Artificial intelligence for predictive biomarker discovery in immuno-oncology: a systematic review

BACKGROUND

The widespread use of immune checkpoint inhibitors (ICIs) has revolutionised treatment of multiple cancer types. However, selecting patients who may benefit from ICI remains challenging. Artificial intelligence (AI) approaches allow exploitation of high-dimension oncological data in research and development of precision immuno-oncology.

MATERIALS AND METHODS

We conducted a systematic literature review of peer-reviewed original articles studying the ICI efficacy prediction in cancer patients across five data modalities: genomics (including genomics, transcriptomics, and epigenomics), radiomics, digital pathology (pathomics), and real-world and multimodality data.

RESULTS

A total of 90 studies were included in this systematic review, with 80% published in 2021-2022. Among them, 37 studies included genomic, 20 radiomic, 8 pathomic, 20 real-world, and 5 multimodal data. Standard machine learning (ML) methods were used in 72% of studies, deep learning (DL) methods in 22%, and both in 6%. The most frequently studied cancer type was non-small-cell lung cancer (36%), followed by melanoma (16%), while 25% included pan-cancer studies. No prospective study design incorporated AI-based methodologies from the outset; rather, all implemented AI as a post hoc analysis. Novel biomarkers for ICI in radiomics and pathomics were identified using AI approaches, and molecular biomarkers have expanded past genomics into transcriptomics and epigenomics. Finally, complex algorithms and new types of AI-based markers, such as meta-biomarkers, are emerging by integrating multimodal/multi-omics data.

CONCLUSION

AI-based methods have expanded the horizon for biomarker discovery, demonstrating the power of integrating multimodal data from existing datasets to discover new meta-biomarkers. While most of the included studies showed promise for AI-based prediction of benefit from immunotherapy, none provided high-level evidence for immediate practice change. A priori planned prospective trial designs are needed to cover all lifecycle steps of these software biomarkers, from development and validation to integration into clinical practice.

Peripheral arterial occlusive disease: role of MR angiography

PURPOSE

Magnetic resonance angiography (MRA) has recently become instrumental in the diagnosis of arterial disease in various body districts and is gaining an increasingly important role in the study of peripheral vascularisation. The aim of our study was to evaluate the reliability of MRA using digital subtraction angiography (DSA) as the reference standard.

MATERIALS AND METHODS

Between November 2003 and August 2004, 30 patients with known peripheral arterial disease were studied by MRA and DSA. MRA was performed with a Philips Intera 1.5 T, with acquisitions from the coeliac trunk to the feet. For acquisitions of the feet and ankles we used unenhanced time-of-flight (TOF) sequences with a head coil. The angiographic sequence was acquired in three volumes of 40-45 cm after administration of paramagnetic contrast material.

RESULTS

In the patients with peripheral arterial disease, the technique provided a precise evaluation of the stenosis (mild, moderate, severe) or obstruction of the peripheral district as well as the detection of other diseases, such as stenosis of the renal arteries or aneurysms.

CONCLUSIONS

Total-body three-dimensional (3D) MRA allows a fast, safe, and accurate assessment of the arterial system in patients with arteriosclerosis and can be considered an alternative to DSA in the management of patients with steno-obstructive disease of the peripheral arteries.

Primary endoleakage in endovascular treatment of the thoracic aorta: importance of intraoperative transesophageal echocardiography

OBJECTIVES

Endovascular treatment of the thoracic aorta has developed as an efficacious alternative to open surgical repair. However, despite the high primary success rate, perigraft leakage constitutes the major concern in long-term follow-up. Endoleaks are widely reported both in abdominal and thoracic endovascular series and are usually identified by intraoperative angiography. Transesophageal echocardiography is a sensitive imaging technique in the evaluation of aortic diseases, widely used to monitor cardiac surgery. The aim of this study was to evaluate the efficacy of transesophageal echocardiography in leakage detection during endovascular stent procedures of the thoracic aorta.

METHODS

Intraoperative transesophageal echocardiography was used in conjunction with angiography in 25 patients subjected to endovascular stent treatment of the descending thoracic aorta. Spiral computed tomographic scanning was performed before discharge and 3, 6, and 12 months after treatment.

RESULTS

Information from transesophageal echocardiography was relevant in the selection of the landing zone in 62% of cases. In 8 patients, transesophageal echocardiography with color Doppler sonography showed a perigraft leak, 6 of which were not visible on angiography, suggesting the need for further balloon expansion or graft extension. Postoperative computed tomographic scanning in the 25 patients showed 1 endoleak, which sealed spontaneously. At 3 months, computed tomographic examination confirmed the absence of perigraft leakage in all patients.

CONCLUSIONS

During implantation of a stent-graft in the descending thoracic aorta, transesophageal echocardiography provides information in addition to that provided by angiography, improving immediate and late procedural results.