Retrospective analysis of interpretable machine learning in predicting ICU thrombocytopenia in geriatric ICU patients.

We developed an interpretable machine learning algorithm that prospectively predicts the risk of thrombocytopenia in older critically ill patients during their stay in the intensive care unit (ICU), ultimately aiding clinical decision-making and improving patient care. Data from 2286 geriatric patients who underwent surgery and were admitted to the ICU of Dongyang People's Hospital between 2012 and 2021 were retrospectively analyzed. Integrated algorithms were developed, and four machine-learning algorithms were used. Selected characteristics included common demographic data, biochemical indicators, and vital signs. Eight key variables were selected using the Least Absolute Shrinkage and Selection Operator and Random Forest Algorithm. Thrombocytopenia occurred in 18.2% of postoperative geriatric patients, with a higher mortality rate. The C5.0 model showed the best performance, with an area under the receiver operating characteristic curve close to 0.85, along with unparalleled accuracy, precision, specificity, recall, and balanced accuracy scores of 0.88, 0.98, 0.89, 0.98, and 0.85, respectively. The support vector machine model excelled at predictively assessing thrombocytopenia severity, demonstrating an accuracy rate of 0.80 in the MIMIC database. Thus, our machine learning-based models have considerable potential in effectively predicting the risk and severity of postoperative thrombocytopenia in geriatric ICU patients for better clinical decision-making and patient care.

Case report: Prone positioning in the improvement of severe post-operative hypoxia following aortic dissection.

Postoperative hypoxemia after aortic dissection surgery presents a considerable clinical challenge, and acute respiratory distress syndrome (ARDS) is a common etiology. Prone positioning treatment has emerged as a potential intervention for improving respiratory function in this context. We report the case of a 27-year-old male who developed severe hypoxemia complicated by pulmonary embolism after aortic dissection surgery. He was diagnosed with postoperative hypoxemia combined with pulmonary embolism following aortic dissection. His respiratory status continued to deteriorate despite receiving standard postoperative care, thereby necessitating an alternative approach. Implementation of prone positioning treatment led to a substantial amelioration in his oxygenation and overall respiratory health, with a consistent hemodynamic state observed throughout the treatment. This technique resulted in significant relief in symptoms and improvement in respiratory parameters, facilitating successful extubation and, ultimately, discharge. This case underlines the possible efficacy of prone positioning therapy in managing severe hypoxia complicated by pulmonary embolism following aortic dissection surgery, warranting more thorough research to explore the potential of this treatment modality.

Ensemble machine learning algorithm for predicting acute kidney injury in patients admitted to the neurointensive care unit following brain surgery.

Acute kidney injury (AKI) is a common postoperative complication among patients in the neurological intensive care unit (NICU), often resulting in poor prognosis and high mortality. In this retrospective cohort study, we established a model for predicting AKI following brain surgery based on an ensemble machine learning algorithm using data from 582 postoperative patients admitted to the NICU at the Dongyang People's Hospital from March 1, 2017, to January 31, 2020. Demographic, clinical, and intraoperative data were collected. Four machine learning algorithms (C5.0, support vector machine, Bayes, and XGBoost) were used to develop the ensemble algorithm. The AKI incidence in critically ill patients after brain surgery was 20.8%. Intraoperative blood pressure; postoperative oxygenation index; oxygen saturation; and creatinine, albumin, urea, and calcium levels were associated with the postoperative AKI occurrence. The area under the curve value for the ensembled model was 0.85. The accuracy, precision, specificity, recall, and balanced accuracy values were 0.81, 0.86, 0.44, 0.91, and 0.68, respectively, indicating good predictive ability. Ultimately, the models using perioperative variables exhibited good discriminatory ability for early prediction of postoperative AKI risk in patients admitted to the NICU. Thus, the ensemble machine learning algorithm may be a valuable tool for forecasting AKI.

Analgesic efficacy of butorphanol combined with sufentanil after heart valve surgery: A propensity score-matching analysis.

Pain is common after heart valve surgery and can stimulate the sympathetic nervous system, causing hemodynamic instability and respiratory complications. Current treatments for postoperative pain are insufficient, and postoperative pain is difficult to control effectively with a single analgesic. Therefore, we investigated the analgesic efficacy of butorphanol with sufentanil after heart valve surgery and its hemodynamic effects. The records of 221 patients admitted to the intensive care unit after cardiac valve replacement between January 1, 2018, and May 31, 2021, were retrospectively analyzed. Patients were allocated to 2 groups based on the postoperative pain treatment they received: treatment group (administered butorphanol combined with sufentanil), and control group (administered conventional sufentanil analgesia). After propensity score matching for sex, age, Acute Physiology and Chronic Health Evaluation II score, type of valve surgery, and operation duration, 76 patients were included in the study, and analgesic efficacy, hemodynamic changes, and adverse drug reactions were compared between the 2 groups. After propensity score matching, the baseline characteristics were not significantly different between the groups. The histogram and jitter plot of the propensity score distribution indicated good matching. No significant differences were observed in the duration of mechanical ventilation, duration of stay in the intensive care unit, duration of total hospital stay, and hospitalization expenditure between the groups (P > .05). The treatment group had notably higher minimum systolic blood pressure (P = .024) and lower heart rate variability (P = .049) than those in the control group. Moreover, the treatment group exhibited better analgesic efficacy and had lower critical-care pain observation tool scores and consumption of sufentanil 24 hours after surgery than the control group (P < .05). The incidence of vomiting was notably lower in the treatment than in the control group (P = .028). Butorphanol combined with sufentanil can be used in patients after heart valve replacement. This combined treatment has good analgesic efficacy and is associated with reduced adverse drug reactions and, potentially, steady hemodynamics.

