-
International Journal of Surgery Case... Jun 2024Purtscher retinopathy is the rare form of occlusive microvasculopathy, characterized by multiple retinal white areas around the optic nerve head and fovea with...
INTRODUCTION AND IMPORTANCE
Purtscher retinopathy is the rare form of occlusive microvasculopathy, characterized by multiple retinal white areas around the optic nerve head and fovea with paravascular clearing and may be related to intraretinal hemorrhages. Acute Pancreatitis (AP) is one of the most common gastrointestinal reasons for hospital admissions globally. The complications of Acute Pancreatitis may include Purtscher's-like retinopathy, which has a low incidence rate of less than 0.24 instances per million cases. This case report highlights the value of thorough medical history taking and examination, and it apprises the consideration of ophthalmological manifestation in patients of Acute Pancreatitis.
CASE PRESENTATION
A 34-year-old female came to the emergency room due to intense abdominal pain associated with nausea and vomiting, which worsened over the last 24 h. The pain was described as continuous, sharp, and cramping-like in the upper abdomen, radiating to the back. Lab tests revealed elevated serum amylase and lipase levels, indicating pancreatitis, along with slight leukocytosis. A contrast-enhanced CT scan confirmed acute pancreatitis with mild inflammation and enlargement of the pancreas. Two days after admission, the patient experienced a sudden and painless loss of central vision in both eyes. There was no history of trauma or any other significant relevant history, other than pancreatitis. The ophthalmologist's examination found reduced visual acuity (6/60 in the right eye, 3/60 in the left eye), normal corneas, and anterior chambers.
DISCUSSION
Inkeles and Walsh established the first link between acute pancreatitis and Purtscher-like retinopathy when they reported three cases of the distinctive retinal appearance in individuals with acute pancreatitis in 1975.
CONCLUSION
The recovery and prognosis in cases of Purtscher-like retinopathy is variable and further research is required to ascertain the usage of corticosteroids and pentoxifylline in improving the course of a patient's with Purtscher's-like retinopathy.
PubMed: 38875828
DOI: 10.1016/j.ijscr.2024.109881 -
International Journal of Surgery Case... May 2024Paraneoplastic leukemoid reactions (PLRs) in the context of sarcomas represent a unique clinical entity that poses significant diagnostic challenges and adds valuable...
INTRODUCTION
Paraneoplastic leukemoid reactions (PLRs) in the context of sarcomas represent a unique clinical entity that poses significant diagnostic challenges and adds valuable insights to the surgical literature. Characterized by an abnormal elevation of white blood cell count, these reactions are often associated with aggressive tumor biology and poor prognosis, emphasizing the need for heightened awareness among clinicians.
CASE PRESENTATION
A 48-year-old male presented with a rapidly growing, ulcerated tumor on his thigh. Lab tests revealed an extreme leukocytosis with a white blood cell count of 92,860/mm3. Imaging and biopsy confirmed a high-grade spindle cell sarcoma.
CLINICAL DISCUSSION
After excluding other causes of leukocytosis, a PLR secondary to sarcoma was diagnosed. Despite initial antibiotic treatment, leukocytosis persisted, prompting a decision for surgical intervention. The patient underwent successful tumor resection, resulting in a significant decrease in leukocyte count and subsequent stable recovery, supported by adjuvant radiotherapy.
CONCLUSION
This case underscores the importance of recognizing PLRs in sarcoma patients as they can significantly impact clinical management and prognosis. It highlights the necessity of a multidisciplinary approach for accurate diagnosis and effective treatment. The case contributes to the surgical literature by detailing the diagnostic process and therapeutic interventions in managing such complex presentations, thereby providing key "take-away" lessons on the importance of considering PLRs in the differential diagnosis of leukocytosis in patients with malignancies.
PubMed: 38875823
DOI: 10.1016/j.ijscr.2024.109819 -
Clinics (Sao Paulo, Brazil) Jun 2024Exercise rehabilitation is the core of Cardiac Rehabilitation (CR) and will improve the prognosis of patients receiving Percutaneous Coronary Intervention (PCI surgery)....
Effects of different early cardiac rehabilitation exercise treatments on the prognosis of acute myocardial infarction patients receiving percutaneous coronary intervention.
