet Dry Powder Insufflator for High-Efficiency Aerosol Delivery to Rats.

Pulmonary deposition of lung-targeted therapeutic aerosols can achieve direct drug delivery to the site of action, thereby enhancing the efficacy and reducing systemic exposure. In this study, we investigated the in vitro and in vivo aerosol performance of the novel small animal air-jet dry powder insufflator (Rat AJ DPI) using spray-dried albuterol excipient-enhanced-growth (EEG) powder as a model formulation. The in vitro aerosolization performance of the optimized albuterol EEG powder was first assessed using the Rat AJ DPI. The performance of Rat AJ DPI to deliver albuterol EEG aerosol to rat lungs was then compared to that of the Penn-Century Insufflator. Albuterol EEG powders dispersed using the Rat AJ DPI demonstrated narrow unimodal aerosol size distribution profiles, which were independent of the loaded powder dose (1, 2, and 5 mg). In addition, the span value for Rat AJ DPI (5 mg powder mass) was 1.32, which was 4.2-fold lower than that for Penn-Century insufflator (5 mg powder mass). At a higher loaded mass of 5 mg, the Rat AJ DPI delivered significantly larger doses to rat lungs compared with the Penn-Century DPI. The Rat AJ DPI with hand actuation delivered approximately 85% of the total emitted dose (2 and 5 mg loadings), which was comparatively higher than that for Penn-Century DPI (approximately 75%). In addition, percentage deposition in each of the lung lobes for the Rat AJ DPI was observed to be independent of the administration dose (2 and 5 mg loadings) with coefficients of variation below 12%, except in the right middle lobe. Automatic actuation of a 5 mg powder mass using the Rat AJ DPI demonstrated a similar delivered dose compared to manual actuation of the same dose, with 82% of the total emitted dose reaching the lung lobes. High-efficiency delivery of the aerosol to the lobar lung region and low sensitivity of the interlobar delivery efficiency to the loaded dose highlight the suitability of the new air-jet DPI for administering therapeutic pharmaceutical aerosols to small test animals.

Renewable solar and wind energies on buildings for green ports in Egypt.

Energy management plan is utilized as an optimum strategy by using solar and wind energies, as a new preliminary implementation. The aim of the study is to create an optimum strategy through an optimization of an energy management system. The study implemented an onsite model, two numerical approaches, and an optimization analysis on a Mediterranean port. Two approaches have been used: solar energy is applied experimentally and numerically, and then wind energy is simulated. An optimization analysis integrated the two approaches together to control their operation. The results showed the installed solar panels provided sufficient generated power for the buildings. Also, the simulated wind arrays showed good behavior with increased power coefficient for the wind turbines, for future implementation. These results were validated using the DesignBuilder software and showed accurate values regarding the experiment for solar panels and CFD simulation. Eventually, a Pareto optimality analysis is applied between the solar and wind energies to reveal an energy management plan. Renewable energy offered energy to support the consumption of the port's buildings.

Genotype Complements the Phenotype: Identification of the Pathogenicity of an LMNA Splice Variant by Nanopore Long-Read Sequencing in a Large DCM Family.