Prediction of persistent acute kidney injury in postoperative intensive care unit patients using integrated machine learning: a retrospective cohort study.

Acute kidney injury (AKI) often occurs in patients in the intensive care unit (ICU). AKI duration is closely related to the prognosis of critically ill patients. Identifying the disease course length in AKI is critical for developing effective individualised treatment. To predict persistent AKI at an early stage based on a machine learning algorithm and integrated models. Overall, 955 patients admitted to the ICU after surgery complicated by AKI were retrospectively evaluated. The occurrence of persistent AKI was predicted using three machine learning methods: a support vector machine (SVM), decision tree, and extreme gradient boosting and with an integrated model. External validation was also performed. The incidence of persistent AKI was 39.4-45.1%. In the internal validation, SVM exhibited the highest area under the receiver operating characteristic curve (AUC) value, followed by the integrated model. In the external validation, the AUC values of the SVM and integrated models were 0.69 and 0.68, respectively, and the model calibration chart revealed that all models had good performance. Critically ill patients with AKI after surgery had high incidence of persistent AKI. Our machine learning model could effectively predict the occurrence of persistent AKI at an early stage.

Pheochromocytoma-related cardiomyopathy presenting as acute myocardial infarction: A case report.

INTRODUCTION: Pheochromocytoma (PHEO)-related cardiomyopathy is a rare condition in which release of a large amount of catecholamines leads to severe vasoconstriction, coronary vasospasm, myocardial ischemia, injury, and necrosis. Its clinical manifestations can be similar to those of acute coronary syndrome. PATIENT CONCERNS: A 63-year-old woman was diagnosed with acute non-ST segment elevation myocardial infarction following chest pain for 8 hours. The results of coronary angiography were normal. The patient developed dyspnea, cough with frothy pink sputum, paroxysmal sweating, arrhythmia, and blood pressure fluctuation, and was transferred to the intensive care unit for monitoring and treatment. DIAGNOSIS: PHEO, catecholamine cardiomyopathy (CICMP). INTERVENTION: After monitoring the pulse index continuous cardiac output and treatment with α and ß adrenergic receptor blockers for 18 days, laparoscopic resection of the left adrenal mass was performed. OUTCOMES: The patient's condition improved and she was discharged 31 days after admission. Outpatient follow-up examinations 1 month and 1 year later did not show recurrence. LESSONS: PHEO can cause CICMP, the manifestations of which are partly similar to those of takotsubo cardiomyopathy (TTC). Once the patient's condition stabilizes, surgery should be considered. Fluid management is necessary, and agents such as α and ß adrenergic receptor blockers should be administered.

Acute myocardial infarction induced by eosinophilic granulomatosis with polyangiitis: A case report.

BACKGROUND: Eosinophilic granulomatosis with polyangiitis (EGPA) is a multisystem disease characterized by allergic rhinitis, asthma, and a significantly high eosinophil count in the peripheral blood. It mainly involves the arterioles and venules. When the coronary arteries are invaded, it can lead to acute myocardial infarction (AMI), acute heart failure, and other manifestations that often lead to death in the absence of timely treatment. CASE SUMMARY: A 69-year-old man was admitted to the emergency department due to chest pain for more than 1 h. He had a past history of bronchial asthma and chronic obstructive pulmonary disease and was diagnosed with AMI and heart failure. Thrombus aspiration of the left circumflex artery and percutaneous transluminal coronary angioplasty were performed immediately. After surgery, the patient was admitted to the intensive care unit. The patient developed eosinophilia, and medical history taking revealed fatigue of both thighs 1 mo prior. Local skin numbness and manifestations of peripheral nerve involvement were found on the lateral side of the right thigh. Skin biopsy of the lower limbs pathologically confirmed EGPA. The patient was treated with methylprednisolone combined with intravenous immunoglobulin and was discharged after 21 d. On follow-up at 7 d after discharge, heart failure recurred. The condition improved after cardiotonic and diuretic treatment, and the patient was discharged. CONCLUSION: Asthma, impaired cardiac function, and eosinophilia are indicative of EGPA. Delayed diagnosis often leads to heart involvement and death.