Search Results (40)

Objective: This study aims to apply different deep learning convolutional neural network algorithms to assess the grading of cervical spinal stenosis and to evaluate their consistency with clinician grading results as well as clinical manifestations of patients. Methods: We retrospectively enrolled 954 patients with cervical spine magnetic resonance imaging (MRI) data and medical records from the Fifth Affiliated Hospital of Sun-Yat Sen University. The Kang grading method for sagittal MR images of the cervical spine and the spinal cord compression ratio for horizontal MR images of the cervical spine were adopted for cervical spinal canal stenosis grading. The collected data were randomly divided into training/validation and test sets. The training/validation sets were processed by various image preprocessing and annotation methods, in which deep learning convolutional networks, including classification, target detection, and key point localization models, were applied. The predictive grading of the test set by the model was finally contrasted with the grading results of the clinicians, and correlation analysis was performed with the clinical manifestations of the patients. Result: The EfficientNet_B5 model achieved a five-fold cross-validated accuracy of 79.45% and near-perfect agreement with clinician grading on the test set (κ= 0.848, 0.822), surpassing resident–clinician consistency (κ = 0.732, 0.702). The model-derived compression ratio (0.45 ± 0.07) did not differ significantly from manual measurements (0.46 ± 0.07). Correlation analysis showed moderate associations between model outputs and clinical symptoms: EfficientNet_B5 grades (r = 0.526) were comparable to clinician assessments (r = 0.517, 0.503) and higher than those of residents (r = 0.457, 0.448). Conclusion: CNN models demonstrate strong performance in the objective, consistent, and efficient grading of cervical spinal stenosis severity, offering potential clinical value in automated diagnostic support. Full article

Background/Objectives: Mitral regurgitation (MR) is the most common left heart valve disease, but its exact prevalence remains uncertain. To estimate the prevalence of MR we conducted a systematic review and meta-analysis of population-based studies. Methods: We searched the Medline/PubMed, Embase, and Scopus databases, in January 2023, for studies reporting or allowing for the calculation of the prevalence of moderate-to-severe MR in the general population. Eligible studies included those using echocardiography or primary care databases from countries with universal healthcare. Studies where echocardiography was performed for medical indications were excluded. Random-effects meta-analysis was used to calculate the pooled estimates. Subgroup and meta-regression analyses were employed to investigate the reasons for heterogeneity. Mixed-model multivariable meta-regression was used to estimate age- and sex-specific prevalence. Results: After screening 13,847 records, we identified 20 eligible studies (22 study populations) including 6,036,691 individuals. The global prevalence of moderate-to-severe MR was 0.67% (95% CI, 0.33−1.11). Prevalence increased greatly with age, and it was estimated to be approximately 0.63% (0.25–1.16) at age 50, 2.85% (1.96–3.90) at 70, and 6.45% (4.17–9.16) by 90 years. North America showed the largest crude prevalence (1.11%; 0.52−1.88), followed by Europe (0.60%; 0.34−0.92), Asia (0.24%; 0.00−0.92), and Africa (0.16%; 0.03−0.37). Differences in prevalence by geographic region and ethnic group were primarily attributable to population age. Prevalence did not differ by sex, study year, or diagnostic criteria. Conclusions: Moderate-to-severe MR is a prevalent condition, particularly among elderly people. With rising life expectancy worldwide, ensuring universal access to interventions will be vital to reduce morbidity and mortality. Full article

