The trial’s elegant 2 × 2 factorial design addressed two independent questions simultaneously. The first randomisation, published in The Lancet, compared the four-drug PAXG regimen — cisplatin, nab-paclitaxel, capecitabine and gemcitabine — against the widely used mFOLFIRINOX combination of fluorouracil, leucovorin, irinotecan and oxaliplatin as preoperative therapy. That analysis showed PAXG produced a longer median event-free survival of 16 months versus 10.2 months, with a hazard ratio of 0.63, establishing the regimen as a new benchmark in this disease. Patients who remained free of progression or limiting toxicity after four months were then offered a second randomisation, the subject of the new analysis: whether the final two months of the same regimen should be given before surgery or reserved as adjuvant treatment after resection.

Between February 2021 and September 2024, 171 patients underwent this second randomisation, with 86 assigned to long-course and 79 to short-course preoperative chemotherapy. After central review excluded six patients found to be ineligible, the intention-to-treat population comprised 165 patients, and the final event-free survival analysis was performed after a median follow-up of 33.4 months, by which time 116 events — 70 percent of the population — had occurred. No patient was lost to follow-up, an unusually clean dataset for a trial of this size and complexity.

The primary result was unambiguous in its neutrality. Event-free survival, the prespecified primary endpoint encompassing progression, recurrence, unresectability, intraoperative metastasis detection and death, was statistically indistinguishable between the arms. The unadjusted hazard ratio comparing long-course with short-course treatment was 0.98, with a 95 percent confidence interval of 0.68 to 1.41 and a P value of 0.90. Median event-free survival was 13.0 months in the long-course group and 15.2 months in the short-course group, while three-year event-free survival rates were 27.1 percent and 23.6 percent respectively. Multivariable Cox regression confirmed the conclusion: chemotherapy duration was not associated with event-free survival after adjustment, whereas the chemotherapy regimen itself remained the only significant factor, with PAXG conferring a hazard ratio of 0.67 compared with mFOLFIRINOX.

Beneath that headline of equivalence, however, the secondary endpoints tell a more nuanced and biologically interesting story. A reduction of 50 percent or more in the tumour marker CA19-9 was achieved significantly more often with prolonged preoperative therapy, in 97 percent of evaluable patients compared with 84 percent in the short-course arm. Four complete pathological responses were observed with long-course treatment and none with short-course treatment, a borderline difference. The rate of lymph-node-negative resections was significantly higher in the long-course group, at 45 percent versus 27 percent, suggesting deeper systemic tumour clearance before the operation. Radiological partial responses were also numerically more frequent with the longer course, at 57 percent versus 47 percent.

Perhaps the most practically important finding concerns chemotherapy delivery itself. In the per-protocol population, 71 percent of patients randomised to complete all chemotherapy before surgery actually received all four planned administrations in the final phase, compared with only 51 percent of those whose last two months were deferred until after resection. Relative dose-density — the proportion of planned drug actually delivered over the final four administrations — was consistently higher across every agent in the long-course arm, with figures such as 85 percent versus 61 percent for cisplatin and 83 percent versus 54 percent for fluorouracil. The differential is almost entirely attributable to poor tolerability during the postoperative recovery period, when dose reductions and discontinuations are common. Because prior evidence has linked dose-density to overall survival in resectable pancreatic cancer, the authors argue that completing systemic therapy before surgery may be the more reliable way to deliver the full therapeutic payload.

The resection picture reinforces the message that longer preoperative therapy does not forfeit the chance of curative surgery, a concern raised by an earlier systematic review suggesting that courses of eight weeks or less yielded higher resection rates. In the CASSANDRA intention-to-treat population, 80 percent of long-course patients and 87 percent of short-course patients underwent resection, a difference that was not statistically significant. Notably, the apparent short-course advantage was concentrated among patients treated with mFOLFIRINOX, where the resection gap reached statistical significance, while the difference was negligible in the PAXG stratum — an observation the investigators interpret as evidence that more effective regimens can sustain disease control over longer preoperative periods. Concerns that prolonged neoadjuvant therapy in resectable disease simply allows tumours to progress beyond the surgeon’s reach were not supported by the data.

The trial is not without limitations, and the investigators are candid about them. The sample size for the second randomisation was constrained by the design, leaving 80 percent power only to detect large effect sizes, so smaller but clinically meaningful differences cannot be excluded. The enrolled population was necessarily selected: only patients who remained progression-free and tolerant after four months of chemotherapy could participate, limiting generalisability to all-comers. The absence of central pathological and radiological review, the inclusion of both resectable and borderline resectable disease, an upper age limit of 75 years, and the use of two different chemotherapy regimens all add interpretive complexity, although the prespecified test for a regimen-by-duration interaction was not significant. Overall survival data are also immature: with only 44 percent of deaths accrued so far, median survival was 50.5 months in the long-course arm versus 35.1 months in the short-course arm, a non-significant difference with three-year survival rates of 56.8 percent and 46.6 percent respectively — figures that, if they hold, would represent a striking improvement over historical benchmarks.

Taken together, the results reframe rather than resolve the question of neoadjuvant duration. The trial’s authors conclude that six months of preoperative chemotherapy achieves results comparable to four months before surgery with two months after, and that the choice to prolong preoperative treatment beyond four months can reasonably be personalised according to clinical circumstances, tumour biology and patient preference. PAXG emerges as the preferred backbone regimen in this setting, and patients who progress during the final two months of preoperative therapy may be spared a major operation unlikely to benefit them. The deeper biochemical, radiological and pathological responses seen with longer treatment hint at improved systemic clearance of micrometastatic disease, even if that has not yet translated into event-free or overall survival gains. What is clear is that the era of assuming a single fixed duration of preoperative therapy for all patients with operable pancreatic cancer is over, and future research must now turn toward more effective drug regimens and better tools for selecting which patients truly benefit from surgery.

Subject of Research: Optimal duration of neoadjuvant chemotherapy before surgery in resectable and borderline resectable pancreatic ductal adenocarcinoma

Article Title: Short-term versus long-course neoadjuvant chemotherapy for resectable and borderline resectable pancreatic ductal adenocarcinoma (PACT-21 CASSANDRA): results from the second randomisation analysis of a randomised, open-label, 2 × 2 factorial phase 3 trial

Article References: Reni, M., Orsi, G., Carconi, C., Malleo, G., Procaccio, L., Macchini, M., Bencardino, K., Merelli, B., Pretta, A., Rapposelli, I. G., Pecorelli, N., Partelli, S., Sperti, E., Crippa, S., Liscia, N., Di Marco, M., Milella, M., Lonardi, S., Palumbo, D., … Falconi, M. (2026). Short-term versus long-course neoadjuvant chemotherapy for resectable and borderline resectable pancreatic ductal adenocarcinoma (PACT-21 CASSANDRA): results from the second randomisation analysis of a randomised, open-label, 2 × 2 factorial phase 3 trial. eClinicalMedicine, 99, Article 104190. https://doi.org/10.1016/j.eclinm.2026.104190

Image Credits: AI Generated

DOI: 10.1016/j.eclinm.2026.104190

Keywords: pancreatic cancer, neoadjuvant chemotherapy, phase 3 trial, PAXG, mFOLFIRINOX, event-free survival, CA19-9, surgical resection, dose-density, PACT-21 CASSANDRA, Short-term, versus