To our knowledge, the adoption of Learning Health System (LHS) concepts or approaches for improving stroke care, patient outcomes, and value have not previously been summarized. This topical review provides a summary of the published evidence about LHSs applied to stroke, and case examples applied to different aspects of stroke care from high and low-to-middle income countries. Our attempt to systematically identify the relevant literature and obtain real-world examples demonstrated the dissemination gaps, the lack of learning and action for many of the related LHS concepts across the continuum of care but also elucidated the opportunity for continued dialogue on how to study and scale LHS advances. In the field of stroke, we found only a few published examples of LHSs and health systems globally implementing some selected LHS concepts, but the term is not common. A major barrier to identifying relevant LHS examples in stroke may be the lack of an agreed taxonomy or terminology for classification. We acknowledge that health service delivery settings that leverage many of the LHS concepts do so operationally and the lessons learned are not shared in peer-reviewed literature. It is likely that this topical review will further stimulate the stroke community to disseminate related activities and use keywords such as learning health system so that the evidence base can be more readily identified.
- MeSH
- Stroke * MeSH
- Humans MeSH
- Learning Health System * MeSH
- Check Tag
- Humans MeSH
- Publication type
- Journal Article MeSH
- Review MeSH
- Research Support, N.I.H., Extramural MeSH
1st ed. xxiv, 313 s.
This paper describes the interactive tools of the AKUTNE.CZ (part of MEFANET) and SEPSIS-Q portals for Problem Based Learning (PBL) sessions in medical education. The portals aim to be a comprehensive source of information and educational materials, covering all aspects of acute medicine for undergraduate medical students and health professionals. Our focus is mainly on simulation-based tools for teaching and learning algorithms in acute patient care, the backbone of the AKUTNE.CZ and SEPSIS-Q portals. Over the last five years, more than 30 interactive algorithms in the Czech and English languages (http:// www.akutne.eu) have been devel¨oped and published online, allowing users to test and improve their knowledge and skills in the field of acute medicine. Additionally, we have created six SEPSIS-Q interactive scenarios in the Czech version. The peerreviewed algorithms were used for conducting PBL-like sessions in General Medicine (First Aid, Anaesthesiology and Pain Management, Emergency Medicine) and in Nursing (Obstetric Analgesia and Anaesthesia for Midwives, Intensive Care Medicine). The interactive scenarios serve to demonstrate interesting cases, with preference for Intensive Care Medicine sessions in General Medicine and Nursing.
- MeSH
- Algorithms MeSH
- Humans MeSH
- Computer-Assisted Instruction methods MeSH
- Problem-Based Learning * methods trends MeSH
- Sepsis * diagnosis therapy MeSH
- Education, Medical, Undergraduate methods MeSH
- Education, Nursing, Baccalaureate methods MeSH
- Emergency Medicine methods instrumentation education MeSH
- Check Tag
- Humans MeSH
- Publication type
- Research Support, Non-U.S. Gov't MeSH
BACKGROUND: Neuromuscular diseases (NMDs) are rare disorders characterized by progressive muscle fibre loss, leading to replacement by fibrotic and fatty tissue, muscle weakness and disability. Early diagnosis is critical for therapeutic decisions, care planning and genetic counselling. Muscle magnetic resonance imaging (MRI) has emerged as a valuable diagnostic tool by identifying characteristic patterns of muscle involvement. However, the increasing complexity of these patterns complicates their interpretation, limiting their clinical utility. Additionally, multi-study data aggregation introduces heterogeneity challenges. This study presents a novel multi-study harmonization pipeline for muscle MRI and an AI-driven diagnostic tool to assist clinicians in identifying disease-specific muscle involvement patterns. METHODS: We developed a preprocessing pipeline to standardize MRI fat content across datasets, minimizing source bias. An ensemble of XGBoost models was trained to classify patients based on intramuscular fat replacement, age at MRI and sex. The SHapley Additive exPlanations (SHAP) framework was adapted to analyse model predictions and identify disease-specific muscle involvement patterns. To address class imbalance, training and evaluation were conducted using class-balanced metrics. The model's performance was compared against four expert clinicians using 14 previously unseen MRI scans. RESULTS: Using our harmonization approach, we curated a dataset of 2961 MRI samples from genetically confirmed cases of 20 paediatric and adult NMDs. The model achieved a balanced accuracy of 64.8% ± 3.4%, with a weighted top-3 accuracy of 84.7% ± 1.8% and top-5 accuracy of 90.2% ± 2.4%. It also identified key features relevant for differential diagnosis, aiding clinical decision-making. Compared to four expert clinicians, the model obtained the highest top-3 accuracy (75.0% ± 4.8%). The diagnostic tool has been implemented as a free web platform, providing global access to the medical community. CONCLUSIONS: The application of AI in muscle MRI for NMD diagnosis remains underexplored due to data scarcity. This study introduces a framework for dataset harmonization, enabling advanced computational techniques. Our findings demonstrate the potential of AI-based approaches to enhance differential diagnosis by identifying disease-specific muscle involvement patterns. The developed tool surpasses expert performance in diagnostic ranking and is accessible to clinicians worldwide via the Myo-Guide online platform.
