Predicting prognosis in patients with stroke treated with intravenous alteplase through blood pressure changes: A machine learning-based approach

The use of machine learning (ML) in predicting disease prognosis has increased, and researchers have adopted different methods for variable selection to optimize early screening for AIS to determine its prognosis as soon as possible. We aimed to improve the understanding of the predictors of poor functional outcome at three months after discharge in AIS patients treated with intravenous thrombolysis and to construct a highly effective prognostic model to improve prediction accuracy. And four ML methods (random forest, support vector machine, naive Bayesian, and logistic regression) were used to screen and recombine the features for construction of an ML prognostic model. A total of 352 patients that had experienced AIS and had been treated with intravenous thrombolysis were recruited. The variables included in the model were NIHSS on admission, age, white blood cell count, percentage of neutrophils and triglyceride after thrombolysis, tirofiban, early neurological deterioration, early neurological improvement, and BP at each time point or period. The model's area under the curve for predicting 30-day modified Rankin scale was 0.790 with random forest, 0.542 with support vector machine, 0.411 with naive Bayesian, and 0.661 with logistic regression. The random forest model was shown to accurately evaluate the prognosis of AIS patients treated with intravenous thrombolysis, and therefore they may be helpful for accurate and personalized secondary prevention. The model offers improved prediction accuracy that may reduce rates of misdiagnosis and missed diagnosis in patients with AIS.     

Long-term follow-up of 64 children with classical infantile-onset Pompe disease since 2004: A French real-life observational study

Background

Classical infantile-onset Pompe disease (IOPD) is the most severe form of Pompe disease. Enzyme replacement therapy (ERT) has significantly increased survival but only a few studies have reported long-term outcomes.

Methods

We retrospectively analyzed the outcomes of classical IOPD patients diagnosed in France between 2004 and 2020.

Results

Sixty-four patients were identified. At diagnosis (median age 4 months) all patients had cardiomyopathy and most had severe hypotonia (57 of 62 patients, 92%). ERT was initiated in 50 (78%) patients and stopped later due to being ineffective in 10 (21%). Thirty-seven (58%) patients died during follow-up, including all untreated and discontinued ERT patients, and 13 additional patients. Mortality was higher during the first 3 years of life and after the age of 12 years. Persistence of cardiomyopathy during follow-up and/or the presence of heart failure were highly associated with an increased risk of death. In contrast, cross-reactive immunologic material (CRIM)-negative status (n = 16, 26%) was unrelated to increased mortality, presumably because immunomodulation protocols prevent the emergence of high antibody titers to ERT. Besides survival, decreased ERT efficacy appeared after the age of 6 years, with a progressive decline in motor and pulmonary functions for most survivors.

Conclusions

This study reports the long-term follow-up of one of the largest cohorts of classical IOPD patients and demonstrates high long-term mortality and morbidity rates with a secondary decline in muscular and respiratory functions. This decreased efficacy seems to be multifactorial, highlighting the importance of developing new therapeutic approaches targeting various aspects of pathogenesis.