Dilated cardiomyopathy (DCM) is a common cause of heart failure (HF) and is of familial origin in 20−40% of cases. Genetic testing by next-generation sequencing (NGS) has yielded a definite diagnosis in many cases; however, some remain elusive. In this study, we used a combination of NGS, human-induced pluripotent-stem-cell-derived cardiomyocytes (iPSC-CMs) and nanopore long-read sequencing to identify the causal variant in a multi-generational pedigree of DCM. A four-generation family with familial DCM was investigated. Next-generation sequencing (NGS) was performed on 22 family members. Skin biopsies from two affected family members were used to generate iPSCs, which were then differentiated into iPSC-CMs. Short-read RNA sequencing was used for the evaluation of the target gene expression, and long-read RNA nanopore sequencing was used to evaluate the relevance of the splice variants. The pedigree suggested a highly penetrant, autosomal dominant mode of inheritance. The phenotype of the family was suggestive of laminopathy, but previous genetic testing using both Sanger and panel sequencing only yielded conflicting evidence for LMNA p.R644C (rs142000963), which was not fully segregated. By re-sequencing four additional affected family members, further non-coding LMNA variants could be detected: rs149339264, rs199686967, rs201379016, and rs794728589. To explore the roles of these variants, iPSC-CMs were generated. RNA sequencing showed the LMNA expression levels to be significantly lower in the iPSC-CMs of the LMNA variant carriers. We demonstrated a dysregulated sarcomeric structure and altered calcium homeostasis in the iPSC-CMs of the LMNA variant carriers. Using targeted nanopore long-read sequencing, we revealed the biological significance of the variant c.356+1G>A, which generates a novel 5' splice site in exon 1 of the cardiac isomer of LMNA, causing a nonsense mRNA product with almost complete RNA decay and haploinsufficiency. Using novel molecular analysis and nanopore technology, we demonstrated the pathogenesis of the rs794728589 (c.356+1G>A) splice variant in LMNA. This study highlights the importance of precise diagnostics in the clinical management and workup of cardiomyopathies.

Safety and Efficacy of Ledipasvir/Sofosbuvir in the Treatment of Chronic Hepatitis C Virus Infection in Treatment-Naïve Children without and with Comorbidities.

BACKGROUND: Chronic hepatitis C virus (HCV) infection represents a crucial health problem in children that greatly influences their quality of life. Many efforts have been directed toward investing in effective drugs with a high safety profile and oral administration for better compliance. OBJECTIVES: This study aims to assess the safety of a fixed-dose combination of ledipasvir/sofosbuvir plus drug efficacy and sustained virologic response (SVR) at 12 weeks after treatment discontinuation. METHOD: One tablet (90 mg ledipasvir, 400 mg sofosbuvir) was administered to treatment-naïve children aged 12-18 years weighing at least 35 kg with chronic HCV infection for 6 months, genotype 4. Patients were divided into 2 groups, (1) without comorbidities (24 patients) and (2) with comorbidities (26 patients). RESULTS: At the end of the therapy, all patients (100%) had SVR and a significant reduction of liver enzymes with mild tolerable side effects. CONCLUSION: Ledipasvir/sofosbuvir fixed-dose combination is a safe and highly effective therapeutic option in Egyptian children aged ≥ 12 years, with chronic HCV infection, genotype 4, either without or with comorbidities.

Structured, Harmonized, and Interoperable Integration of Clinical Routine Data to Compute Heart Failure Risk Scores.

Risk prediction in patients with heart failure (HF) is essential to improve the tailoring of preventive, diagnostic, and therapeutic strategies for the individual patient, and effectively use health care resources. Risk scores derived from controlled clinical studies can be used to calculate the risk of mortality and HF hospitalizations. However, these scores are poorly implemented into routine care, predominantly because their calculation requires considerable efforts in practice and necessary data often are not available in an interoperable format. In this work, we demonstrate the feasibility of a multi-site solution to derive and calculate two exemplary HF scores from clinical routine data (MAGGIC score with six continuous and eight categorical variables; Barcelona Bio-HF score with five continuous and six categorical variables). Within HiGHmed, a German Medical Informatics Initiative consortium, we implemented an interoperable solution, collecting a harmonized HF-phenotypic core data set (CDS) within the openEHR framework. Our approach minimizes the need for manual data entry by automatically retrieving data from primary systems. We show, across five participating medical centers, that the implemented structures to execute dedicated data queries, followed by harmonized data processing and score calculation, work well in practice. In summary, we demonstrated the feasibility of clinical routine data usage across multiple partner sites to compute HF risk scores. This solution can be extended to a large spectrum of applications in clinical care.

An eye on the future for defeating hydrocephalus, ciliary dyskinesia-related hydrocephalus: review article.