Background: The main data basis for the Diagnosis-Related Group (DRG) payment methodology is the disease diagnosis and clinical codes in the Medical Record (MR). Problems such as up-coding have arisen during implementation in many countries, and problems with MR quality and solutions have been studied mostly from the physician’s perspective. We investigated and analyzed the main influences on clinical coding from the perspectives of directors and coders in Medical Records Section (MRS) to provide recommendations for improvements in data quality. Methods: The questionnaire was developed, revised and improved using literature research and expert consultation methods. From 13 to 19 June 2024, the electronic questionnaire survey was conducted among the directors and coders of medical records department in healthcare organization. A total of 484 directors and coders were included in this study. And relevant statistics were computed and analyzed by non-parametric tests. Results: Coders should possess strong job responsibilities (92.36%), coding skills (91.33%), knowledge of clinical medicine (90.70%), and other comprehensive qualities and abilities. When encountering difficult problems, the clinical coders should first communicate with clinical doctors (91.95%). The two main factors affecting the quality of MR and clinical coding are the individual factors of doctors (88.84%) and the individual factors of coders (85.54%). Conclusions: Doctors and coders are the primary factors influencing the quality of clinical coding. It is recommended to establish a systematic training program for doctors to enhance the connotative quality of MR, for coders to solidify professional coding skills, strengthen communication and exchange, adopt reasonable behaviors, avoid moral hazards, and effectively improve the quality of clinical coding. Full article

Purpose: Lymphomas are generally radiosensitive; therefore, disease volume tends to shrink during radiotherapy courses. As MRI-linac provides excellent soft tissue definition and allows daily re-contouring of gross tumor volume and clinical target volume, its adoption could be beneficial for the treatment of lymphomas. Nonetheless, at this time there is a lack of literature regarding the use of MR-linac in this context. Methods: A prospective observational study was conducted on patients affected by non-Hodgkin lymphoma (NHL) involving head and neck (H&N) sites and treated with Elekta Unity^® MR-Linac. The clinical and dosimetric data of the first eight patients were collected and integrated with relevant data from medical records. Results: Seven patients had B-cell lymphoma (three DLBCL, two MALT, one follicular, and one mantle-cell) and one T-cell/NK lymphoma. The intent of RT was radical for four patients, salvage treatment for three, and CAR-T bridging for one. Two patients presented orbital localizations and six cervical lymphonodal sites. Median GTV was 5.74 cc, median CTV 127.01 cc, and median PTV 210.37 cc. The prescribed dose was 24–50 Gy in 2 Gy fractions for seven patients and 24 Gy in 3 Gy fractions for one patient. All the patients experienced acute toxicity, the maximum grade was G1 for five patients and G2 for three at the end of RT. One month after radiotherapy seven patients still experienced G1 toxicity, but no toxicity grade ≥ 2 was reported. First radiological assessment was performed for all the patients after a median of 101.5 days, reporting complete response in all the cases. After a median follow up of 330 days, no patient experienced local disease progression, while one patient developed distant progression. Conclusions: radiotherapy for NHL with H&N localization using a 1.5 T MR-linac was feasible, with no >G2 toxicity and optimal response rate and disease control. Full article

Introduction: This study presents long-term data of pediatric AIS patients with a favorable initial clinical presentation who were followed by a tertiary pediatric neurology clinic with a well-organized stroke team. Method: Patients who were diagnosed with AIS at pediatric age (28 days–18 years) and followed for at least 5 years by the same clinic were included in this study. The clinical and demographical characteristics of the patients were retrospectively collected from their medical records. At their last visit, the modified Rankin scale (mRS) and Pediatric Stroke Outcome Measure Short Neuro Exam (PSOM-SNE) were administered, and a neurological examination was performed. Results: A total of 32 patients (20 of whom were male, 62.5%) were included in this study. Their mean age at the time of the study was 162.62 ± 64.4 (62–300) months. The mean age at first ischemic stroke was 77.39 ± 61.93 (0.5–180) months, and the mean follow-up duration was 85.44 ± 20.52 (60–121) months. Seventeen patients (53.3%) reported normal daily functions at the last visit. A younger presentation age (≤60 months) was related to a longer hospital admission duration (24 h vs. 9 h) and worse long-term functional outcomes (p = 0.023). The affected vascular territory did not have any significant effect on long-term clinical outcomes (p = 0.550). Anticoagulant treatment alone was consistent with a worse prognosis compared to antithrombotic treatment alone or the combination of both (p = 0.026). PSOM-SNE scores were helpful in detecting some mild cognitive and language dysfunctions in patients with favorable mRS scores and subtle neurological sequelae. Conclusions: Pediatric AIS with a mild presentation has some degree of long-term morbidity, even when handled at well-organized stroke centers. A younger presentation age has the highest risk of long-term neurological sequelae. Full article