OBJECTIVES
Exercise rehabilitation is the core of Cardiac Rehabilitation (CR) and will improve the prognosis of patients receiving Percutaneous Coronary Intervention (PCI surgery). The current study retrospectively analyzed the effects of different exercise-based CR strategies on the prognosis of AMI patients receiving PCI treatment.
METHODS
Clinicopathological information from 127 patients was collected and divided into different groups based on the exercise-based CR received, including Continuous Resistance Exercise (COR), Continuous Aerobic Exercise (COA), Interval Resistance Exercise (IVR), Interval Aerobic Exercise (IVA), Inspiratory Muscle Exercises (ITM), and Control. The differences regarding cardio-pulmonary function, hemodynamics, and life quality were analyzed against different CR strategies.
RESULTS
All the exercise-based CR strategies showed improving effects compared with patients in the Control group regarding cardio-pulmonary parameters, with IVR showing the strongest improving effects (IVR > ITM > COR > IVA > COA) (p < 0.05) at the first recoding point. However, the improving effects of exercise-based CR declined with time. Regarding the effects on hemodynamics parameters, the improving effects of exercise-based CR were only observed regarding LVEF, and the effects of IVR were also the strongest (IVR > COR > ITM > COA > IVA) (p < 0.05). Similar improving effects were also observed for 6MWT and life quality (IVR showing the strongest improving effects) (p < 0.05), which all declined three months after the surgery.
CONCLUSIONS
The current study showed that exercise-based CRs had better improving effects than the normal nursing strategy on the prognosis of AMI patients receiving PCI surgery.
PubMed: 38875753
DOI: 10.1016/j.clinsp.2024.100408 -
JMIR AI Dec 2023An early warning tool to predict attacks could enhance asthma management and reduce the likelihood of serious consequences. Electronic health records (EHRs) providing... (Review)
Review
BACKGROUND
An early warning tool to predict attacks could enhance asthma management and reduce the likelihood of serious consequences. Electronic health records (EHRs) providing access to historical data about patients with asthma coupled with machine learning (ML) provide an opportunity to develop such a tool. Several studies have developed ML-based tools to predict asthma attacks.
OBJECTIVE
This study aims to critically evaluate ML-based models derived using EHRs for the prediction of asthma attacks.
METHODS
We systematically searched PubMed and Scopus (the search period was between January 1, 2012, and January 31, 2023) for papers meeting the following inclusion criteria: (1) used EHR data as the main data source, (2) used asthma attack as the outcome, and (3) compared ML-based prediction models' performance. We excluded non-English papers and nonresearch papers, such as commentary and systematic review papers. In addition, we also excluded papers that did not provide any details about the respective ML approach and its result, including protocol papers. The selected studies were then summarized across multiple dimensions including data preprocessing methods, ML algorithms, model validation, model explainability, and model implementation.
RESULTS
Overall, 17 papers were included at the end of the selection process. There was considerable heterogeneity in how asthma attacks were defined. Of the 17 studies, 8 (47%) studies used routinely collected data both from primary care and secondary care practices together. Extreme imbalanced data was a notable issue in most studies (13/17, 76%), but only 38% (5/13) of them explicitly dealt with it in their data preprocessing pipeline. The gradient boosting-based method was the best ML method in 59% (10/17) of the studies. Of the 17 studies, 14 (82%) studies used a model explanation method to identify the most important predictors. None of the studies followed the standard reporting guidelines, and none were prospectively validated.
CONCLUSIONS
Our review indicates that this research field is still underdeveloped, given the limited body of evidence, heterogeneity of methods, lack of external validation, and suboptimally reported models. We highlighted several technical challenges (class imbalance, external validation, model explanation, and adherence to reporting guidelines to aid reproducibility) that need to be addressed to make progress toward clinical adoption.
PubMed: 38875586
DOI: 10.2196/46717 -
JMIR AI May 2023The identification of objective pain biomarkers can contribute to an improved understanding of pain, as well as its prognosis and better management. Hence, it has the...
A Scalable Radiomics- and Natural Language Processing-Based Machine Learning Pipeline to Distinguish Between Painful and Painless Thoracic Spinal Bone Metastases: Retrospective Algorithm Development and Validation Study.
BACKGROUND
The identification of objective pain biomarkers can contribute to an improved understanding of pain, as well as its prognosis and better management. Hence, it has the potential to improve the quality of life of patients with cancer. Artificial intelligence can aid in the extraction of objective pain biomarkers for patients with cancer with bone metastases (BMs).