- MeSH
- Adult MeSH
- Internet MeSH
- Middle Aged MeSH
- Humans MeSH
- Magnetic Resonance Imaging * methods MeSH
- Neuromuscular Diseases * diagnosis diagnostic imaging MeSH
- Machine Learning * MeSH
- Check Tag
- Adult MeSH
- Middle Aged MeSH
- Humans MeSH
- Male MeSH
- Female MeSH
- Publication type
- Journal Article MeSH
Modern QSAR approaches have wide practical applications in drug discovery for designing potentially bioactive molecules. If such models are based on the use of 2D descriptors, important information contained in the spatial structures of molecules is lost. The major problem in constructing models using 3D descriptors is the choice of a putative bioactive conformation, which affects the predictive performance. The multi-instance (MI) learning approach considering multiple conformations in model training could be a reasonable solution to the above problem. In this study, we implemented several multi-instance algorithms, both conventional and based on deep learning, and investigated their performance. We compared the performance of MI-QSAR models with those based on the classical single-instance QSAR (SI-QSAR) approach in which each molecule is encoded by either 2D descriptors computed for the corresponding molecular graph or 3D descriptors issued for a single lowest energy conformation. The calculations were carried out on 175 data sets extracted from the ChEMBL23 database. It is demonstrated that (i) MI-QSAR outperforms SI-QSAR in numerous cases and (ii) MI algorithms can automatically identify plausible bioactive conformations.
Cíl: Porovnat operační, patologické a pooperační výsledky robotické radikální hysterektomie (RRH) v „learning curve“ s laparoskopicky asistovanou radikální vaginální hysterektomií (LAVRH) a abdominální radikální hysterektomií (ARH) u pacientek s časnými stadii karcinomu děložního hrdla. Typ studie: Komparativní studie. Pracoviště: Porodnicko-gynekologická klinika, FN a LF UP Olomouc. Metodika: Porovnali jsme prvních dvacet pacientek operovaných roboticky pro karcinom děložního hrdla ve stadiu IA2–IIA s historicky předcházejícími pacientkami operovanými laparoskopicky asistovanou radikální vaginální hysterektomií nebo abdominální radikální hysterektomií. Všechny operace byly provedeny třemi operatéry (R. P., P. D., M. K.) na Porodnicko-gynekologické klinice FN a LF UP v Olomouci v období od 2004 do 2011. Výsledky: Nenalezli jsme rozdíl mezi skupinami ve věkovém složení, v body mass indexu, histopatologii nádorů, počtu odstraněných uzlin nebo předoperační hodnotě hemoglobinu. Délku robotického operačního výkonu se podařilo zkrátit ze 400 minut na méně než 225 minut srovnatelných s průměrnou délkou 215 minut u otevřené radikální hysterektomie. Zjistili jsme rozdíly mezi před- a pooperačními hodnotami krevního hemoglobinu (RRH, 14,9 ? 7,6; LARVH, 23,0 ? 8,5; ARH, 28,0 ? 12,4). Tyto rozdíly byly statisticky významné ve prospěch skupiny RRH (p = 0,0012). Průměrná délka hospitalizace byla významně kratší u pacientek operovaných roboticky(7,2 versus 8,8 dnů, p = 0,0005). Průměrný počet získaných pánevních uzlin se významně nelišil mezi skupinami. Žádná z robotických nebo laparoskopických operací nevyžadovala konverzi na laparotomii. Rozdíly mezi závažnými peroperačními komplikacemi nebyly signifikantní. Závěr: Robotická radikální hysterektomie vykázala srovnatelné anebo lepší peroperační parametry než laparoskopicky asistovaná radikální vaginální hysterektomie. Zavedení robotické chirurgie v léčbě časných stadií karcinomu hrdla děložního vyžaduje méně než 20 výkonů pro dosažení délky operace srovnatelné s otevřeným přístupem.
