Hervé Spechbach

Reversible ventricular arrythmia induced by dasatinib

Ventricular arrhythmias induced by dasatinib are rare events, but physicians in charge of chronic myeloid leukemia patients should be aware of such potential complications and the need for regular ECG controls during treatment with tyrosine kinase inhibitors.

Post-artesunate delayed haemolysis ‒ report of four cases and review of the literature

As a result of a huge effort of the international community, the burden of malaria dropped impressively during the last decade. One of the reasons is probably the availability of effective and safe treatments such as artemisinin derivatives. However, along with the greater use of intravenous artesunate recently in severe malaria, as recommended by the World Health Organization, a new adverse event has been described: post-artesunate delayed haemolysis (PADH). It appears after the end of the treatment in a phase of clinical improvement. Even though several causes may act as co-factors, the mechanism of pitting of the infected erythrocytes is most probably the main explanation. After the description of four PADH cases, we hereby present a short review of the current knowledge on this problem.

Handling Ellipsis in a Spoken Medical Phraselator

We consider methods for handling incomplete (elliptical) utterances in spoken phraselators, and describe how they have been implemented inside BabelDr, a substantial spoken medical phraselator. The challenge is to extend the phrase matching process so that it is sensitive to preceding dialogue context. We contrast two methods, one using limited-vocabulary strict grammar-based speech and language processing and one using large-vocabulary speech recognition with fuzzy grammar-based processing, and present an initial evaluation on a spoken corpus of 821 context-sentence/elliptical-phrase pairs. The large-vocabulary/fuzzy method strongly outperforms the limited-vocabulary/strict method over the whole corpus, though it is slightly inferior for the subset that is within grammar coverage. We investigate possibilities for combining the two processing paths, using several machine learning frameworks, and demonstrate that hybrid methods strongly outperform the large-vocabulary/fuzzy method.