OBJECTIVE
This study aimed to develop and evaluate a scalable natural language processing (NLP)- and radiomics-based machine learning pipeline to differentiate between painless and painful BM lesions in simulation computed tomography (CT) images using imaging features (biomarkers) extracted from lesion center point-based regions of interest (ROIs).
METHODS
Patients treated at our comprehensive cancer center who received palliative radiotherapy for thoracic spine BM between January 2016 and September 2019 were included in this retrospective study. Physician-reported pain scores were extracted automatically from radiation oncology consultation notes using an NLP pipeline. BM center points were manually pinpointed on CT images by radiation oncologists. Nested ROIs with various diameters were automatically delineated around these expert-identified BM center points, and radiomics features were extracted from each ROI. Synthetic Minority Oversampling Technique resampling, the Least Absolute Shrinkage And Selection Operator feature selection method, and various machine learning classifiers were evaluated using precision, recall, F-score, and area under the receiver operating characteristic curve.
RESULTS
Radiation therapy consultation notes and simulation CT images of 176 patients (mean age 66, SD 14 years; 95 males) with thoracic spine BM were included in this study. After BM center point identification, 107 radiomics features were extracted from each spherical ROI using pyradiomics. Data were divided into 70% and 30% training and hold-out test sets, respectively. In the test set, the accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve of our best performing model (neural network classifier on an ensemble ROI) were 0.82 (132/163), 0.59 (16/27), 0.85 (116/136), and 0.83, respectively.
CONCLUSIONS
Our NLP- and radiomics-based machine learning pipeline was successful in differentiating between painful and painless BM lesions. It is intrinsically scalable by using NLP to extract pain scores from clinical notes and by requiring only center points to identify BM lesions in CT images.
PubMed: 38875572
DOI: 10.2196/44779 -
JCO Clinical Cancer Informatics Jun 2024Rare cancers constitute over 20% of human neoplasms, often affecting patients with unmet medical needs. The development of effective classification and prognostication...
PURPOSE
Rare cancers constitute over 20% of human neoplasms, often affecting patients with unmet medical needs. The development of effective classification and prognostication systems is crucial to improve the decision-making process and drive innovative treatment strategies. We have created and implemented MOSAIC, an artificial intelligence (AI)-based framework designed for multimodal analysis, classification, and personalized prognostic assessment in rare cancers. Clinical validation was performed on myelodysplastic syndrome (MDS), a rare hematologic cancer with clinical and genomic heterogeneities.
METHODS
We analyzed 4,427 patients with MDS divided into training and validation cohorts. Deep learning methods were applied to integrate and impute clinical/genomic features. Clustering was performed by combining Uniform Manifold Approximation and Projection for Dimension Reduction + Hierarchical Density-Based Spatial Clustering of Applications with Noise (UMAP + HDBSCAN) methods, compared with the conventional Hierarchical Dirichlet Process (HDP). Linear and AI-based nonlinear approaches were compared for survival prediction. Explainable AI (Shapley Additive Explanations approach [SHAP]) and federated learning were used to improve the interpretation and the performance of the clinical models, integrating them into distributed infrastructure.
RESULTS
UMAP + HDBSCAN clustering obtained a more granular patient stratification, achieving a higher average silhouette coefficient (0.16) with respect to HDP (0.01) and higher balanced accuracy in cluster classification by Random Forest (92.7% ± 1.3% and 85.8% ± 0.8%). AI methods for survival prediction outperform conventional statistical techniques and the reference prognostic tool for MDS. Nonlinear Gradient Boosting Survival stands in the internal (Concordance-Index [C-Index], 0.77; SD, 0.01) and external validation (C-Index, 0.74; SD, 0.02). SHAP analysis revealed that similar features drove patients' subgroups and outcomes in both training and validation cohorts. Federated implementation improved the accuracy of developed models.
CONCLUSION
MOSAIC provides an explainable and robust framework to optimize classification and prognostic assessment of rare cancers. AI-based approaches demonstrated superior accuracy in capturing genomic similarities and providing individual prognostic information compared with conventional statistical methods. Its federated implementation ensures broad clinical application, guaranteeing high performance and data protection.
