CHE: Chemie hat die höchste Promotionsquote in Deutschland Im Fach Chemie führen rechnerisch vier von fünf Masterabschlüsse später zu Promotionen. Die meisten Doktorarbeiten werden im Fach Medizin verfasst. Dies zeigt ein aktueller DatenCHECK des CHE Centrum ...

Im Fach #Chemie führen rechnerisch vier von fünf Masterabschlüsse später zu #Promotionen. Die meisten #Doktorarbeiten werden im Fach #Medizin verfasst. Dies zeigt ein aktueller DatenCHECK des CHE Centrum für #Hochschulentwicklung.

bildungsklick.de/hochschule-u...

Information Extraction of Doctoral Theses Using Two Different Large Language Models vs Health Services Researchers: Development and #usability Study Background: The “Archive of German language general practice” (ADAM) stores about 500 paper based doctoral theses from 1965 till today. While they have been grouped in different categories no deeper systematic process of information extraction (IE) has been performed yet. Recently developed Large Language Models (LLMs) like ChatGPT have been attributed the potential to help in IE of medical documents. However, there are concerns about hallucination of LLM. Furthermore, there have not been reports regarding their usage in non-recent doctoral theses yet. Objective: To analyze if LLMs can help to extract information from doctor thesis by using GPT-4o and gemini-1.5-flash for paper based doctoral theses in ADAM. Methods: We randomly selected ten doctoral theses from 1965 till 2022. After preprocessing we used two different LLM pipelines, using models of OpenAI and Google, respectively. Pipelines were used to extract dissertation characteristics and generate uniform abstracts. Furthermore, one pooled human-generated abstract was written for comparison. Furthermore, blinded raters were asked to evaluate LLM-generated abstracts in comparison to the human-generated ones. BERTScores were calculated as evaluation metric. Results: Relevant dissertation characteristics and keywords could be extracted for all theses (n=10): name and place of the institute, title of theses, name(s) of author and year of publication. For all except one doctoral thesis an abstract could be generated using GPT-4o, while gemini-1.5-flash provided abstracts in all cases (n=10). The modality of abstract generation showed no influence in raters evaluation using the non-parametric Kruskal-Wallis test for independent groups (P=.44). Creation of LLM-generated abstracts was estimated 24 to 36 times faster than creation by humans. Evaluation metrics showed moderate-to-high semantic similarity (Mean F1 BERT-Score, GPT-4o: 0.72 and Gemini: 0.71). Translation from German into Eng-lish did not result in a loss of information (n=10). Conclusions: An accumulating body of not published doctoral theses makes it difficult to extract relevant evidence. Recent advances in LLMs like ChatGPT, have raised expectations in text mining, but have not yet been used in IE of “historic” medical documents. This #feasibility study sug-gests that both models, GPT-4o and gemini-1.5-flash helped to accurately simplify and con-dense doctoral theses into relevant information while LLM-generated abstracts being per-ceived similar, were semantic similar and taking about thirty times less time in comparison to human-generated ones. This pilot study demonstrates the #feasibility of a regular office scanning workflow and general-purpose LLMs to extract relevant information and produce accurate abstracts from ADAM doctoral theses. Taken together this information could help to better search the scientific background from family medicine from the last 60 years, helping to develop current research questions.

JMIR Formative Res: Information Extraction of Doctoral Theses Using Two Different Large Language Models vs Health Services Researchers: Development and #usability Study #Doktorarbeiten #Informationsextraktion #Sprachmodelle #Gesundheitsforschung #Doktorand

Es gäbe… [Konjunktiv!] – allein, wer zahlt's? #Doktorarbeiten #CDU #Minister+innen

#Doktorarbeiten sind eh ganz simpel. Einfach was raushauen. Also die These "Ich bin #Doktor" selbstständig auf ein #Blatt gebracht und veröffentlicht erfüllt die #Höhe. #Beispiel #Luther. Also da passiert kaum was. Es sei sie schreiben ihren Namen unter die #Arbeit von jemand anderen.

#Doktorarbeiten sind eh ganz simpel. Einfach was raushauen. Also die These "Ich bin #Doktor" selbstständig auf ein #Blatt gebracht und veröffentlicht erfüllt die #Höhe. #Beispiel #Luther. Also da passiert kaum was. Es sei sie schreiben ihren Namen unter die #Arbeit von jemand anderen.