Congenital hydrocephalus affects approximately one in 1000 newborn children and is fatal in approximately 50% of untreated cases. The currently known management protocols usually necessitate multiple interventions and long-term use of healthcare resources due to a relatively high incidence of complications, and many of them mostly provide a treatment of the effect rather than the cause of cerebrospinal fluid flow reduction or outflow obstruction. Future studies discussing etiology specific hydrocephalus alternative treatments are needed. We systematically reviewed the available literature on the effect of ciliary abnormality on congenital hydrocephalus pathogenesis, to open a discussion on the feasibility of factoring ciliary abnormality in future research on hydrocephalus treatment modalities. Although there are different forms of ciliopathies, we focused in this review on primary ciliary dyskinesia. There is growing evidence of association of other ciliary syndromes and hydrocephalus, such as the reduced generation of multiple motile cilia, which is distinct from primary ciliary dyskinesia. Data for this review were identified by searching PubMed using the search terms 'hydrocephalus,' 'Kartagener syndrome,' 'primary ciliary dyskinesia,' and 'immotile cilia syndrome.' Only articles published in English and reporting human patients were included. Seven studies met our inclusion criteria, reporting 12 cases of hydrocephalus associated with primary ciliary dyskinesia. The patients had variable clinical presentations, genetic backgrounds, and ciliary defects. The ependymal water propelling cilia differ in structure and function from the mucus propelling cilia, and there is a possibility of isolated non-syndromic ependymal ciliopathy causing only hydrocephalus with growing evidence in the literature for the association ependymal ciliary abnormality and hydrocephalus. Abdominal and thoracic situs in children with hydrocephalus can be evaluated, and secondary damage of ependymal cilia causing hydrocephalus in cases with generalized ciliary abnormality can be considered.

Controlling my genome with my smartphone: first clinical experiences of the PROMISE system.

BACKGROUND: The development of Precision Medicine strategies requires high-dimensional phenotypic and genomic data, both of which are highly privacy-sensitive data types. Conventional data management systems lack the capabilities to sufficiently handle the expected large quantities of such sensitive data in a secure manner. PROMISE is a genetic data management concept that implements a highly secure platform for data exchange while preserving patient interests, privacy, and autonomy. METHODS: The concept of PROMISE to democratize genetic data was developed by an interdisciplinary team. It integrates a sophisticated cryptographic concept that allows only the patient to grant selective access to defined parts of his genetic information with single DNA base-pair resolution cryptography. The PROMISE system was developed for research purposes to evaluate the concept in a pilot study with nineteen cardiomyopathy patients undergoing genotyping, questionnaires, and longitudinal follow-up. RESULTS: The safety of genetic data was very important to 79%, and patients generally regarded the data as highly sensitive. More than half the patients reported that their attitude towards the handling of genetic data has changed after using the PROMISE app for 4 months (median). The patients reported higher confidence in data security and willingness to share their data with commercial third parties, including pharmaceutical companies (increase from 5 to 32%). CONCLUSION: PROMISE democratizes genomic data by a transparent, secure, and patient-centric approach. This clinical pilot study evaluating a genetic data infrastructure is unique and shows that patient's acceptance of data sharing can be increased by patient-centric decision-making.

An Apple Watch Dashboard for HiGHmed Heart Insufficency Patients.

Wearables are commercially available devices allowing continuous monitoring of users' health parameters. Their easy availability, increasing accuracy and functionality render them relevant for medical practice, specifically for longitudinal monitoring. There are clear benefits for the health care system, such as the opportunity of timely interventions by monitoring a patient during his daily life, resulting in a cost reduction in medical care and improved patient well-being. However, some tools are essential to enable the application of wearables in medical daily practice. For example, there is a need for software solutions that allow clinicians to quickly and easily analyze data from devices of their patients. The goal of this study was to develop a dashboard for physicians, which allows rapid data interpretation of longitudinal data from the Apple Watch. The prototype dashboard is an interactive web-based visualization platform utilizing Plotly. The dashboard displays the most important parameters like heart rate, steps per day, activity, exercise collected by the Apple Watch in a user-friendly and accessible way. Clear visualization makes it easy to identify trends or deviations in the data and see how these changes in daily behaviour affect patients' health. Our software is a key component to monitor patients with heart failure who participate in the HiGHmed use case cardiology project.

Impact of IL10, MTP, SOD2, and APOE Gene Polymorphisms on the Severity of Liver Fibrosis Induced by HCV Genotype 4.

