Emergency teleradiological activity is an epidemiological estimator and predictor of the covid-19 pandemic in mainland France

Using the Textual Content of Radiological Reports to Detect Emerging Diseases: A Proof-of-Concept Study of COVID-19

Changes in the content of radiological reports at population level could detect emerging diseases. Herein, we developed a method to quantify similarities in consecutive temporal groupings of radiological reports using natural language processing, and we investigated whether appearance of dissimilarities between consecutive periods correlated with the beginning of the COVID-19 pandemic in France. CT reports from 67,368 consecutive adults across 62 emergency departments throughout France between October 2019 and March 2020 were collected. Reports were vectorized using time frequency-inverse document frequency (TF-IDF) analysis on one-grams. For each successive 2-week period, we performed unsupervised clustering of the reports based on TF-IDF values and partition-around-medoids. Next, we assessed the similarities between this clustering and a clustering from two weeks before according to the average adjusted Rand index (AARI). Statistical analyses included (1) cross-correlation functions (CCFs) with the number of positive SARS-CoV-2 tests and advanced sanitary index for flu syndromes (ASI-flu, from open-source dataset), and (2) linear regressions of time series at different lags to understand the variations of AARI over time. Overall, 13,235 chest CT reports were analyzed. AARI was correlated with ASI-flu at lag = + 1, + 5, and + 6 weeks (P = 0.0454, 0.0121, and 0.0042, respectively) and with SARS-CoV-2 positive tests at lag = - 1 and 0 week (P = 0.0057 and 0.0001, respectively). In the best fit, AARI correlated with the ASI-flu with a lag of 2 weeks (P = 0.0026), SARS-CoV-2-positive tests in the same week (P < 0.0001) and their interaction (P < 0.0001) (adjusted R2 = 0.921). Thus, our method enables the automatic monitoring of changes in radiological reports and could help capturing disease emergence.

Emergency department CT examinations demonstrate no evidence of early viral circulation at the start of the COVID-19 pandemic-a multicentre epidemiological study

BACKGROUND

Biological studies suggested that the COVID-19 outbreak in France occurred before the first official diagnosis on January 24, 2020. We investigated this controversial topic using a large collection of chest CTs performed throughout French emergency departments within 6 months before the 1st lockdown.

RESULTS

Overall, 49,311 consecutive patients (median age: 60 years, 23,636/49,311 [47.9%] women) with available chest CT images and reports from 61 emergency departments between September 1, 2020, and March 16, 2020 (day before the 1st French lockdown), were retrospectively included in this multicentre study. In the macroscopic analysis of reports automatically (labelled for presence of ground glass opacities [GGOs], reticulations, and bilateral and subpleural abnormalities), we found a significant breakpoint on February 17, 2020, for the weekly time series with 1, 2 and ≥ 3 of these 4 radiological features, with 146/49,311 (0.3%) patients showing bilateral abnormalities and ground glass opacities (GGOs) from that day. According to radiologists, 22/146 (15.1%) CT images showed typical characteristics of COVID-19, including 4/146 (2.7%) before February 2020. According to hospital records, one patient remained without microbial diagnosis, two patients had proven influenza A and one patient had concomitant influenza A and mycoplasma infection.

CONCLUSION

These results suggest that SARS-CoV-2 was not circulating in the areas covered by the 61 emergency departments involved in our study before the official beginning of the COVID-19 outbreak in France. In emergency patients, the strong resemblance among mycoplasma, influenza A and SARS-CoV-2 lung infections on chest CT and the nonspecificity of CT patterns in low prevalence periods is stressed.

CRITICAL RELEVANCE STATEMENT

We proposed here an innovative approach to revisit a controversial 'real' start of the COVID-19 pandemic in France based on (1) a population-level approach combining text mining, time series analysis and an epidemiological dataset and (2) a patient-level approach with careful retrospective reading of chest CT scans complemented by analysis of samples performed contemporarily to the chest CT. We showed no evidence that SARS-CoV-2 was actively circulating in France before February 2020.

How artificial intelligence improves radiological interpretation in suspected pulmonary embolism

Objectives

To evaluate and compare the diagnostic performances of a commercialized artificial intelligence (AI) algorithm for diagnosing pulmonary embolism (PE) on CT pulmonary angiogram (CTPA) with those of emergency radiologists in routine clinical practice.

Methods

This was an IRB-approved retrospective multicentric study including patients with suspected PE from September to December 2019 (i.e., during a preliminary evaluation period of an approved AI algorithm). CTPA quality and conclusions by emergency radiologists were retrieved from radiological reports. The gold standard was a retrospective review of CTPA, radiological and clinical reports, AI outputs, and patient outcomes. Diagnostic performance metrics for AI and radiologists were assessed in the entire cohort and depending on CTPA quality.

