Is Risk-Stratifying Patients with Colorectal Cancer Using a Deep Learning-Based Prognostic Biomarker Cost-Effective?

OBJECTIVES

Accurate risk stratification of patients with stage II and III colorectal cancer (CRC) prior to treatment selection enables limited health resources to be efficiently allocated to patients who are likely to benefit from adjuvant chemotherapy. We aimed to investigate the cost-effectiveness of a recently developed deep learning-based prognostic method, Histotyping, from the perspective of the Norwegian healthcare system.

METHODS

Two partitioned survival models were developed to assess the cost-effectiveness of Histotyping for two treatment cohorts: patients with CRC stage II and III. For each of the two cohorts, Histotyping was used for risk stratification to assign adjuvant chemotherapy and was compared with the standard of care (SOC) (adjuvant chemotherapy to all patients). Health outcomes measured in the model were quality-adjusted life years (QALYs) and life years (LYs) gained. Deterministic and probabilistic sensitivity analyses were performed to determine the impact of uncertainty. Scenario analyses were performed to assess the impact of the parameters with the greatest uncertainty.

RESULTS

Risk-stratifying patients with CRC stage II and III using Histotyping was dominant (less costly and more effective) compared to SOC. In patients with CRC stage II, the net monetary benefit of Histotyping was 270,934 Norwegian kroners (NOK) (year of valuation is 2021), and the net health benefit of Histotyping was 0.99. In stage III, the net monetary benefit of Histotyping was 195,419 NOK, and the net health benefit of Histotyping was 0.71.

CONCLUSIONS

 Risk-stratifying patients with CRC using Histotyping prior to the administration of adjuvant chemotherapy is likely to be a cost-effective strategy in Norway.

Decompression sickness from saturation diving: a case control study of some diving exposure characteristics

A comprehensive computerized database of diving activity for a Norwegian offshore diving contractor [Stolt-Nielsen Seaway (SNS)] covering the years 1983-1990 has been established. The database contains detailed dive information about 12,087 surface-oriented and 2,622 saturation dives. During this period a majority of the divers were permanently employed. Preliminary analysis had suggested that decompression sickness (DCS) might be the result of exposure to factors causing pathophysiologic effects which accumulate over the course of a single dive or a series of dives. This concept evolved into the HADES (Highest Accumulated Decompression Score) theory which assumes that DCS is predictable once the underlying exposure factors are understood. The incidence of DCS among the SNS divers from saturation diving in the North Sea was studied by use of a "nested" case-control design. Twenty-one case dives (i.e., dives where DCS occurred) were compared with 41 randomly selected control dives. For these dives, several saturation dive characteristics were established. The relative pressure change between maximum and minimum storage depths was significantly greater among the cases. For each 1% increase in the relative pressure change there was a 5% increase in the probability of a saturation dive resulting in DCS. Significantly more cases than controls performed a saturation dive with more than one storage depth, and the data suggested that there were more and greater ascending and descending changes in storage depth conditions among the affected divers.

[Practical cost analysis of high-cost medicine at the Rikshospital--how do we value the clinical activities?]

How should the costs involved in clinical activities be calculated? The authors argue that interest for this question will increase in the years ahead. Costing requires several choices to be made both regarding principles and practical methodology. The results for high-cost treatments at the National Hospital in Norway (Rikshospitalet) are presented. The various treatments include bone marrow, liver, kidney, kidney-pancreas, heart and heart-lung transplantations, arterio-coronary bypass, valvular and aortic surgery, extra-corporal membrane oxygenation and surgical treatment of epilepsy. Methodological issues are presented and discussed. The costing is performed from an institutional perspective. Increased use of bottom-up, actual cost methodology, combined with the direct allocation of overheadcosts is recommended. This allows the study of interpatient variations in consumption of resources.

Is preliminary binephrectomy necessary in patients with autosomal dominant polycystic kidney disease undergoing renal transplantation?

Patients with end-stage chronic renal failure due to autosomal dominant polycystic kidney disease who underwent renal transplantation with or without preliminary binephrectomy were retrospectively studied to determine the effect of binephrectomy on outcome. Nineteen patients were identified. Thirteen patients had no surgery prior to transplantation and six underwent preliminary binephrectomy. One patient died as a result of the nephrectomy. Twenty-one renal allografts were performed on 18 patients of whom seven have died of sepsis; 10 have functioning grafts and one has returned to dialysis. Patients not undergoing preliminary binephrectomy had a statistically significant (p less than 0.05) increase in mortality and morbidity due to septic complications related to polycystic kidney disease. Indications for bilateral nephrectomy should be reconsidered.