Complications of hepatitis C virus (HCV) chronic infection cause ~400,000 deaths worldwide annually. One complication, liver fibrosis, is influenced by host genetic factors. Genes influencing fibrosis include immune, metabolic, oxidative stress, and viral entry genes, such as interleukin 10 (IL10), microsomal triglyceride-transfer protein (MTP), superoxide dismutase-2 (SOD2), and apolipoprotein E (APOE)-encoding genes, respectively. Thus, correlating variations in these genes with HCV-induced fibrosis represents an attractive biomarker for the prognosis of fibrosis severity in chronically infected patients. Here, we aimed to test whether polymorphisms in IL10, MTP, SOD2, and APOE genes correlated with the severity of fibrosis induced by HCV genotype 4 (HCV-gt4) in a cohort of chronically infected Egyptian patients. Our results demonstrate a significant association between the severity of fibrosis and specific SNPs in IL-10, SOD2, and ApoE-encoding genes. Haplotype-combination analysis for IL10, MTP, SOD2, and APOE showed statistically significant associations between specific haplotype combinations and fibrosis severity. Identifying biomarkers correlating with the severity of HCV-gt4-induced fibrosis would significantly impact precision prophylaxis and treatment of patients at risk.

Energy Metabolites as Biomarkers in Ischemic and Dilated Cardiomyopathy.

With more than 25 million people affected, heart failure (HF) is a global threat. As energy production pathways are known to play a pivotal role in HF, we sought here to identify key metabolic changes in ischemic- and non-ischemic HF by using a multi-OMICS approach. Serum metabolites and mRNAseq and epigenetic DNA methylation profiles were analyzed from blood and left ventricular heart biopsy specimens of the same individuals. In total we collected serum from n = 82 patients with Dilated Cardiomyopathy (DCM) and n = 51 controls in the screening stage. We identified several metabolites involved in glycolysis and citric acid cycle to be elevated up to 5.7-fold in DCM (p = 1.7 × 10-6). Interestingly, cardiac mRNA and epigenetic changes of genes encoding rate-limiting enzymes of these pathways could also be found and validated in our second stage of metabolite assessment in n = 52 DCM, n = 39 ischemic HF and n = 57 controls. In conclusion, we identified a new set of metabolomic biomarkers for HF. We were able to identify underlying biological cascades that potentially represent suitable intervention targets.

Insulin Resistance and Non-Alcoholic Fatty Liver Disease in Premenopausal Women with Metabolic Syndrome.

It is suggested that estrogen protects premenopausal women against non-alcoholic fatty liver disease. From another perspective, the relation between metabolic syndrome (MetS) and non-alcoholic fatty liver disease (NAFLD) is bidirectional. Role of insulin resistance (IR) in NAFLD continues to be a matter of debate. The present study aimed to assess the relation between IR and NAFLD in premenopausal women with MetS. The study included 51 premenopausal women with MetS. In addition, there were 40 age-matched healthy controls. All participants were subjected to careful history taking and thorough clinical examination. Performed laboratory investigations included fasting blood glucose, fasting insulin, lipid profile, and liver functions. Calculation of IR was achieved by the Homeostasis Model Assessment (HOMA-IR). NAFLD was graded into three grades according to findings of abdominal ultrasound. Patients had significantly higher BMI, SBP, DBP, FBG, fasting insulin, HOMA-IR, total cholesterol, triglycerides, and LDL levels when compared with controls. They also had significantly lower HDL levels in comparison to controls. Moreover, they have more advanced grades of NAFLD in contrast to controls. Comparison between patients with various grades of NAFLD regarding the clinical data revealed significant increase of fasting insulin and HOMA-IR levels with advancing NAFLD grade. Using multivariate regression analysis, HOMA-IR was an independent predictor of advanced NAFLD grade. In conclusion, the present study documented a combined inter-relation between MetS, IR, and NAFLD in premenopausal women with MetS. IR is correlated with NAFLD grade.

Predictors for hepatocellular carcinoma recurrence after microwave ablation.

