A Large-Scale Multicenter Retrospective Study on Nephrotoxicity Associated With Empiric Broad-Spectrum Antibiotics in Critically Ill Patients.

BACKGROUND: Evidence regarding acute kidney injury associated with concomitant administration of vancomycin and piperacillin-tazobactam is conflicting, particularly in patients in the ICU. RESEARCH QUESTION: Does a difference exist in the association between commonly prescribed empiric antibiotics on ICU admission (vancomycin and piperacillin-tazobactam, vancomycin and cefepime, and vancomycin and meropenem) and acute kidney injury? STUDY DESIGN AND METHODS: This was a retrospective cohort study using data from the eICU Research Institute, which contains records for ICU stays between 2010 and 2015 across 335 hospitals. Patients were enrolled if they received vancomycin and piperacillin-tazobactam, vancomycin and cefepime, or vancomycin and meropenem exclusively. Patients initially admitted to the ED were included. Patients with hospital stay duration of < 1 h, receiving dialysis, or with missing data were excluded. Acute kidney injury was defined as Kidney Disease: Improving Global Outcomes stage 2 or 3 based on serum creatinine component. Propensity score matching was used to match patients in the control (vancomycin and meropenem or vancomycin and cefepime) and treatment (vancomycin and piperacillin-tazobactam) groups, and ORs were calculated. Sensitivity analyses were performed to study the effect of longer courses of combination therapy and patients with renal insufficiency on admission. RESULTS: Thirty-five thousand six hundred fifty-four patients met inclusion criteria (vancomycin and piperacillin-tazobactam, n = 27,459; vancomycin and cefepime, n = 6,371; vancomycin and meropenem, n = 1,824). Vancomycin and piperacillin-tazobactam was associated with a higher risk of acute kidney injury and initiation of dialysis when compared with that of both vancomycin and cefepime (Acute kidney injury: OR, 1.37 [95% CI, 1.25-1.49]; dialysis: OR, 1.28 [95% CI, 1.14-1.45]) and vancomycin and meropenem (Acute kidney injury: OR, 1.27 [95%, 1.06-1.52]; dialysis: OR, 1.56 [95% CI, 1.23-2.00]). The odds of acute kidney injury developing was especially pronounced in patients without renal insufficiency receiving a longer duration of vancomycin and piperacillin-tazobactam therapy compared with vancomycin and meropenem therapy. INTERPRETATION: VPT is associated with a higher risk of acute kidney injury than both vancomycin and cefepime and vancomycin and meropenem in patients in the ICU, especially for patients with normal initial kidney function requiring longer durations of therapy. Clinicians should consider vancomycin and meropenem or vancomycin and cefepime to reduce the risk of nephrotoxicity for patients in the ICU.

Deep Learning for Cancer Symptoms Monitoring on the Basis of Electronic Health Record Unstructured Clinical Notes.

PURPOSE: Symptoms are vital outcomes for cancer clinical trials, observational research, and population-level surveillance. Patient-reported outcomes (PROs) are valuable for monitoring symptoms, yet there are many challenges to collecting PROs at scale. We sought to develop, test, and externally validate a deep learning model to extract symptoms from unstructured clinical notes in the electronic health record. METHODS: We randomly selected 1,225 outpatient progress notes from among patients treated at the Dana-Farber Cancer Institute between January 2016 and December 2019 and used 1,125 notes as our training/validation data set and 100 notes as our test data set. We evaluated the performance of 10 deep learning models for detecting 80 symptoms included in the National Cancer Institute's Patient-Reported Outcomes version of the Common Terminology Criteria for Adverse Events (PRO-CTCAE) framework. Model performance as compared with manual chart abstraction was assessed using standard metrics, and the highest performer was externally validated on a sample of 100 physician notes from a different clinical context. RESULTS: In our training and test data sets, 75 of the 80 candidate symptoms were identified. The ELECTRA-small model had the highest performance for symptom identification at the token level (ie, at the individual symptom level), with an F1 of 0.87 and a processing time of 3.95 seconds per note. For the 10 most common symptoms in the test data set, the F1 score ranged from 0.98 for anxious to 0.86 for fatigue. For external validation of the same symptoms, the note-level performance ranged from F1 = 0.97 for diarrhea and dizziness to F1 = 0.73 for swelling. CONCLUSION: Training a deep learning model to identify a wide range of electronic health record-documented symptoms relevant to cancer care is feasible. This approach could be used at the health system scale to complement to electronic PROs.