Systemic lupus erythematosus (SLE) is a complex autoimmune disease that poses serious long-term patient burdens. (1) Background: SLE patient classification and care are often complicated by case heterogeneity (diverse variations in symptoms and severity). Large language models (LLMs) and generative artificial intelligence (genAI) may mitigate this challenge by profiling medical records to assess key medical criteria. (2) Methods: To demonstrate genAI-based profiling, ACR (American College of Rheumatology) 1997 SLE classification criteria were used to define medically relevant LLM prompts. Records from 78 previously studied patients (45 classified as having SLE; 33 indeterminate or negative) were computationally profiled, via five genAI replicate runs. (3) Results: GenAI determinations of the “Discoid Rash” and “Pleuritis or Pericarditis” classification criteria yielded perfect concurrence with clinical classification, while some factors such as “Immunologic Disorder” (56% accuracy) were statistically unreliable. Compared to clinical classification, our genAI approach achieved a 72% predictive success rate. (4) Conclusions: GenAI classifications may prove sufficiently predictive to aid medical professionals in evaluating SLE patients and structuring care strategies. For individual criteria, accuracy seems to correlate inversely with complexities in clinical determination, implying that improvements in AI patient profiling tools may emerge from continued advances in clinical classification efficacy. Full article

Background: Hepatic encephalopathy (HE) may arise as a possible consequence of cirrhosis. Magnetic resonance imaging (MRI) may reveal a T1-weighted hyperintensity in the globi pallidi, indicating the deposition of paramagnetic substances. The objective of this research was to implement a machine learning-based radiomic model to predict the diagnosis and severity of chronic hepatic encephalopathy in adult patients with cirrhosis. Methods: Between October 2018 and February 2020, brain magnetic resonance imaging (MRI) was conducted on adult patients, both with and without cirrhosis. The control population consisted of individuals who did not have a previous medical record of chronic liver disease. The grade of hepatic encephalopathy (HE) was determined by considering factors such as the presence of underlying liver disease, the severity of clinical symptoms, and the frequency of encephalopathic episodes. Radiomic texture analysis based on five machine learning algorithms was applied to axial T1-weighted MR images of bilateral lentiform nuclei. Using the area under the receiver operating characteristics curve, we determined the accuracy of the five machine learning-based algorithms in predicting the presence of HE and the HE grading. Results: The ultimate research cohort included 124 individuals, with 70 being cirrhotic patients and 54 being non-cirrhotic controls. Of the total number of patients, 38 had a previous occurrence of HE and, among them, 22 had a grade of HE greater than 1. The multilayer perceptron algorithm classified patients versus controls with an accuracy of 100%. The k-nearest neighbor (KNN) algorithm classified patients with or without HE with an accuracy of 76.5%. The multilayer perceptron algorithm classified HE grade (HE grade 1, HE grade ≥ 2) with an accuracy of 94.1%. Conclusions: The machine learning algorithms implemented provide a robust modeling technique for deriving valuable insights from brain MR images in cirrhotic patients and this can serve as an imaging tool valuable for the assessment of the burden of hepatic encephalopathy. Full article