AIM OF THE STUDY: Microwave ablation (MWA) for treatment of hepatocellular carcinoma (HCC) is a new promising modality. The prognosis after treatment is mainly linked to the recurrence. We aimed to investigate the predictive value of α-fetoprotein (AFP) score and Aurora B kinase (AURKB) in HCC recurrence after MWA. MATERIAL AND METHODS: A cross-sectional study where 25 early-stage HCC patients (Barcelona Clinic Liver Cancer 0/A-B) were treated with MWA. Tumor biopsies were obtained just prior to MWA and assessed for WHO pathological grade and AURKB expression by immunohistochemistry. AFP score was calculated and a cut-off value of 2 classifies patients into high and low risk of recurrence. After achieving complete ablation, patients were followed every 3 months for 1 year by triphasic CT to detect recurrence. RESULTS: Child-Pugh classification has no significant impact on prognosis of HCC after MWA (χ2 = 1.924, p = 0.165). Serum AFP level and AFP score can effectively predict the response to MWA among HCC patients (χ2 = 6.451, MC p = 0.031) (χ2 = 9.0, p = 0.003), respectively. AFP score was strongly associated with the pathological grade of the tumor (r = 0.467, p = 0.019). AURKB was over-expressed in tumoral more than non-tumoral specimens (p < 0.001). It was correlated with the size of the tumor, the number of tumor nodules and the pathological grade of the tumor (p < 0.05) but has no role in predicting recurrence after MWA (p = 0.869). CONCLUSIONS: AFP score but not AURKB can predict the risk of recurrence of HCC after MWA.

The Patient as Genomic Data Manager - Evaluation of the PROMISE App.

PROMISE (Personal Medical Safe) was a German research project which aimed to provide the responsibility of genomic data to the patient via a mobile app. The patient should accept or decline study requests to use his/her genomic data via the app. In the evaluation of the app the experiences with mobile health as well as the opinion on being the genomic data manager were measured. Furthermore, the test patients were asked about their opinion and their concerns on the PROMISE app. Most of the 19 test patients were aware of the high sensibility of genomic data and thought that the PROMISE app was a suitable solution. The largest part found it good that they were the responsible data owner. However, several participants also found it important to have a permanent contact person when it comes to questions on inquiries or the app.

Two Hearts at Risk: Emergency Alcohol Septal Ablation in a Pregnant Woman With Decompensated HOCM.

Hypertrophic obstructive cardiomyopathy (HOCM) increases the risk for mother and fetus during pregnancy. Alcohol septal ablation (ASA) is an established procedure in nonpregnant patients with HOCM. In this report, we present a case of a 29-year-old woman in her 29th gestational week with decompensated HOCM undergoing a successful ASA. (Level of Difficulty: Advanced.).

The chameleon of cardiology: cardiac sarcoidosis before and after heart transplantation.

Cardiac sarcoidosis is a chronic inflammatory disease with a large spectrum of symptoms that can mimic diseases such as dilated, hypertrophic, or arrhythmogenic cardiomyopathies. It can be asymptomatic but can also present with ventricular arrhythmias, conduction disease, and heart failure (HF) or even sudden cardiac death (SCD). We present here the case of a patient transplanted due to end-stage arrhythmogenic right ventricular cardiomyopathy (ARVC), fulfilling the task force criteria. A few years after successful heart transplantation (HTX), the patient developed similar symptoms and morphofunctional changes of the heart, which led to critical re-evaluation of his primary diagnosis.

Deep Learning Approaches Outperform Conventional Strategies in De-Identification of German Medical Reports.

One of the major obstacles for research on German medical reports is the lack of de-identified medical corpora. Previous de-identification tasks focused on non-German medical texts, which raised the demand for an in-depth evaluation of de-identification methods on German medical texts. Because of remarkable advancements in natural language processing using supervised machine learning methods on limited training data, we evaluated them for the first time on German medical reports using our annotated data set consisting of 113 medical reports from the cardiology domain. We applied state-of-the-art deep learning methods using pre-trained models as input to a bidirectional LSTM network and well-established conditional random fields for de-identification of German medical reports. We performed an extensive evaluation for de-identification and multiclass named entity recognition. Using rule based and out of domain machine learning methods as a baseline, the conditional random field improved F2-score from 70 to 93% for de-identification, the neural approach reached 96% in F2-score while keeping balanced precision and recall rates. These results show, that state-of-the-art machine learning methods can play a crucial role in de-identification of German medical reports.