Natural Language Processing to Identify Advance Care Planning Documentation in a Multisite Pragmatic Clinical Trial.

CONTEXT: Large multisite clinical trials studying decision-making when facing serious illness require an efficient method for abstraction of advance care planning (ACP) documentation from clinical text documents. However, the current gold standard method of manual chart review is time-consuming and unreliable. OBJECTIVES: To evaluate the ability to use natural language processing (NLP) to identify ACP documention in clinical notes from patients participating in a multisite trial. METHODS: Patients with advanced cancer followed in three disease-focused oncology clinics at Duke Health, Mayo Clinic, and Northwell Health were identified using administrative data. All outpatient and inpatient notes from patients meeting inclusion criteria were extracted from electronic health records (EHRs) between March 2018 and March 2019. NLP text identification software with semi-automated chart review was applied to identify documentation of four ACP domains: (1) conversations about goals of care, (2) limitation of life-sustaining treatment, (3) involvement of palliative care, and (4) discussion of hospice. The performance of NLP was compared to gold standard manual chart review. RESULTS: 435 unique patients with 79,797 notes were included in the study. In our validation data set, NLP achieved F1 scores ranging from 0.84 to 0.97 across domains compared to gold standard manual chart review. NLP identified ACP documentation in a fraction of the time required by manual chart review of EHRs (1-5 minutes per patient for NLP, vs. 30-120 minutes for manual abstraction). CONCLUSION: NLP is more efficient and as accurate as manual chart review for identifying ACP documentation in studies with large patient cohorts.

Mining heterogeneous clinical notes by multi-modal latent topic model.

Latent knowledge can be extracted from the electronic notes that are recorded during patient encounters with the health system. Using these clinical notes to decipher a patient's underlying comorbidites, symptom burdens, and treatment courses is an ongoing challenge. Latent topic model as an efficient Bayesian method can be used to model each patient's clinical notes as "documents" and the words in the notes as "tokens". However, standard latent topic models assume that all of the notes follow the same topic distribution, regardless of the type of note or the domain expertise of the author (such as doctors or nurses). We propose a novel application of latent topic modeling, using multi-note topic model (MNTM) to jointly infer distinct topic distributions of notes of different types. We applied our model to clinical notes from the MIMIC-III dataset to infer distinct topic distributions over the physician and nursing note types. Based on manual assessments made by clinicians, we observed a significant improvement in topic interpretability using MNTM modeling over the baseline single-note topic models that ignore the note types. Moreover, our MNTM model led to a significantly higher prediction accuracy for prolonged mechanical ventilation and mortality using only the first 48 hours of patient data. By correlating the patients' topic mixture with hospital mortality and prolonged mechanical ventilation, we identified several diagnostic topics that are associated with poor outcomes. Because of its elegant and intuitive formation, we envision a broad application of our approach in mining multi-modality text-based healthcare information that goes beyond clinical notes. Code available at https://github.com/li-lab-mcgill/heterogeneous_ehr.

Aging Process of Lateral Facial Fat Compartments: A Retrospective Study.

BACKGROUND: Since 2007, when the anatomy of facial fat compartment was described, an increasing number of studies on the aging process of the compartment of cadavers has emerged. OBJECTIVES: The authors evaluated the aging changes of lateral facial fat compartments on the same person. METHODS: Sixty-three patients were included in this retrospective study. All patients had magnetic resonance imaging scans with at least 4 years apart. The authors targeted the fat compartments of the superficial temporal, subcutaneous temporal, and buccal fat pad, comparing the data on different time points. RESULTS: The thickness of the subcutaneous temporal fat did not change significantly. The 3 diameters of the superficial temporal fat compartment all became thinner on the axial view (P < 0.05). On the sagittal view, the superficial temporal fat elongated from 38.89 mm to 43.74 mm (P < 0.05). The buccal fat compartment also lengthened from 68.73 mm to 74.39 mm (P < 0.05) and had a positive correlation with follow-up duration only. CONCLUSIONS: The study revealed the fat compartment change on the same person with time. The temporal hollow mainly originates from the thinner part of the superficial temporal fat. The descending of the buccal fat pad aggravates the labiomandibular fold. By understanding the aging process more fully, we can rejuvenate our patients more naturally.

MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports.

