Data processing pipeline for cardiogenic shock prediction using machine learning.

Introduction: Recent advances in machine learning provide new possibilities to process and analyse observational patient data to predict patient outcomes. In this paper, we introduce a data processing pipeline for cardiogenic shock (CS) prediction from the MIMIC III database of intensive cardiac care unit patients with acute coronary syndrome. The ability to identify high-risk patients could possibly allow taking pre-emptive measures and thus prevent the development of CS. Methods: We mainly focus on techniques for the imputation of missing data by generating a pipeline for imputation and comparing the performance of various multivariate imputation algorithms, including k-nearest neighbours, two singular value decomposition (SVD)-based methods, and Multiple Imputation by Chained Equations. After imputation, we select the final subjects and variables from the imputed dataset and showcase the performance of the gradient-boosted framework that uses a tree-based classifier for cardiogenic shock prediction. Results: We achieved good classification performance thanks to data cleaning and imputation (cross-validated mean area under the curve 0.805) without hyperparameter optimization. Conclusion: We believe our pre-processing pipeline would prove helpful also for other classification and regression experiments.

Overlap syndrome SLE - ANCA associated vasculitis.

Incidence of ANCA antibodies in patients with systemic lupus erythematosus (SLE) is described in 24-31 %, but they are not related to the distribution and severity of organ involvement in SLE; the routine monitoring is not recommended. Overlap syndrome of systemic lupus erythematosus and ANCA associated vasculitis (AAV) is rare. The difficult diagnosis and treatment of this syndrome is described in this case report of the patient with SLE and severe kidney involvement resulting from AAV.

Intramedullary spinal cord and cauda equina metastasis of breast carcinoma: case report.

AIM: We present a case report of a female patient with metastasis of breast carcinoma to the medullary conus and cauda equina. METHODS: A 48-year-old woman with a history of breast tumor, suddenly felt severe weakness and numbness of the lower extremities. MRI of the spine disclosed a mass lesion within the medullary conus, with leptomeningeal involvement of cauda equina at the spinal level L1. Laminectomy was performed and partial resection of the medullary conus tumor and especially release of nerve roots of cauda equina was achieved using microsurgical techniques. RESULTS: Her clinical status, especially right leg weakness and sensory loss in the lower extremities have immediately improved but bladder dysfunction remained and she was unable to walk. The histological picture and immunophenotype indicates the presence of metastatic ductal adenocarcinoma of the mammary gland. Patient died 4 months after the spinal cord and cauda equina surgery. CONCLUSION: To our knowledge, this is the first report of successful surgical treatment of metastatic leptomeningeal infiltration of breast carcinoma.