Background: Chronic subdural hematoma (CSDH) is increasingly common due to the aging population and widespread use of anticoagulant and antiplatelet medications. The objective of this study is to examine the internal composition of CSDH and explore potential risk factors associated with its recurrence. Methods: This retrospective study analyzed data from 189 patients who underwent surgery in our department between 2014 and 2018. Recorded data included demographics, clinical information, details of surgical interventions, computer tomography (CT) scans, neurological assessments, and follow-up data. The outcome was evaluated clinically and through CT follow-up conducted 4–12 weeks post-surgery. CT scans measured various parameters, including hematoma thickness, hyperdense regions, chronic components, and membrane presence. Results: Patients after the evacuation of CSDH were significantly more common males (66.1%, p > 0.001) had a significantly higher BMI (p < 0.001, 61.6%), arterial hypertension (p < 0.001, 68.3%), and the intake of anticoagulant therapy (p < 0.001, 58%). The recurrence rate was 18.6% after 4 weeks and 2.1% after 8–12 weeks. After uni- and multivariable analysis, the initial hemispheric type (p = 0.019, HR: 3.191; p = 0.012, HR: 3.810) and the increasing preoperative midline shift in CT (p = 0.028, HR: 1.114; p = 0.041, HR: 1.107) were found as independent predictors for recurrence. Overall, outcomes were favorable with a modified Rankin scale (mRS) of 0–2 at discharge (72%), after 4 (89.7%) and 12 (87%) weeks. Conclusion: According to our data, increasing midline shift before surgery and initial hemispheric type of hematoma were independent predictors of recurrence. Most patients achieved an excellent outcome with a low-risk profile. Full article

Background/Objectives: Post-polio syndrome (PPS) affects former polio patients, manifesting decades after initial infection with progressive symptoms like pain, fatigue, and muscle weakness. Diagnosis relies on the clinical criteria and exclusion of other probable causes. The purpose of this study is to determine the scope and new diagnostic value of magnetic resonance imaging (MRI) in identifying muscle involvement in PPS and distinguishing it from prior poliomyelitis (PPM). Methods: This study was approved by the Koç University Ethics Committee with Approval No. 2023.409.IRB2.090. Electronic medical archives from two academic institutions were searched for records tagged with ICD code B-91 for poliomyelitis sequalae. The resulting search query of 291 records was manually sorted for PPS and PPM, medical history, clinical examination findings, and lumbar MR images down to 32 patients. Two independent radiologists evaluated the paraspinal musculature in the MRIs using the Mercuri scale. Inter-rater agreement, comparison of the paraspinal musculatures between groups, and their relationship to leg involvement were assessed with the resulting data. Results: Inter-rater agreement was found to be almost perfect across all muscles, except for the multifidus muscle. When clinical examination findings were included for these muscles, quadratus lumborum (QL) degradation was found in both right-side (p = 0.017) and left-side (p = 0.002) leg involvement. Conclusions: QL muscle deterioration may serve as a diagnostic marker for PPS, potentially guiding lumbar pain treatment through rehabilitation. Full article

Background and Objectives: The aim of the report is to report the outcomes of the medial rectus (MR) disinsertion procedure for the management of large-angle esotropia (ET) patients. Materials and Methods: This is a retrospective case series of patients with large-angle ET who underwent an MR disinsertion procedure between March 2012 to April 2022. The procedure happened accidentally during muscle surgery. The demographic and clinical data, including sex, age, visual acuity, pre- and postoperative angle of strabismus, duction limitations, results of intraoperative forced duction tests, and follow-up duration were collected from medical records. Results: Five patients were enrolled in this study. The mean age was 62.2 ± 9.8 years, and the mean follow-up was 24.8 ± 8.7 months. The ET at the primary position of gaze was 92.0 ± 17.9 prism diopters (PD) before MR disinsertion and 38.0 ± 29.5 PD after MR disinsertion only. Abduction deficiency was −4 before after MR disinsertion, which improved to −1 at the last follow-up. Conclusions: The results of MR disinsertion were not as frustrating as anticipated. MR disinsertion may be considered in patients with large-angle sensory ET who refuse surgery on the opposite eye. Full article

