The Use of Breast-specific Gamma Imaging as a Low-Cost Problem-Solving Strategy for Avoiding Biopsies in Patients With Inconclusive Imaging Findings on Mammography and Ultrasonography.

OBJECTIVE: To evaluate the clinical performance and financial costs of breast-specific gamma imaging (BSGI) as a biopsy-reducing problem-solving strategy in patients with inconclusive diagnostic imaging findings. METHODS: A retrospective analysis of all patients for whom BSGI was utilized for inconclusive imaging findings following complete diagnostic mammographic and sonographic evaluation between January 2013 and December 2018 was performed. Positive BSGI findings were correlated and biopsied with either US or stereotactic technique with confirmation by clip location and pathology. After a negative BSGI result, patients were followed for a minimum of 24 months or considered lost to follow-up and excluded (22 patients). Results of further imaging studies, biopsies, and pathology results were analyzed. Net savings of avoided biopsies were calculated based on average Medicare charges. RESULTS: Four hundred and forty female patients from 30 to 95 years (mean 55 years) of age were included in our study. BSGI demonstrated a negative predictive value (NPV) of 98.4% (314/319) and a positive predictive value for biopsy of 35.5% (43/121). The overall sensitivity was 89.6% (43/48), and the specificity was 80.1% (314/392). In total, 78 false positive but only 5 false negative BSGI findings were identified. Six hundred and twenty-one inconclusive imaging findings were analyzed with BSGI and a total of 309 biopsies were avoided. Estimated net financial savings from avoided biopsies were $646 897. CONCLUSION: In the management of patients with inconclusive imaging findings on mammography or ultrasonography, BSGI is a problem-solving imaging modality with high NPV that helps avoid costs of image-guided biopsies.

Multi-modal learning for inpatient length of stay prediction.

Predicting inpatient length of stay (LoS) is important for hospitals aiming to improve service efficiency and enhance management capabilities. Patient medical records are strongly associated with LoS. However, due to diverse modalities, heterogeneity, and complexity of data, it becomes challenging to effectively leverage these heterogeneous data to put forth a predictive model that can accurately predict LoS. To address the challenge, this study aims to establish a novel data-fusion model, termed as DF-Mdl, to integrate heterogeneous clinical data for predicting the LoS of inpatients between hospital discharge and admission. Multi-modal data such as demographic data, clinical notes, laboratory test results, and medical images are utilized in our proposed methodology with individual "basic" sub-models separately applied to each different data modality. Specifically, a convolutional neural network (CNN) model, which we termed CRXMDL, is designed for chest X-ray (CXR) image data, two long short-term memory networks are used to extract features from long text data, and a novel attention-embedded 1D convolutional neural network is developed to extract useful information from numerical data. Finally, these basic models are integrated to form a new data-fusion model (DF-Mdl) for inpatient LoS prediction. The proposed method attains the best R2 and EVAR values of 0.6039 and 0.6042 among competitors for the LoS prediction on the Medical Information Mart for Intensive Care (MIMIC)-IV test dataset. Empirical evidence suggests better performance compared with other state-of-the-art (SOTA) methods, which demonstrates the effectiveness and feasibility of the proposed approach.