Objective: To compare intraoperative, pathologic and postoperative outcomes of „learning curve“ robotic radical hysterectomy (RRH) with laparoscopy assisted radical vaginal hysterectomy (LARVH) and abdominal radical hysterectomy (ARH) in patients with early stage cervical carcinoma. Design: Comparative study. Setting: Department of Obstetrics and Gynecology, University Hospital, Olomouc. Methods: The first twenty patients with cervical cancer stages IA2-IIA underwent RRH and were compared with previous twenty LARVH and ARH cases. The procedures were performed at University Hospital Olomouc, Czech Republic between 2004 and 2011. Results: There were no differences between groups for age, body mass index, tumor histology, number of nodes removed or preoperative hemoglobin levels. The median theatre time in the learning period for the robot procedure was reduced from 400 min to less than 223 min and compared well to the 215 min for an open procedure. We found differences between the pre- and postoperative hemoglobin levels (RRH, 14.9 ?7 .6; LARVH, 23.0 ? 8.5; ARH, 28.0 ? 12.4). This difference was statistically significant in favor of RRH group ( p= 0.0012). Mean length of stay was significantly shorter for the RRH group (7.2 versus 8.8 days,p = 0.0005). Mean pelvic lymph node count was similar in the three groups. None of the robotic or laparoscopic procedures required conversion to laparotomy. The differences in major operative complications between the two groups were not significant. Conclusion: Based on our experience, robotic radical hysterectomy showed better results than traditional laparoscopically assisted radical vaginal hysterectomy in early stage cervical carcinoma cases. Introduction of this new technique requires a learning curve of less than 20 cases that will reduce the operating time to a level comparable to open surger.
- Keywords
- karcinom hrdla děložního, robotická chirurgie, radikální hysterektomie,
- MeSH
- Surgical Procedures, Operative methods MeSH
- Surgery, Computer-Assisted methods MeSH
- Adult MeSH
- Hemoglobins MeSH
- Hospitalization MeSH
- Hysterectomy, Vaginal * MeSH
- Hysterectomy * MeSH
- Carcinoma * surgery MeSH
- Learning Curve * MeSH
- Laparoscopy * MeSH
- Laparotomy MeSH
- Middle Aged MeSH
- Lymph Nodes MeSH
- Minimally Invasive Surgical Procedures methods MeSH
- Young Adult MeSH
- Uterine Cervical Neoplasms * surgery MeSH
- Robotics * MeSH
- Aged MeSH
- Check Tag
- Adult MeSH
- Middle Aged MeSH
- Young Adult MeSH
- Aged MeSH
- Female MeSH
- Publication type
- Comparative Study MeSH
Background: Classifying diseases into ICD codes has mainly relied on human reading a large amount of written materials, such as discharge diagnoses, chief complaints, medical history, and operation records as the basis for classification. Coding is both laborious and time consuming because a disease coder with professional abilities takes about 20 minutes per case in average. Therefore, an automatic code classification system can significantly reduce the human effort. Objectives: This paper aims at constructing a machine learning model for ICD-10 coding, where the model is to automatically determine the corresponding diagnosis codes solely based on free-text medical notes. Methods: In this paper, we apply Natural Language Processing (NLP) and Recurrent Neural Network (RNN) architecture to classify ICD-10 codes from natural language texts with supervised learning. Results: In the experiments on large hospital data, our predicting result can reach F1-score of 0.62 on ICD-10-CM code. Conclusion: The developed model can significantly reduce manpower in coding time compared with a professional coder.
- MeSH
- Electronic Data Processing methods MeSH
- Deep Learning * MeSH
- Electronic Health Records MeSH
- International Classification of Diseases * MeSH
- Neural Networks, Computer MeSH
- Machine Learning MeSH
- Information Storage and Retrieval methods statistics & numerical data MeSH
- Data Visualization MeSH
- Natural Language Processing MeSH
- Publication type
- Research Support, Non-U.S. Gov't MeSH
Detection and segmentation of brain abnormalities using Magnetic Resonance Imaging (MRI) is an important task that, nowadays, the role of AI algorithms as supporting tools is well established both at the research and clinical-production level. While the performance of the state-of-the-art models is increasing, reaching radiologists and other experts' accuracy levels in many cases, there is still a lot of research needed on the direction of in-depth and transparent evaluation of the correct results and failures, especially in relation to important aspects of the radiological practice: abnormality position, intensity level, and volume. In this work, we focus on the analysis of the segmentation results of a pre-trained U-net model trained and validated on brain MRI examinations containing four different pathologies: Tumors, Strokes, Multiple Sclerosis (MS), and White Matter Hyperintensities (WMH). We present the segmentation results for both the whole abnormal volume and for each abnormal component inside the examinations of the validation set. In the first case, a dice score coefficient (DSC), sensitivity, and precision of 0.76, 0.78, and 0.82, respectively, were found, while in the second case the model detected and segmented correct (True positives) the 48.8% (DSC ≥ 0.5) of abnormal components, partially correct the 27.1% (0.05 > DSC > 0.5), and missed (False Negatives) the 24.1%, while it produced 25.1% False Positives. Finally, we present an extended analysis between the True positives, False Negatives, and False positives versus their position inside the brain, their intensity at three MRI modalities (FLAIR, T2, and T1ce) and their volume.
- Publication type
- Journal Article MeSH
