This retrospective study was conducted to determine whether increased length of hospital stay (LOS) and mortality are associated with nutritional risk upon hospital admission in gastrointestinal cancer patients, using a computerized screening tool developed by a university hospital. We included adult gastrointestinal cancer patients whose hospital stays ranged from 24 hours to 90 days. The sample included 4,345 patients. The average age of the patients was 60.5 ± 11.4 years and 2,959 (68.1%) were males. The mean of LOS was 8.2 ± 8.2 days and the mortality rate was 3.4% (n = 146). The majority of the patients were at low risk (LG) (n = 3,102 [71.4%]), while 779 patients (17.9%) were at moderate risk (MG), and 464 (10.7%) were at high risk (HG). In comparing the three groups based on nutritional risk, hospital LOS was significantly longer in the HG (11.4 ± 11.4 days) than it was in the LG (7.7 ± 7.9 days) and the MG (7.9 ± 7.9 days) (p < 0.0001). Significant differences were found in the hospital mortality rate, which was the highest in the HG (13.6%) and the lowest in the LG (1.5%) (p < 0.0001). In the multiple logistic regression analysis, moderate-to-severe nutritional risk, increased age, and emergency admission were selected as significant variables for increased LOS and mortality. Further research is needed to evaluate the benefits of nutritional screening and intervention and their effect on outcomes in various disease populations.