Multiple complications, including heart, liver, and kidney disease. Have implemented DITTO to identify cohorts of patients withĭocumented diagnoses of diabetes mellitus, hypertension, and overweight – commonĭiseases, which in turn place patients at risk for Of the text of physician notes, and can be employed in healthcare enterprises. Patient cohorts with a particular diagnosis through analysis Through Textual element Occurrences) that accurately and rapidly identifies We therefore have designed a software tool DITTO (Diagnosis Identification Systems are not freely available to the public. Additionally, commercially available software is expensive and most academic Training on the data set and are slow (take c. However, these tools require extensive manual More recently, both academic 13 and commercial 14 tools were reported to have attained high accuracy in identifying clinicalĬoncepts from free text. Most of the early reports were characterized by There have been a number of attempts to identify diagnoses from the text In physician notes is unstructured and its analysis presents a technical Notes are a very rich source of clinical information 8, and are now commonly available in digital format. Is currently most commonly used for large-scale applications despiteĪs most elements of the medical record are increasingly computerized, moreĭata becomes available for computer-assisted analysis. In a medium to large-size healthcare facility. Is a labor-intensive process that is not scalable to the level needed Of individuals diagnosed with a particular disease. Manual chart review remains the gold standard for identification Each of these methods has its own shortcomings and sensitivity remains Several approaches have been used to identify patients with specific conditions, includingĭeath certificates 3, billing data 4 – 6, and surveys 7. Include, among others, quality of care surveillance 1, identification of prospective subjects for a research study 2 and clinical decision support. Require identification of large patient cohorts with a particular diagnosis. We plan to continue to work to enhance its functionality andĪ number of important applications in medicine and biomedical research DITTO is an important advancement in the field, and DITTOĬan be adapted for use in another healthcare facility or to detectĪ different diagnosis. Of currently used techniques for each of the three diseases. Its accuracy substantially exceeded the performance DITTO processed 1.7×10 5 notes/hr with sensitivity ranging from 74 to 96%, and specificityįrom 86 to 100%. Overweight has shown it to be rapid and highly accurate. Through analysis of the text of physician notes in the electronic medicalĮvaluation of DITTO on the example of diabetes mellitus, hypertension and We have therefore designed DITTO – a toolįor identification of patients with a documented specific diagnosis Currently used methods are either labor-intensive Study subjects, require identification of large cohorts of patients Quality of care surveillance and identification of prospective A number of important applications in medicine and biomedical research, including
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |