Do comprehensive deep learning algorithms suffer from hidden stratification? A retrospective study on pneumothorax detection in chest radiography

Occult tension pneumothorax discovered following imaging for adult trauma patients in the modern major trauma system: a multicentre observational study

BACKGROUND

Tension pneumothorax following trauma is a life-threatening emergency and radiological investigation is normally discouraged prior to treatment in traditional trauma doctrines such as ATLS. Some trauma patients may be physiologically stable enough for diagnostic imaging and occult tension pneumothorax is discovered radiologically. We assessed the outcomes of these patients and compared them with those with clinical diagnosis of tension pneumothorax prior to imaging.

METHODS

A multicentre civilian-military collaborative network of six major trauma centres in the UK collected observational data from adult patients who had a diagnosis of traumatic tension pneumothorax during a 33-month period. Patients were divided into 'radiological' (diagnosis following CT/CXR) or 'clinical' (no prior CT/CXR) groups. The effect of radiological diagnosis on survival was analysed using multivariable logistic regression that included the covariates of age, gender, comorbidities and Injury Severity Score.

RESULTS

There were 133 patients, with a median age of 41 (IQR 24-61); 108 (81%) were male. Survivors included 49 of 59 (83%) in the radiological group and 59 of 74 (80%) in the clinical group (p=0.487). Multivariable logistic regression showed no significant association between radiological diagnosis and survival (OR 2.40, 95% CI 0.80 to 7.95; p=0.130). There was no significant difference in mortality between the groups.

CONCLUSION

Radiological imaging may be appropriate for selected trauma patients at risk of tension pneumothorax if they are considered haemodynamically stable. Trauma patients may be physiologically stable enough for radiological imaging but have occult tension pneumothorax because they did not have the typical clinical presentation. The historical dogma of the 'forbidden scan' no longer applies to such patients.

Radiomics-based decision support tool assists radiologists in small lung nodule classification and improves lung cancer early diagnosis

BACKGROUND

Methods to improve stratification of small (≤15 mm) lung nodules are needed. We aimed to develop a radiomics model to assist lung cancer diagnosis.

METHODS

Patients were retrospectively identified using health records from January 2007 to December 2018. The external test set was obtained from the national LIBRA study and a prospective Lung Cancer Screening programme. Radiomics features were extracted from multi-region CT segmentations using TexLab2.0. LASSO regression generated the 5-feature small nodule radiomics-predictive-vector (SN-RPV). K-means clustering was used to split patients into risk groups according to SN-RPV. Model performance was compared to 6 thoracic radiologists. SN-RPV and radiologist risk groups were combined to generate "Safety-Net" and "Early Diagnosis" decision-support tools.

RESULTS

In total, 810 patients with 990 nodules were included. The AUC for malignancy prediction was 0.85 (95% CI: 0.82-0.87), 0.78 (95% CI: 0.70-0.85) and 0.78 (95% CI: 0.59-0.92) for the training, test and external test datasets, respectively. The test set accuracy was 73% (95% CI: 65-81%) and resulted in 66.67% improvements in potentially missed [8/12] or delayed [6/9] cancers, compared to the radiologist with performance closest to the mean of six readers.

CONCLUSIONS

SN-RPV may provide net-benefit in terms of earlier cancer diagnosis.

Analysis of Line and Tube Detection Performance of a Chest X-ray Deep Learning Model to Evaluate Hidden Stratification

This retrospective case-control study evaluated the diagnostic performance of a commercially available chest radiography deep convolutional neural network (DCNN) in identifying the presence and position of central venous catheters, enteric tubes, and endotracheal tubes, in addition to a subgroup analysis of different types of lines/tubes. A held-out test dataset of 2568 studies was sourced from community radiology clinics and hospitals in Australia and the USA, and was then ground-truth labelled for the presence, position, and type of line or tube from the consensus of a thoracic specialist radiologist and an intensive care clinician. DCNN model performance for identifying and assessing the positioning of central venous catheters, enteric tubes, and endotracheal tubes over the entire dataset, as well as within each subgroup, was evaluated. The area under the receiver operating characteristic curve (AUC) was assessed. The DCNN algorithm displayed high performance in detecting the presence of lines and tubes in the test dataset with AUCs > 0.99, and good position classification performance over a subpopulation of ground truth positive cases with AUCs of 0.86-0.91. The subgroup analysis showed that model performance was robust across the various subtypes of lines or tubes, although position classification performance of peripherally inserted central catheters was relatively lower. Our findings indicated that the DCNN algorithm performed well in the detection and position classification of lines and tubes, supporting its use as an assistant for clinicians. Further work is required to evaluate performance in rarer scenarios, as well as in less common subgroups.

Deep learning for pneumothorax diagnosis: a systematic review and meta-analysis

BACKGROUND

Deep learning (DL), a subset of artificial intelligence (AI), has been applied to pneumothorax diagnosis to aid physician diagnosis, but no meta-analysis has been performed.

METHODS

A search of multiple electronic databases through September 2022 was performed to identify studies that applied DL for pneumothorax diagnosis using imaging. Meta-analysis via a hierarchical model to calculate the summary area under the curve (AUC) and pooled sensitivity and specificity for both DL and physicians was performed. Risk of bias was assessed using a modified Prediction Model Study Risk of Bias Assessment Tool.

RESULTS

In 56 of the 63 primary studies, pneumothorax was identified from chest radiography. The total AUC was 0.97 (95% CI 0.96-0.98) for both DL and physicians. The total pooled sensitivity was 84% (95% CI 79-89%) for DL and 85% (95% CI 73-92%) for physicians and the pooled specificity was 96% (95% CI 94-98%) for DL and 98% (95% CI 95-99%) for physicians. More than half of the original studies (57%) had a high risk of bias.

CONCLUSIONS

Our review found the diagnostic performance of DL models was similar to that of physicians, although the majority of studies had a high risk of bias. Further pneumothorax AI research is needed.