A NLP Pipeline for the Automatic Extraction of a Complete Microorganism’s Picture from Microbiological Notes

Mora, Sara; Attene, Jacopo; Gazzarata, Roberta; Giacobbe, Daniele Roberto; Blobel, Bernd; Parruti, Giustino

doi:10.3390/jpm12091424

Cited by 5 publications

(4 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In case these two words are different the minimal Levenshtein edit distance [16] from the word suggested by Enchant and the word suggested by bart-it is calculated, and the word with minimal distance is chosen. The edit distance is calculated with FuzzyWuzzy Python library, as done in previous studies [17]. Abbreviation Extension (IV).…”

Section: Resultsmentioning

confidence: 99%

Defining a Preprocessing Pipeline for the MULTI-SITA Project and General Medical Italian Natural Language Data

Cappello,

Mora,

Giacobbe

et al. 2023

Studies in Health Technology and Informatics

View full text Add to dashboard Cite

The application of Natural Language Processing (NLP) to medical data has revolutionized different aspects of health care. The benefits obtained from the implementation of this technique spill over into several areas, including in the implementation of chatbots, which can provide medical assistance remotely. Every possible application of NLP depends on one first main step: the pre-processing of the corpus retrieved. The raw data must be prepared with the aim to be used efficiently for further analysis. Considerable progress has been made in this direction for the English language but for other languages, such as Italian, the state of the art is not equivalently advanced, especially for texts containing technical medical terms. The aim of this work is to identify and develop a preprocessing pipeline suitable for medical data written in Italian. The pipeline has been developed in Python environment, employing Enchant, ntlk modules and Hugging Face’s BERT and BART-based models. Then, it has been tested on real conversations typed between patients and physicians regarding medical questions. The algorithm has been developed within the MULTI-SITA project of the Italian Society of Anti-Infective Therapy (SITA), but shows a flexible structure that can adapt to a large variety of data.

show abstract

Section: Resultsmentioning

confidence: 99%

Defining a Preprocessing Pipeline for the MULTI-SITA Project and General Medical Italian Natural Language Data

Cappello,

Mora,

Giacobbe

et al. 2023

Studies in Health Technology and Informatics

View full text Add to dashboard Cite

show abstract

“…In our laboratory PhD students and other trainees are now applying machine learning and natural language processing. [53][54][55] It will be quite interesting and relatively easy to d https://www.iso.org/standard/77337.html. extract and organize these data to verify clinical and diagnostic hypotheses given a large number of data and taking inspiration from similar works already present in the literature.…”

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Ten Years of Medical Informatics and Standards Support for Clinical Research in an Infectious Diseases Network

et al. 2023

Self Cite

View full text Add to dashboard Cite

Background It is 30 years since evidence-based medicine became a great support for individual clinical expertise in daily practice and scientific research. Electronic systems can be used to achieve the goal of collecting data from heterogeneous datasets and to support multicenter clinical trials. The Ligurian Infectious Diseases Network (LIDN) is a web-based platform for data collection and reuse originating from a regional effort and involving many professionals from different fields. Objectives The objective of this work is to present an integrated system of ad hoc interfaces and tools that we use to perform pseudonymous clinical data collection, both manually and automatically, to support clinical trials. Methods The project comprehends different scenarios of data collection systems, according to the degree of information technology of the involved centers. To be compliant with national regulations, the last developed connection is based on the standard Clinical Document Architecture Release 2 by Health Level 7 guidelines, interoperability is supported by the involvement of a terminology service. Results Since 2011, the LIDN platform has involved more than 8,000 patients from eight different hospitals, treated or under treatment for at least one infectious disease among human immunodeficiency virus (HIV), hepatitis C virus, severe acute respiratory syndrome coronavirus 2, and tuberculosis. Since 2013, systems for the automatic transfer of laboratory data have been updating patients' information for three centers, daily. Direct communication was set up between the LIDN architecture and three of the main national cohorts of HIV-infected patients. Conclusion The LIDN was originally developed to support clinicians involved in the project in the management of data from HIV-infected patients through a web-based tool that could be easily used in primary-care units. Then, the developed system grew modularly to respond to the specific needs that arose over a time span of more than 10 years.

show abstract

“…The first is that it cannot be excluded a priori that a ML model trained on a large number of laboratory and microbiological variables could be already sufficiently accurate in predicting candidemia; thus, in our opinion, this possibility is worth testing [31]. The second point is that our group is concomitantly working on the development of a natural language processing (NLP)-based pipeline for the extraction of clinical variables from the text of laboratory notes and electronic health records [43], that, in the future, could expand our ability to automatically extract relevant features beyond laboratory and microbiological variables.…”

Section: Discussionmentioning

confidence: 99%

Validation of an Automated System for the Extraction of a Wide Dataset for Clinical Studies Aimed at Improving the Early Diagnosis of Candidemia

et al. 2023

Self Cite

View full text Add to dashboard Cite

There is increasing interest in assessing whether machine learning (ML) techniques could further improve the early diagnosis of candidemia among patients with a consistent clinical picture. The objective of the present study is to validate the accuracy of a system for the automated extraction from a hospital laboratory software of a large number of features from candidemia and/or bacteremia episodes as the first phase of the AUTO-CAND project. The manual validation was performed on a representative and randomly extracted subset of episodes of candidemia and/or bacteremia. The manual validation of the random extraction of 381 episodes of candidemia and/or bacteremia, with automated organization in structured features of laboratory and microbiological data resulted in ≥99% correct extractions (with confidence interval < ±1%) for all variables. The final automatically extracted dataset consisted of 1338 episodes of candidemia (8%), 14,112 episodes of bacteremia (90%), and 302 episodes of mixed candidemia/bacteremia (2%). The final dataset will serve to assess the performance of different ML models for the early diagnosis of candidemia in the second phase of the AUTO-CAND project.

show abstract

A NLP Pipeline for the Automatic Extraction of a Complete Microorganism’s Picture from Microbiological Notes

Cited by 5 publications

References 33 publications

Defining a Preprocessing Pipeline for the MULTI-SITA Project and General Medical Italian Natural Language Data

Defining a Preprocessing Pipeline for the MULTI-SITA Project and General Medical Italian Natural Language Data

Ten Years of Medical Informatics and Standards Support for Clinical Research in an Infectious Diseases Network

Validation of an Automated System for the Extraction of a Wide Dataset for Clinical Studies Aimed at Improving the Early Diagnosis of Candidemia

Contact Info

Product

Resources

About