Challenges and perspectives in use of artificial intelligence to support treatment recommendations in clinical oncology.

Artificial intelligence (AI) promises to be the next revolutionary step in modern society. Yet, its role in all fields of industry and science need to be determined. One very promising field is represented by AI-based decision-making tools in clinical oncology leading to more comprehensive, personalized therapy approaches. In this review, the authors provide an overview on all relevant technical applications of AI in oncology, which are required to understand the future challenges and realistic perspectives for decision-making tools. In recent years, various applications of AI in medicine have been developed focusing on the analysis of radiological and pathological images. AI applications encompass large amounts of complex data supporting clinical decision-making and reducing errors by objectively quantifying all aspects of the data collected. In clinical oncology, almost all patients receive a treatment recommendation in a multidisciplinary cancer conference at the beginning and during their treatment periods. These highly complex decisions are based on a large amount of information (of the patients and of the various treatment options), which need to be analyzed and correctly classified in a short time. In this review, the authors describe the technical and medical requirements of AI to address these scientific challenges in a multidisciplinary manner. Major challenges in the use of AI in oncology and decision-making tools are data security, data representation, and explainability of AI-based outcome predictions, in particular for decision-making processes in multidisciplinary cancer conferences. Finally, limitations and potential solutions are described and compared for current and future research attempts.

Prevention and Management of Donor-transmitted Cancer After Liver Transplantation: Guidelines From the ILTS-SETH Consensus Conference.

As with any other intervention in health, liver transplantation (LT) entails a variety of risks, including donor-transmitted cancers (DTCs). At present, 2%-4% of used deceased organ donors are known to have a current or past history of malignancy. The frequency of DTCs is consistently reported at 3-6 cases per 10 000 solid organ transplants, with a similar frequency in the LT setting. A majority of DTCs are occult cancers unknown in the donor at the time of transplantation. Most DTCs are diagnosed within 2 y after LT and are associated with a 51% probability of survival at 2 y following diagnosis. The probability of death is greatest for DTCs that have already metastasized at the time of diagnosis. The International Liver Transplantation Society-Sociedad Española de Trasplante Hepático working group on DTC has provided guidance on how to minimize the occurrence of DTCs while avoiding the unnecessary loss of livers for transplantation both in deceased and living donor LT. The group endorses the Council of Europe classification of risk of transmission of cancer from donor to recipient (minimal, low to intermediate, high, and unacceptable), classifies a range of malignancies in the liver donor into these 4 categories, and recommends when to consider LT, mindful of the risk of DTCs, and the clinical condition of patients on the waiting list. We further provide recommendations to professionals who identify DTC events, stressing the need to immediately alert all stakeholders concerned, so a coordinated investigation and management can be initiated; decisions on retransplantation should be made on a case-by-case basis with a multidisciplinary approach.

Prevention of ischemic-type biliary lesions by arterial back-table pressure perfusion.

Ischemic-type biliary lesions (ITBLs) lead to considerable morbidity after orthotopic liver transplantation (OLT). The exact pathogenesis is unknown. We tested the hypothesis that insufficient perfusion of biliary arterial vessels might be responsible for ITBLs. This could be prevented by improved perfusion techniques. Since February 2000, we performed a controlled study using arterial back-table pressure perfusion (AP) to achieve reliable perfusion of the biliary-tract capillary system, which may be impaired by the high viscosity of University of Wisconsin solution. We retrospectively analyzed 190 OLTs performed between September 1997 and July 2002 with regard to ITBLs. One hundred thirty-one grafts were preserved by in situ standard perfusion (SP), including portal perfusion, whereas in 59 cases, additional AP was performed. Donor-related factors, recipient age, indication for OLT, OLT technique, immunosuppression, and ischemia time were similar in both groups. In the SP group, 21 of 131 patients (16%) developed ITBLs. Only 1 of 59 patients with grafts receiving AP developed ITBLs. This difference was highly significant (P =.004). Peak aspartate aminotransferase (AST) and alanine aminotransferase (ALT) levels within the first 3 days were significantly lower in the AP group (AST, P =.016; ALT, P =.007). Multivariate analysis showed a significant influence of AP (P =.010) and donor age (P =.003) on the development of ITBLs. AP is an easy and reliable method to prevent ITBLs in OLT. It therefore should be used as the standard technique in liver procurement.