Clinical and genetic insights into non-compaction: a meta-analysis and systematic review on 7598 individuals.

BACKGROUND: Left ventricular non-compaction has been increasingly diagnosed in recent years. However, it is still debated whether non-compaction is a pathological condition or a physiological trait. In this meta-analysis and systematic review, we compare studies, which investigated these two different perspectives. Furthermore, we provide a comprehensive overview on the clinical outcome as well as genetic background of left ventricular non-compaction cardiomyopathy in adult patients. METHODS AND RESULTS: We retrieved PubMed/Medline literatures in English language from 2000 to 19/09/2018 on clinical outcome and genotype of patients with non-compaction. We summarized and extensively reviewed all studies that passed selection criteria and performed a meta-analysis on key phenotypic parameters. Altogether, 35 studies with 2271 non-compaction patients were included in our meta-analysis. The mean age at diagnosis was the mid of their fifth decade. Two-thirds of patients were male. Congenital heart diseases including atrial or ventricular septum defect or Ebstein anomaly were reported in 7% of patients. Twenty-four percent presented with family history of cardiomyopathy. The mean frequency of neuromuscular diseases was 5%. Heart rhythm abnormalities were reported frequently: conduction disease in 26%, supraventricular tachycardia in 17%, and sustained or non-sustained ventricular tachycardia in 18% of patients. Three important outcome measures were reported including systemic thromboembolic events with a mean frequency of 9%, heart transplantation with 4%, and adequate ICD therapy with 15%. Nine studies investigated the genetics of non-compaction cardiomyopathy. The most frequently mutated gene was TTN with a pooled frequency of 11%. The average frequency of MYH7 mutations was 9%, for MYBPC3 mutations 5%, and for CASQ2 and LDB3 3% each. TPM1, MIB1, ACTC1, and LMNA mutations had an average frequency of 2% each. Mutations in PLN, HCN4, TAZ, DTNA, TNNT2, and RBM20 were reported with a frequency of 1% each. We also summarized the results of eight studies investigating the non-compaction in altogether 5327 athletes, pregnant women, patients with sickle cell disease, as well as individuals from population-based cohorts, in which the presence of left ventricular hypertrabeculation ranged from 1.3 to 37%. CONCLUSION: The summarized data indicate that non-compaction may lead to unfavorable outcome in different cardiomyopathy entities. The presence of key features in a multimodal diagnostic approach could distinguish between benign morphological trait and manifest cardiomyopathy.

Incidence of and Causes for Ventriculoperitoneal Shunt Failure in Children Younger Than 2 Years: A Systematic Review.

OBJECTIVES: Ventriculoperitoneal (VP) shunting is commonly used to treat pediatric hydrocephalus, but failure rates are high. VP shunt failure in children is mostly caused by infection and/or proximal/distal shunt obstruction. However, to our knowledge, no previous reviews have discussed this topic using only clinical studies when age-related data could be obtained. This systematic review aimed at reevaluating what is already known as the most common causes of shunt failure and to determine the incidence and causes of VP shunt failure during the first 2 years of life as a step to establish solid evidence-based guidelines to avoid VP shunt failure in infants. METHODS: We performed a search using the search terms "Cerebrospinal Fluid Shunts" (Medical Subject Headings [MeSH]) AND failure [All Fields] AND ("humans" [MeSH] AND English [lang] AND "infant" [MeSH]). Only articles that specifically discussed VP shunt complications in children < 2 years were included. RESULTS: We found that the most common causes of VP shunt failure in children < 2 years were shunt obstruction and infection, both observed in a range. CONCLUSION: VP shunt failure is very common in infants, mostly resulting from obstruction and infection. Future studies should focus on methods designed to avoid these complications or on alternative treatments for hydrocephalus.