Stroke mortality prediction based on ensemble learning and the combination of structured and textual data.

For severe cerebrovascular diseases such as stroke, the prediction of short-term mortality of patients has tremendous medical significance. In this study, we combined machine learning models Random Forest classifier (RF), Adaptive Boosting (AdaBoost), Extremely Randomised Trees (ExtraTree) classifier, XGBoost classifier, TabNet, and DistilBERT to construct a multi-level prediction model that used bioassay data and radiology text reports from haemorrhagic and ischaemic stroke patients to predict six-month mortality. The performances of the prediction models were measured using the area under the receiver operating characteristic curve (AUROC), the area under the precision-recall curve (AUPRC), precision, recall, and F1-score. The prediction models were built with the use of data from 19,616 haemorrhagic stroke patients and 50,178 ischaemic stroke patients. Novel six-month mortality prediction models for these patients were developed, which enhanced the performance of the prediction models by combining laboratory test data, structured data, and textual radiology report data. The achieved performances were as follows: AUROC = 0.89, AUPRC = 0.70, precision = 0.52, recall = 0.78, and F1 score = 0.63 for haemorrhagic patients, and AUROC = 0.88, AUPRC = 0.54, precision = 0.34, recall = 0.80, and F1 score = 0.48 for ischaemic patients. Such models could be used for mortality risk assessment and early identification of high-risk stroke patients. This could contribute to more efficient utilisation of healthcare resources for stroke survivors.

The angiographic and clinical outcomes of intracranial aneurysms following irradiation in patients with nasopharyngeal carcinoma: A 13-year experience and literature review.

BACKGROUND AND PURPOSE: Intracranial aneurysms are a known but rare complication of radiotherapy (RT). We reviewed the angiographic and clinical outcomes of intracranial aneurysms following RT in patients with nasopharyngeal carcinoma (NPC), a malignancy endemic in Hong Kong. MATERIALS AND METHODS: The clinical, angiographic and laboratory data was collected for nine NPC patients harboring fifteen intracranial aneurysms following RT, diagnosed between 1st January 2000 and 31st December 2012. RESULTS: The median age at aneurysm diagnosis was 56 years with a male predilection (67%). The median latent period to diagnosis was nine years (0.3-30). Eight patients (89%) presented with aneurysmal subarachnoid hemorrhage. Nine aneurysms were located at the anterior circulation, and 14 were saccular in morphology. Of the treated aneurysms, eight underwent endovascular intervention and two were surgically clipped. Within a year, 50% of the treated aneurysms had recurred. Poor neurological outcome was noted. At two-year follow-up, the median score for modified Rankin score and Glasgow Outcome score was 5 and 2 respectively. The two-year mortality rate of patients with treated ruptured intracranial aneurysms was 50%. CONCLUSION: Compared to previous studies, our irradiated NPC patients had higher mortality and morbidity rates after aneurysm rupture and a higher angiographic recurrence rate following treatment. Greater vigilance is required in the detection of post-treatment recurrence of these aneurysms due to the higher risk of rupture. The authors recommend dedicated screening of intracranial aneurysms by active surveillance in routine CT protocols or the addition of three-dimensional time-of-flight magnetic resonance angiography in MR protocols.

Volume measurement of the intracranial aneurysm: a discussion and comparison of the alternatives to manual segmentation.

OBJECTIVE: Several modalities are available for volumetric measurement of the intracranial aneurysm. We discuss the challenges involved in manual segmentation, and analyze the application of alternative methods using automatic segmentation and geometric formulae in measurement of aneurysm volumes and coil packing density. METHODS: The volumes and morphology of 38 aneurysms treated with endovascular coiling at a single center were measured using three-dimensional rotational angiography (3DRA) reconstruction software using automatic segmentation. Aneurysm volumes were also calculated from their height, width, depth, size of neck, and assumed shape in 3DRA images using simple geometric formulae. The aneurysm volumes were dichotomized as "small" or "large" using the median volume of the studied population (54 mm(3)) measured by automatic segmentation as the cut-off value for further statistical analysis. RESULTS: A greater proportion of aneurysms were categorized as being "small" when geometric formulae were applied. The median aneurysm volumes obtained were 54.5 mm(3) by 3DRA software, and 30.6 mm(3) using mathematical equations. An underestimation of aneurysm volume with a resultant overestimation in the calculated coil packing density (p = 0.002) was observed. CONCLUSION: Caution must be exercised in the application of simple geometric formulae in the management of intracranial aneurysms as volumes may potentially be underestimated and packing densities falsely elevated. Future research should focus on validation of automatic segmentation in volumetric measurement and improving its accuracy to enhance its application in clinical practice.