Topics: Humans; Prognosis; Artificial Intelligence; Precision Medicine; Female; Rare Diseases; Male; Deep Learning; Neoplasms; Myelodysplastic Syndromes; Algorithms; Middle Aged; Aged; Cluster Analysis
PubMed: 38875514
DOI: 10.1200/CCI.24.00008 -
American Society of Clinical Oncology... Jun 2024Multiple chimeric antigen receptor (CAR) T-cell and bispecific antibody (bsAb) therapies have been approved, demonstrating impressive clinical efficacy in... (Review)
Review
Multiple chimeric antigen receptor (CAR) T-cell and bispecific antibody (bsAb) therapies have been approved, demonstrating impressive clinical efficacy in relapsed/refractory multiple myeloma (MM). Currently, these treatment share overlapping approval indications in the relapsed/refractory space, highlighting the importance of optimal selection and sequencing to maximize clinical efficacy. For patients previously unexposed to T-cell-directed therapies, several factors should be weighed when both options are available. These factors include access and logistical challenges associated with CAR T-cell therapy, disease-specific factors such as tempo of disease relapse, in addition to patient-specific factors such as frailty, and distinct toxicity profiles across these agents. Sequential therapy, whether it involves CAR T-cell therapy followed by bsAb or vice versa, has demonstrated clinical efficacy. When sequencing these agents, it is crucial to consider various factors that contribute to treatment resistance with careful selection of treatments for subsequent therapy in order to achieve favorable long-term patient outcomes.
Topics: Humans; Multiple Myeloma; Immunotherapy; Immunotherapy, Adoptive; Antibodies, Bispecific; Combined Modality Therapy; Treatment Outcome; Receptors, Chimeric Antigen
PubMed: 38875506
DOI: 10.1200/EDBK_432204 -
Medicine Jun 2024This study examines the relationship between red blood cell distribution width (RDW) and the prognosis of patients undergoing hepatectomy for hepatocellular carcinoma... (Meta-Analysis)
Meta-Analysis
This study examines the relationship between red blood cell distribution width (RDW) and the prognosis of patients undergoing hepatectomy for hepatocellular carcinoma (HCC). Additionally, it explores the potential effect of RDW for the early identification of high-risk patients after surgery, advocating for timely interventions to improve outcomes. A comprehensive literature search was conducted on May 16, 2022, across PubMed (23 studies), Embase (45 studies), the Cochrane Library (1 study), and CNKI (17 studies), resulting in 6 relevant articles after screening. This analysis primarily focused on the postoperative outcomes of patients. Hazard ratios (HRs) and 95% confidence intervals (CIs) were pooled to assess prognosis, with survival indicators including overall survival (OS) and disease-free survival (DFS). All 6 studies reported on OS, and 2 addressed DFS. A total of 1645 patients from 6 studies were included. The pooled analysis revealed that RDW is an independent prognostic factor for both OS (HR = 1.50, I² = 84%, 95% CI = 1.23-1.77, P < .01) and DFS (HR = 2.06, I² = 15%, 95% CI = 1.51-2.82, P < .01). Patients in the high RDW group exhibited significantly poorer OS and DFS compared to those in the low RDW group. RDW is a prognostic factor for HCC patients after surgery. Elevated RDW levels are associated with a poorer prognosis, adversely affecting both OS and DFS. RDW may serve as a valuable marker for stratifying risk and guiding intervention strategies in the postoperative management of HCC patients.
Topics: Humans; Carcinoma, Hepatocellular; Liver Neoplasms; Erythrocyte Indices; Hepatectomy; Prognosis; Female; Disease-Free Survival; Postoperative Period; Male
PubMed: 38875439
DOI: 10.1097/MD.0000000000038475 -
Medicine Jun 2024Choline alfoscerate (alpha-glycerylphosphorylcholine) is a phospholipid that includes choline, which increases the release of acetylcholine. The ASCOMALVA trial, a... (Randomized Controlled Trial)
Randomized Controlled Trial Comparative Study Observational Study
BACKGROUND
Choline alfoscerate (alpha-glycerylphosphorylcholine) is a phospholipid that includes choline, which increases the release of acetylcholine. The ASCOMALVA trial, a combination of donepezil and choline alfoscerate, slowed cognitive decline in Alzheimer disease. This study aims to replicate the effect by combining donepezil with other nootropics currently used in South Korea.