This study explored short- and mid-term functional outcomes in patients undergoing decompressive hemicraniectomy (DHC) due to space-occupying cerebral infarction and asked whether there is a potentially harmful effect of a priorly performed endovascular treatment (EVT). Medical records were screened for patients requiring DHC due to space-occupying cerebral infarction between January 2016 and July 2021. Functional outcomes at hospital discharge and at 3 months were assessed by the modified Rankin Scale (mRS). Out of 65 patients with DHC, 39 underwent EVT before DHC. Both groups, i.e., EVT + DHC and DHC alone, had similar volumes (280 ± 90 mL vs. 269 ± 73 mL, t-test, p = 0.633) and proportions of edema and infarction (22.1 ± 6.5% vs. 22.1 ± 6.1%, t-test, p = 0.989) before the surgical intervention. Patients undergoing EVT + DHC tended to have a better functional outcome at hospital discharge compared to DHC alone (mRS 4.8 ± 0.8 vs. 5.2 ± 0.7, Mann–Whitney-U, p = 0.061), while the functional outcome after 3 months was similar (mRS 4.6 ± 1.1 vs. 4.8 ± 0.9, Mann–Whitney-U, p = 0.352). In patients initially presenting with a relevant infarct demarcation (Alberta Stroke Program Early CT Score ≤ 5), the outcome was similar at hospital discharge and after 3 months between patients with EVT + DHC and DHC alone. This study provided no evidence for a harmful effect of EVT before DHC in patients with space-occupying brain infarction. Full article

Background and Objectives: The aim of this study was to investigate the incidence of cerebrovascular pathology in patients with chronic kidney disease and its effect on functional outcomes. Materials and Methods: In a retrospective cross-sectional study (2018–2021), the medical records of patients with acute hemorrhagic and ischemic stroke with concomitant chronic kidney disease who received treatment in Riga East University Hospital Stroke Unit were analyzed. Data were analyzed using IBM SPSS 26.0. The Kruskal–Wallis, Mann–Whitney U test, and Spearman’s rank correlation coefficient methods were used. Results: The final sample consisted of 305 acute cerebrovascular pathology patients (56.4% females). Overall, 57.3% of stroke patients had second-stage chronic kidney disease with average serum creatinine levels of 104.3 mmol/L (±32.8). The functional outcome of the stroke depended on the stage of chronic kidney disease. There was a statistically significant non-linear correlation between glomerular filtration rate and NIHSS (National Institute of Health Stroke Scale) score on admission (Rho −0.194, p = 0.016), glomerular filtration rate and NIHSS score on discharge (Rho −0.186, p = 0.020), and glomerular filtration rate and modified Rankin score on admission (Rho −0.237, p = 0.003) and discharge (Rho −0.224, p = 0.05). The mean NIHSS score of ischemic stroke patients was 8.3 ± 5.9 on admission and 6.5 ± 5.8 on discharge. In the hemorrhagic stroke patient group, the mean NIHSS score was 9.5 ± 7.3 on admission and 7.1 ± 6.9 on discharge. On average, 34.0% of ischemic stroke patients had an mRS score of 5 on admission, while in the hemorrhagic stroke patient group, this figure was 41%. There was no statistical difference in the glomerular filtration rate between the thrombolyzed versus non-thrombolyzed patient groups (Mann–Whitney U test = 1457, p = 0.794). Conclusions: Chronic kidney disease is an important predictor of the severity and functional outcome of a stroke; furthermore, the early management and prevention of complications should be a top priority in the prophylaxis of this cerebrovascular pathology. Full article

High-resolution manometry (HRM) facilitates the detailed evaluation of esophageal motility. In December 2020, Chicago classification (CC) version 4.0 introduced modifications to improve consistency and accuracy. We conducted this study to compare the differences in the interpretations of HRM examinations between CC 3.0 and 4.0. Consecutive HRM records at a Taiwan tertiary medical center, including wet swallows and MRS performed in both supine and sitting positions from October 2019 to May 2021, were retrospectively reviewed and analyzed using both CC versions 3.0 and 4.0. A total of 105 patients were enrolled, and 102 patients completed the exam, while three could not tolerate HRM sitting up. Refractory gastroesophageal reflux disease (GERD) symptoms (n = 65, 63.7%) and dysphagia (n = 37, 36.3%) were the main indications. A total of 18 patients (17.6%) were reclassified to new diagnoses using CC 4.0. Of the 11 patients initially diagnosed with absent contractility, 3 (27.3%) were reclassified as having Type 1 achalasia. Of the 18 patients initially diagnosed with IEM, 6 (33.3%) were reclassified as normal. The incidence of diagnosis changes was similar in both the dysphagia and refractory GERD symptoms groups (21.6% versus 15.3%, p = 0.43). The use of CC 4.0 led to changes in the diagnoses of esophageal motility disease, irrespective of examination indications. Early adoption improves the accuracy of diagnoses and affects patient management. Full article

