Natural language processing pipeline to extract prostate cancer-related information from clinical notes.

OBJECTIVES: To develop an automated pipeline for extracting prostate cancer-related information from clinical notes. MATERIALS AND METHODS: This retrospective study included 23,225 patients who underwent prostate MRI between 2017 and 2022. Cancer risk factors (family history of cancer and digital rectal exam findings), pre-MRI prostate pathology, and treatment history of prostate cancer were extracted from free-text clinical notes in English as binary or multi-class classification tasks. Any sentence containing pre-defined keywords was extracted from clinical notes within one year before the MRI. After manually creating sentence-level datasets with ground truth, Bidirectional Encoder Representations from Transformers (BERT)-based sentence-level models were fine-tuned using the extracted sentence as input and the category as output. The patient-level output was determined by compilation of multiple sentence-level outputs using tree-based models. Sentence-level classification performance was evaluated using the area under the receiver operating characteristic curve (AUC) on 15% of the sentence-level dataset (sentence-level test set). The patient-level classification performance was evaluated on the patient-level test set created by radiologists by reviewing the clinical notes of 603 patients. Accuracy and sensitivity were compared between the pipeline and radiologists. RESULTS: Sentence-level AUCs were ≥ 0.94. The pipeline showed higher patient-level sensitivity for extracting cancer risk factors (e.g., family history of prostate cancer, 96.5% vs. 77.9%, p < 0.001), but lower accuracy in classifying pre-MRI prostate pathology (92.5% vs. 95.9%, p = 0.002) and treatment history of prostate cancer (95.5% vs. 97.7%, p = 0.03) than radiologists, respectively. CONCLUSION: The proposed pipeline showed promising performance, especially for extracting cancer risk factors from patient's clinical notes. CLINICAL RELEVANCE STATEMENT: The natural language processing pipeline showed a higher sensitivity for extracting prostate cancer risk factors than radiologists and may help efficiently gather relevant text information when interpreting prostate MRI. KEY POINTS: When interpreting prostate MRI, it is necessary to extract prostate cancer-related information from clinical notes. This pipeline extracted the presence of prostate cancer risk factors with higher sensitivity than radiologists. Natural language processing may help radiologists efficiently gather relevant prostate cancer-related text information.

Focal Nodular Hyperplasia and Focal Nodular Hyperplasia-like Lesions.

Focal nodular hyperplasia (FNH) is a benign lesion occurring in a background of normal liver. FNH is seen most commonly in young women and can often be accurately diagnosed at imaging, including CT, MRI, or contrast-enhanced US. In the normal liver, FNH frequently must be differentiated from hepatocellular adenoma, which although benign, is managed differently because of the risks of hemorrhage and malignant transformation. When lesions that are histologically identical to FNH occur in a background of abnormal liver, they are termed FNH-like lesions. These lesions can be a source of diagnostic confusion and must be differentiated from malignancies. Radiologists' familiarity with the imaging appearance of FNH-like lesions and knowledge of the conditions that predispose a patient to their formation are critical to minimizing the risks of unnecessary intervention for these lesions, which are rarely symptomatic and carry no risk for malignant transformation. FNH is thought to form secondary to an underlying vascular disturbance, a theory supported by the predilection for formation of FNH-like lesions in patients with a variety of hepatic vascular abnormalities. These include abnormalities of hepatic outflow such as Budd-Chiari syndrome, abnormalities of hepatic inflow such as congenital absence of the portal vein, and hepatic microvascular disturbances, such as those that occur after exposure to certain chemotherapeutic agents. Familiarity with the imaging appearances of these varied conditions and knowledge of their association with formation of FNH-like lesions allow radiologists to identify with confidence these benign lesions that require no intervention. Online supplemental material is available for this article. ©RSNA, 2022.

A Clinical Review of Mesenteric Panniculitis.

Mesenteric panniculitis (MP) is a benign condition characterized by chronic inflammation and fibrosis of adipose tissue mainly of the small bowel mesentery. MP is commonly detected incidentally on cross-sectional imaging of the abdomen and can be asymptomatic in up to nearly half of patients. The most frequent clinical symptom reported is abdominal pain, followed by bloating/distention, diarrhea, constipation, vomiting, anorexia, weight loss, fever, malaise, and nausea. On computed tomography, MP is seen as a mass-like area of increased fat attenuation within the small bowel mesentery, usually located in the left upper quadrant of the abdomen. This mass-like area envelops mesenteric vessels and displaces adjacent bowel segments. Lymph nodes are frequently seen within the area of mesenteric abnormality. One of the most common differential diagnoses of MP is lymphoma, and positron emission tomography/computed tomography may be performed if there is suspicion of a concurrent underlying malignancy. Because of the benign nature of MP, treatment decisions should be guided by severity of symptoms and presence of complications. First-line medical treatment is prednisone and tamoxifen. Surgery is reserved for cases of recurrent bowel obstruction. This article provides a review of MP, including its epidemiology, pathophysiology, clinical presentation, imaging findings, and treatment.

Abdominal radiograph pearls and pitfalls for the emergency department radiologist: a pictorial review.

Abdominal plain films are often the first imaging examination performed on a patient with abdominal pain in the emergency department. Radiograph findings can help guide clinical management and the need for advanced imaging. A pictorial review of a range of abdominal radiograph findings is presented, including bowel gas patterns, abdominal organ evaluation, pathologic gas, calcifications, implanted devices, and foreign bodies.

Utility of Ultrasound in the Diagnosis, Treatment, and Follow-up of Prostate Cancer: State of the Art.

Prostate cancer screening currently consists of serum prostate-specific antigen and digital rectal examination, followed by transrectal ultrasound-guided biopsy for diagnostic confirmation. Although the current paradigm of prostate cancer screening has led to a decrease in advanced disease and cancer-related mortality, these techniques have limitations in terms of sensitivity and specificity, resulting in missed cancers that are clinically significant and the overdetection of clinically insignificant cancers. New imaging techniques and technologies are required to improve the detection of prostate cancer. This article summarizes the use of novel ultrasound techniques and technologies in the detection, biopsy, and treatment of prostate cancer.

Elevation of interleukin-6 levels in cervical secretions as a predictor of preterm delivery.

BACKGROUND: The objective of this study was to evaluate the predictive value of interleukin-6 (IL-6) in cervical secretions for preterm delivery before 34+0 gestational weeks in patients with preterm labor. METHODS: In this prospective study, 31 patients were enrolled with preterm labor and intact membranes. Cervical swabs were taken on admission and the concentration of IL-6 was measured. The gestational age at the time of admission and delivery, as well as the time interval to delivery, were evaluated and compared with the concentration of IL-6 on admission. RESULTS: Cervical IL-6 was significantly elevated in the preterm delivery group (< 34+0 gestational weeks, p < 0.05). Choosing 20 pg/ml as a cut-off concentration, cervical IL-6 had a sensitivity and negative predictive value of 100%, a specificity of 67% and a positive predictive value of 47%. Concerning the time interval to delivery, the sensitivity of IL-6 was 100% and the specificity 57% for delivery within 2 days and 100% and 64% for delivery within 7 days. CONCLUSIONS: Cervical IL-6 is a new, promising diagnostic tool to identify patients at high risk of preterm delivery.