METHODS
The 119 patients with cognitive decline who were eligible to use donepezil, with an mini-mental state examination (MMSE) score of 26 or less, were assigned to: donepezil alone (DO); donepezil and choline alfoscerate (DN); donepezil and acetyl-l-carnitine (DA); or donepezil and ginkgo biloba extract (DG). Cognitive evaluations such as MMSE, clinical dementia rating, Alzheimer disease assessment scale-cognitive subscale (ADAS-Cog), and Alzheimer disease assessment scale-noncognitive subscale were performed at the 12th and 24th weeks from the baseline time point.
RESULTS
At the 12th week, the MMSE score increased 3.52% in the DN group, whereas it increased by 1.36% in the DO group. In the DA + DG group, it decreased by 2.17%. At the 24th week, the MMSE score showed an increase of 1.07% in the DO group and 1.61% in the DN group, but decreased by 5.71% in the DA + DG group. ADAS-Cog decreased by 0.9% in the DO group, while it improved by 13.9% in the DN group at the 12th week. At the 24th week, ADAS-Cog showed improvement in the DN group by 18.5%, whereas it improved by 9.4% in the DO group. Alzheimer disease assessment scale-noncognitive subscale also revealed better performance in the DN group than in the DO group at the 12th and 24th weeks.
CONCLUSION
Choline alfoscerate exhibits additional cognitive improvement in both cognitive and noncognitive domains, supporting the findings of the ASCOMALVA trial.
Topics: Humans; Donepezil; Male; Female; Aged; Double-Blind Method; Drug Therapy, Combination; Glycerylphosphorylcholine; Nootropic Agents; Ginkgo biloba; Indans; Alzheimer Disease; Piperidines; Plant Extracts; Republic of Korea; Acetylcarnitine; Cognitive Dysfunction; Mental Status and Dementia Tests; Treatment Outcome; Aged, 80 and over; Cognition; Ginkgo Extract
PubMed: 38875437
DOI: 10.1097/MD.0000000000038067 -
Medicine Jun 2024The neutrophil lymphocyte ratio (NLR) and red blood cell distribution width (RDW) have been repeatedly demonstrated to be associated with risk of severity, progression,... (Observational Study)
Observational Study
The neutrophil lymphocyte ratio (NLR) and red blood cell distribution width (RDW) have been repeatedly demonstrated to be associated with risk of severity, progression, and prognosis of chronic obstructive pulmonary disease (COPD), but data on respiratory failure (RF) in patients with COPD are very limited. This study aimed to examine the relationship between NLR and RDW and the incident RF in patients with COPD. This is a retrospective study that reviewed data by examining the hospitalization medical records to identify those who were admitted with a diagnosis of COPD. Based on whether RF occurred during index hospitalization, patients were classified as COPD group and COPD combined with RF group. Also, healthy controls of the same age and sex were enrolled in a 1:1 ratio as the COPD group. Univariate comparisons were performed between three groups to examine differences. With the COPD group as reference, multivariable logistic regression was formed to identify the relationship between NLR and RDW and RF, with adjustment for multiple covariates. There were 136 healthy controls, 136 COPD patients and 62 patients with COPD combined with RF included for analysis. There was a significant difference for eight variables, including age, WBC, neutrophil, NLR, RDW, platelet, PLR, and CRP. The Spearman test showed the significant correlation between NLR and WBC (correlation coefficient, 0.38; P = .008), NLR and RDW (correlation coefficient, 0.32; P = .013), and NLR and CRP level (correlation coefficient, 0.54; P < .001). The multivariable logistic regression showed that age (every additional 10 years) (OR, 1.785), NLR (OR, 1.716), RDW (OR, 2.266), and CRP (OR, 1.163) were independently associated with an increased risk of RF. This study demonstrated the independent associative effect of NLR and RDW with RF in patients with COPD, exhibiting the potential clinical role in evaluating the progress of COPD to RF.
Topics: Humans; Pulmonary Disease, Chronic Obstructive; Male; Female; Retrospective Studies; Erythrocyte Indices; Neutrophils; Middle Aged; Aged; Lymphocytes; Respiratory Insufficiency; Lymphocyte Count; Prognosis
PubMed: 38875435
DOI: 10.1097/MD.0000000000038512