Artificial intelligence (AI) is rapidly changing the field of medicine, and prostate cancer is no exception. The significant heterogeneity that characterizes the natural history of prostate cancer often leads to under- or overtreatment. Moreover, the already substantial burden of prostate cancer care on the health care system is predicted to rise significantly. By discerning patterns within immense, complex datasets, AI has the potential to augment the diagnosis, risk stratification, and treatment of prostate cancer beyond what is possible with existing clinical tools. In recent years, AI algorithms have achieved impressive diagnostic accuracy in the realms of imaging and histopathology interpretation, and AI-based biomarkers for risk stratification have been incorporated into major clinical guidelines. Early strides have also been made in radiation treatment planning, intraoperative surgical assistance and surgical education, and quality control. Moving forward, the prospective validation of novel AI algorithms across large, multi-institutional datasets is needed to minimize bias and ensure validity. Furthermore, it is the responsibility of providers across the continuum of prostate cancer care to ensure the safe and ethical integration of AI into clinical practice. This review summarizes the current state of AI applications in the diagnosis, risk stratification, and treatment of prostate cancer, highlighting recent advances and emerging opportunities in this ever-changing field.
Circulating tumor DNA (ctDNA) is emerging as a clinically meaningful biomarker across multiple solid tumors, including breast cancer. Advances in personalized, tumor-informed whole-genome sequencing have enabled highly sensitive detection of ctDNA, allowing for more precise assessment of tumor burden. Across treatment settings, ctDNA testing has demonstrated consistent prognostic value in patients with breast cancer. In the neoadjuvant setting, ctDNA status is strongly prognostic at baseline and following completion of therapy. After definitive surgery, detection of molecular residual disease (MRD) by ctDNA testing is associated with a marked increased risk of recurrence, with positive predictive values approaching 100% and a lead time of approximately 13.5 months over conventional approaches. These data support the potential role of ctDNA testing as an adjunct to current surveillance strategies, with the aim of identifying recurrence before the onset of significant clinical symptoms. Although ctDNA results are not yet used to guide treatment modification outside of established standards of care, the field is advancing rapidly. Multiple ongoing prospective, interventional trials are evaluating MRDguided therapeutic strategies, and emerging evidence suggests that ctDNA may ultimately help individualize adjuvant therapy-either by identifying patients who may safely de-escalate treatment or by signaling when escalation could be beneficial. In the metastatic setting, ctDNA testing can complement radiographic assessment by providing an additional measure of treatment response, particularly in patients with nonmeasurable or difficult-to-visualize disease. Across all settings, ctDNA testing is most informative when performed longitudinally, enabling assessment of dynamic changes over time. Although baseline ctDNA testing provides valuable prognostic information, its absence at this time point or at diagnosis does not limit the utility of ctDNA assessment at subsequent time points.
Poly(ADP-ribose) polymerase (PARP) inhibitors have emerged as an important therapeutic option for patients with homologous recombination repair (HRR)-deficient cancers, especially those with BRCA1/2 mutations. Since the initial US Food Administration approval of olaparib in 2014, PARP inhibitors have shown efficacy across ovarian, breast, and prostate cancers, although differences in trial design and biomarker strategies have resulted in tumor-specific indications. Homologous recombination deficiency (HRD) arises from germline or somatic mutations in HRR genes or from epigenetic inactivation, and it can be assessed through genomic "scars" such as loss of heterozygosity and mutational signatures. Although BRCA1/2 alterations confer the strongest sensitivity to PARP inhibitors, non-BRCA HRR gene mutations demonstrate heterogeneous responses, highlighting the need for more precise HRD assessment, including the role of biallelic vs monoallelic inactivation. Despite initial success, both primary and acquired resistance-through reversion mutations, replication fork stabilization, and therapy-induced clonal hematopoiesis-limit the durability of the response to PARP inhibition. Ongoing studies are evaluating rational combinations targeting complementary DNA damage response pathways (ATR/CHK1/WEE1, PI3K/AKT) and integrating immunotherapy or hormonal agents to extend benefit. Moving forward, harmonizing HRD testing across tumor types, accounting for germline, somatic, and liquid biopsy-derived alterations, and refining patient selection will be essential to maximize therapeutic efficacy and safely expand PARP inhibitor use beyond canonical BRCA-mutated cancers.
Hemophagocytic lymphohistiocytosis (HLH), both primary/familial HLH and secondary HLH, is associated with multiorgan dysfunction caused by excessive immune activation and cytokine release. The high morbidity and mortality rates are in part due to diagnostic challenges leading to a delay in treatment initiation. The diagnosis, which uses the Histiocyte Society clinical criteria from 2004 and the HScore, remains challenging, with limited improvement in outcomes. No grading system is available for HLH. Although etoposide with dexamethasone remains the most frequently used first-line regimen, various new therapies are now being employed in the management of HLH. The interferon gamma inhibitor emapalumab, the Janus kinase signal transducer and activator of transcription pathway inhibitor ruxolitinib, and the interleukin 6 (IL-6) inhibitor tocilizumab have been trialed in HLH management, with additional treatment options being inhibition of IL-18 and tumor necrosis factor alpha. Here, we summarize current management options for HLH; we also propose a new grading system for HLH based on Common Terminology Criteria for Adverse Events version 5.0 as well as on known prognostic factors (eg, abnormal bilirubin and transaminase levels, elevated creatinine level, respiratory failure, neutropenia, hypertriglyceridemia, hypoalbuminemia, and coagulopathy), which could standardize the diagnosis and guide prompt and appropriate management.
Despite major advances in management strategies, metastatic colorectal cancer remains an important clinical challenge because most patients experience progression after standard first- and secondline treatments. In the setting of refractory disease, defined as disease that progresses after 2 or more lines of treatment, the therapeutic landscape is growing. Options include regorafenib, trifluridine plus tipiracil (FTD/TPI) with or without bevacizumab, and fruquintinib, all of which received approval from the US Food and Drug Administration after showing modest survival benefits in phase 3 trials. However, optimal sequencing remains undefined owing to the absence of direct comparative studies. Real-world data suggest that sequencing regorafenib before FTD/TPI may improve outcomes, with the addition of bevacizumab to FTD/TPI offering further survival benefit. Fruquintinib has also shown efficacy after the use of regorafenib and/or FTD/TPI. Therefore, treatment decisions are based on a case-by-case scenario, with factors such as comorbidities, preferred route of administration, and tolerability taken into consideration. Additionally, improved patient stratification with biomarker testing has become essential for guiding personalized treatment selection. This review highlights the current evidence and gaps in sequencing strategies for the treatment of refractory metastatic colorectal cancer, highlighting the need for future research to inform personalized, effective, and sustainable treatment pathways.
