RESUMO
BACKGROUND: Low diagnostic accuracy is a major concern in automated medical history-taking systems with differential diagnosis (DDx) generators. Extending the concept of collective intelligence to the field of DDx generators such that the accuracy of judgment becomes higher when accepting an integrated diagnosis list from multiple people than when accepting a diagnosis list from a single person may be a possible solution. OBJECTIVE: The purpose of this study is to assess whether the combined use of several DDx generators improves the diagnostic accuracy of DDx lists. METHODS: We used medical history data and the top 10 DDx lists (index DDx lists) generated by an artificial intelligence (AI)-driven automated medical history-taking system from 103 patients with confirmed diagnoses. Two research physicians independently created the other top 10 DDx lists (second and third DDx lists) per case by imputing key information into the other 2 DDx generators based on the medical history generated by the automated medical history-taking system without reading the index lists generated by the automated medical history-taking system. We used the McNemar test to assess the improvement in diagnostic accuracy from the index DDx lists to the three types of combined DDx lists: (1) simply combining DDx lists from the index, second, and third lists; (2) creating a new top 10 DDx list using a 1/n weighting rule; and (3) creating new lists with only shared diagnoses among DDx lists from the index, second, and third lists. We treated the data generated by 2 research physicians from the same patient as independent cases. Therefore, the number of cases included in analyses in the case using 2 additional lists was 206 (103 cases × 2 physicians' input). RESULTS: The diagnostic accuracy of the index lists was 46% (47/103). Diagnostic accuracy was improved by simply combining the other 2 DDx lists (133/206, 65%, P<.001), whereas the other 2 combined DDx lists did not improve the diagnostic accuracy of the DDx lists (106/206, 52%, P=.05 in the collective list with the 1/n weighting rule and 29/206, 14%, P<.001 in the only shared diagnoses among the 3 DDx lists). CONCLUSIONS: Simply adding each of the top 10 DDx lists from additional DDx generators increased the diagnostic accuracy of the DDx list by approximately 20%, suggesting that the combinational use of DDx generators early in the diagnostic process is beneficial.
RESUMO
Purpose: The clinical presentation of iron deficiency is not well understood. We aimed to identify the clinical manifestations of iron deficiency without anemia in women. Patients and Methods: We conducted a retrospective cohort study of women who visited the general internal medicine outpatient department of a university hospital in Japan between 2016 and 2022. Women who were prescribed iron supplements were included in the study. Anemia was defined as hemoglobin levels below 12 g/dl. Iron deficiency was defined as serum ferritin levels < 30.0 µg/l. The primary outcome was the difference in symptoms between patients with iron deficiency with and without anemia. The secondary outcome was the ratio of symptom, hemoglobin, and serum ferritin improvement (levels > 30.0 µg/l after treatment), comparing the measurements at the beginning and after supplementation. Results: A total of 147 women were included in the final analysis. There were no significant differences in the initial symptoms and the ratio of symptom improvement between the groups. Compared to patients with iron deficiency anemia, patients with iron deficiency without anemia had high initial serum ferritin levels (14.8 vs 7.1 µg/l, p<0.001), and hemoglobin (13.2 vs 9.9 g/dl, p<0.001). Iron supplements significantly improved the serum ferritin level in two groups and the hemoglobin in iron deficiency anemia. After treatment, iron deficiency without anemia still had high serum ferritin levels (37.7 vs 28.2 µg/l, p=0.017) and hemoglobin (13.3 vs 12.3 g/dl, p < 0.001). Conclusion: There were no differences in any of the investigated symptoms and the ratio of the symptom improvement depending on the anemic state in iron deficiency. After iron supplementation, the serum ferritin levels in the iron deficiency without anemia group improved. Hemoglobin and serum ferritin in iron deficiency without anemia were still highly comparable to that of iron deficiency anemia.
RESUMO
Gold magnetic particles (GMP) are magnetic iron oxide particles modified with gold nanoparticles. The gold particles of GMP specifically bind to cysteine and methionine through Au-S binding. The aim of the present study was to establish a quick and easy protein purification system using novel peptide tags and GMP. Here, we created a variety of peptide tags containing methionine and cysteine and analyzed their affinity to GMP. Binding assays using enhanced green fluorescent protein (EGFP) as a model protein indicated that the tandem methionine tags comprising methionine residues had higher affinity to the GMP than tags comprising both methionine and cysteine residues. Tags comprising both methionine and glycine residues showed slightly higher affinity to GMP and higher elution efficiency than the all-methionine tags. A protein purification assay using phosphorylcholine-treated GMP demonstrated that both a tandem methionine-tagged EGFP and a methionine and glycine-tagged EGFP were specifically purified from a protein mixture with very high efficiency. The efficiency was comparable to that of a histidine-tagged protein purification system. Together, these novel peptide tags, "methionine tags", specifically bind to GMP and can be used for a highly efficient protein purification system.