Results

Overall, 1202 patients were included (median age: 66.2 years). PE prevalence was 15.8% (190/1202). The AI algorithm detected 219 suspicious PEs, of which 176 were true PEs, including 19 true PEs missed by radiologists. In the cohort, the highest sensitivity and negative predictive values (NPVs) were obtained with AI (92.6% versus 90% and 98.6% versus 98.1%, respectively), while the highest specificity and positive predictive value (PPV) were found with radiologists (99.1% versus 95.8% and 95% versus 80.4%, respectively). Accuracy, specificity, and PPV were significantly higher for radiologists except in subcohorts with poor-to-average injection quality. Radiologists positively evaluated the AI algorithm to improve their diagnostic comfort (55/79 [69.6%]).

Conclusion

Instead of replacing radiologists, AI for PE detection appears to be a safety net in emergency radiology practice due to high sensitivity and NPV, thereby increasing the self-confidence of radiologists.

Key Points

• Both the AI algorithm and emergency radiologists showed excellent performance in diagnosing PE on CTPA (sensitivity and specificity ≥ 90%; accuracy ≥ 95%).

• The AI algorithm for PE detection can help increase the sensitivity and NPV of emergency radiologists in clinical practice, especially in cases of poor-to-moderate injection quality.

• Emergency radiologists recommended the use of AI for PE detection in satisfaction surveys to increase their confidence and comfort in their final diagnosis.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00330-022-08645-2.

What Influences the Way Radiologists Express Themselves in Their Reports? A Quantitative Assessment Using Natural Language Processing

Although using standardized reports is encouraged, most emergency radiological reports in France remain in free-text format that can be mined with natural language processing for epidemiological purposes, activity monitoring or data collection. These reports are obtained under various on-call conditions by radiologists with various backgrounds. Our aim was to investigate what influences the radiologists’ written expressions. To do so, this retrospective multicentric study included 30,227 emergency radiological reports of computed tomography scans and magnetic resonance imaging involving exactly one body region, only with pathological findings, interpreted from 2019–09-01 to 2020–02-28 by 165 radiologists. After text pre-processing, one-word tokenization and use of dictionaries for stop words, polarity, sentiment and uncertainty, 11 variables depicting the structure and content of words and sentences in the reports were extracted and summarized to 3 principal components capturing 93.7% of the dataset variance. In multivariate analysis, the 1^st principal component summarized the length and lexical diversity of the reports and was significantly influenced by the weekday, time slot, workload, number of examinations previously interpreted by the radiologist during the on-call period, type of examination, emergency level and radiologists’ gender (P value range: < 0.0001–0.0029). The 2^nd principal component summarized negative formulations, polarity and sentence length and was correlated with the number of examination previously interpreted by the radiologist, type of examination, emergency level, imaging modality and radiologists’ experience (P value range: < 0.0001–0.0032). The last principal component summarized questioning, uncertainty and polarity and was correlated with the type of examination and emergency level (all P values < 0.0001). Thus, the length, structure and content of emergency radiological reports were significantly influenced by organizational, radiologist- and examination-related characteristics, highlighting the subjectivity and variability in the way radiologists express themselves during their clinical activity. These findings advocate for more homogeneous practices in radiological reporting and stress the need to consider these influential features when developing models based on natural language processing.

Impact of COVID-19 on the incidence of CT-diagnosed appendicitis and its complications in the UK and Sweden

AIM

To compare the number of appendicitis cases and its complications, during the first months of the COVID-19 pandemic in Sweden and the UK and the corresponding time period in 2019.

METHOD

Reports of emergency abdominopelvic CT performed at 56 Swedish hospitals and 38 British hospitals between April and July 2020 and a corresponding control cohort from 2019 were reviewed. Two radiologists and two surgeons blinded to the date of cohorts analyzed all reports for diagnosis of appendicitis, perforation, and abscess. A random selection of cases was chosen for the measurement of inter-rater agreement.

RESULT

Both in Sweden (6111) and the UK (5591) fewer, abdominopelvic CT scans were done in 2020 compared to 2019 (6433 and 7223, respectively); p < 0.001. In the UK, the number of appendicitis was 36% lower in April-June 2020 compared to 2019 but not in Sweden. Among the appendicitis cases, there was a higher number of perforations and abscesses in 2020, in Sweden. In the UK, the number of perforations and abscesses were initially lower (April-June 2020) but increased in July 2020. There was a substantial inter-rater agreement for the diagnosis of perforations and abscess formations (K = 0.64 and 0.77).

CONCLUSION

In Sweden, the number of appendicitis was not different between 2019 and 2020; however, there was an increase of complications. In the UK, there was a significant decrease of cases in 2020. The prevalence of complications was lower initially but increased in July. These findings suggest variability in delay in diagnosis of appendicitis depending on the country and time frame studied.