Chest radiography is an extremely powerful imaging modality, allowing for a detailed inspection of a patient's chest, but requires specialized training for proper interpretation. With the advent of high performance general purpose computer vision algorithms, the accurate automated analysis of chest radiographs is becoming increasingly of interest to researchers. Here we describe MIMIC-CXR, a large dataset of 227,835 imaging studies for 65,379 patients presenting to the Beth Israel Deaconess Medical Center Emergency Department between 2011-2016. Each imaging study can contain one or more images, usually a frontal view and a lateral view. A total of 377,110 images are available in the dataset. Studies are made available with a semi-structured free-text radiology report that describes the radiological findings of the images, written by a practicing radiologist contemporaneously during routine clinical care. All images and reports have been de-identified to protect patient privacy. The dataset is made freely available to facilitate and encourage a wide range of research in computer vision, natural language processing, and clinical data mining.

Quantitative analysis of enhanced malignant and benign lesions on contrast-enhanced spectral mammography.

OBJECTIVE: To retrospectively analyze the quantitative measurement and kinetic enhancement among pathologically proven benign and malignant lesions using contrast-enhanced spectral mammography (CESM). METHODS: We investigated the differences in enhancement between 44 benign and 108 malignant breast lesions in CESM, quantifying the extent of enhancements and the relative enhancements between early (between 2-3 min after contrast medium injection) and late (3-6 min) phases. RESULTS: The enhancement was statistically stronger in malignancies compared to benign lesions, with good performance by the receiver operating characteristic curve [0.877, 95% confidence interval (0.813-0.941)]. Using optimal cut-off value at 220.94 according to Youden index, the sensitivity was 75.9%, specificity 88.6%, positive likelihood ratio 6.681, negative likelihood ratio 0.272 and accuracy 82.3%. The relative enhancement patterns of benign and malignant lesions, showing 29.92 vs 73.08% in the elevated pattern, 7.14 vs 92.86% in the steady pattern, 5.71 vs 94.29% in the depressed pattern, and 80.00 vs 20.00% in non-enhanced lesions (p < 0.0001), respectively. CONCLUSION: Despite variations in the degree of tumour angiogenesis, quantitative analysis of the breast lesions on CESM documented the malignancies had distinctive stronger enhancement and depressed relative enhancement patterns than benign lesions. Advances in knowledge: To our knowledge, this is the first study evaluating the feasibility of quantifying lesion enhancement on CESM. The quantities of enhancement were informative for assessing breast lesions in which the malignancies had stronger enhancement and more relative depressed enhancement than the benign lesions.

Progressive Sarcopenia in Patients With Colorectal Cancer Predicts Survival.

OBJECTIVE: The purpose of this study was to evaluate the relationship between sarcopenia and overall and progression-free survival in patients with colorectal cancer. MATERIALS AND METHODS: This study was retrospective and complied with HIPAA. Patients with colorectal cancer who underwent CT at the time of and 6-18 months after diagnosis were included. Patients were followed for at least 5 years after diagnosis. Skeletal muscle index (SMI) and mean muscle attenuation of the psoas and paraspinal muscles at the L4 level determined the degree of sarcopenia. Composite measurements combining psoas and paraspinal muscles (total muscle) were also obtained. Univariate and multivariate Cox proportional hazard analysis was performed to evaluate the association between survival and changes in SMI and changes in attenuation. Kaplan-Meier analysis was also performed. RESULTS: A total of 101 patients were included (mean age ± SD, 63.7 ± 13.7 years; 68 men, 33 women). The hazard ratios for overall survival were 2.27, 1.68, and 1.54 for changes in SMI of the psoas muscle, paraspinal muscle, and total muscle (all p < 0.05). The hazard ratios for overall survival were 1.14, 1.18, and 1.24 for changes in attenuation of the psoas muscle, paraspinal muscle, and total muscle, respectively (all p < 0.05). The hazard ratios for progression-free survival were 1.33, 1.41, and 1.23 for changes in SMI of the psoas muscle, paraspinal muscle, and total muscle (not statistically significant). The hazard ratios for progression-free survival were 1.10, 1.21, and 1.23 for changes in attenuation of the psoas muscle, paraspinal muscle, and total muscle, respectively (p < 0.05). Kaplan-Meier analysis showed significant differences in overall and progression-free survival based on sex-specific quartiles of muscle quantity and quality. CONCLUSION: Progressive sarcopenia after diagnosis of colorectal cancer has a significant negative prognostic association with overall and progression-free survival.