Unmanned aerial vehicle technology is the most advanced and helpful in almost every area of interest in human work. These devices become autonomous and can fulfil a variety of tasks, from simple imaging and obtaining data to search and rescue operations. The most challenging environment for search and rescue operations is the mountainous area. This article is devoted to the theoretical description and simulation tests of a prototype method of landing the light and the medium-weight UAVs used as supplementary devices for SAR (search and rescue) and HEMS (helicopter emergency medical service) in hard-to-reach mountainous terrains. The autonomous flight of a UAV in mountainous terrain has many specifics, and it is usually performed according to predetermined map points (pins) uploaded directly into the control software of the UAV. It is necessary to characterise each point flown on the chosen flight route line in advance and therefore to know its exact geographical coordinates (longitude, latitude and height of the point above the terrain), and the control system of UAV must react to the change in the weather and other conditions in real time. Usually, it is difficult to make this forecast with sufficient time in advance, mainly when UAVs are used as supplementary devices for the needs of HEMS or MRS (mountain rescue service). The most challenging phase is the final approach and landing of the UAV, especially if a loss of GNSS (global navigation satellite system) signal occurs, like in the determined area of the Little Cold Valley in the Slovak High Tatras—which is infamous for the widespread loss of GNSS signals or communication/controlling connection between the UAV and the pilot-operator at the operational station. To solve the loss of guidance, a new method for guiding and controlling the UAV in its final approach and landing in a determined area is tested. An alternative landing navigation system for UAVs in a specific mountainous environment—the authors’ designed frequency Doppler landing system (FDLS)—is briefly described but thoroughly tested with the help of artificial intelligence. An estimation of dynamic stability is used based on the time recording of the current position of the UAV, with the help of a frequency-modulated or amplitude-modulated signal based on the author’s prototype of a precision landing system designed for mountainous terrain. This solution could overcome the problems of GNSS signal loss. The presented research primarily evaluates the success of the simulation flights for the supplementary UAV. The success of navigating the UAV to land in the mountainous environment at an exact landing point using the navigation signals from the FDLS was evaluated at more than 95%. Full article

(1) Objective: Systemic lupus erythematosus (SLE) is a complex disease involving immune dysregulation, episodic flares, and poor quality of life (QOL). For a decentralized digital study of SLE patients, machine learning was used to assess patient-reported outcomes (PROs), QOL, and biometric data for predicting possible disease flares. (2) Methods: Participants were recruited from the LupusCorner online community. Adults self-reporting an SLE diagnosis were consented and given a mobile application to record patient profile (PP), PRO, and QOL metrics, and enlisted participants received smartwatches for digital biometric monitoring. The resulting data were profiled using feature selection and classification algorithms. (3) Results: 550 participants completed digital surveys, 144 (26%) agreed to wear smartwatches, and medical records (MRs) were obtained for 68. Mining of PP, PRO, QOL, and biometric data yielded a 26-feature model for classifying participants according to MR-identified disease flare risk. ROC curves significantly distinguished true from false positives (ten-fold cross-validation: p < 0.00023; five-fold: p < 0.00022). A 25-feature Bayesian model enabled time-variant prediction of participant-reported possible flares (P(true) > 0.85, p < 0.001; P(nonflare) > 0.83, p < 0.0001). (4) Conclusions: Regular profiling of patient well-being and biometric activity may support proactive screening for circumstances warranting clinical assessment. Full article