Construction and validation of a risk prediction model for perianal infection in patients with haematological malignancies during chemotherapy: a prospective study in a tertiary hospital in China

ObjectivesPerianal infection is a serious complication in patients undergoing chemotherapy for haematological malignancies. Therefore, we aimed to develop a predictive model to help medical staff promptly screen patients at a high risk of perianal infection during chemotherapy.DesignThis was a single-centre prospective observational study.SettingThis study was conducted in a tertiary teaching hospital in Chengdu, China.ParticipantsThe study sample comprised 850 patients with haematological malignancies who underwent chemotherapy at the department of haematology or our hospital between January 2021 and June 2022.InterventionsThe included patients were randomly divided into training and validation groups in a 7:3 ratio. Based on the discharge diagnosis, patients with perianal infection were selected as the case group and the other patients were selected as the control group.Outcome measureThe main outcome measure was the occurrence of perianal infections.ResultsA predictive model for perianal infections was established. A history of perianal infection, haemorrhoids, constipation and duration of diarrhoea were independent risk factors. The area under the curve of the The area under the receiver operating characteristic (ROC) curve for the training and validation groups were 0.784 (95% CI 0.727 to 0.841) and 0.789 (95% CI 0.818 to 0.885), respectively. Additionally, the model had good calibration in both the training and validation groups with a non-significant Hosmer-Lemeshow test (p=0.999 and 0.482, respectively).ConclusionsThe risk prediction model, including a history of perianal infection, history of haemorrhoids, constipation and duration of diarrhoea ≥3 days of perianal infection in patients with haematological malignancies during chemotherapy, has good prediction reliability and can be helpful in guiding clinical medical staff in screening and early intervention of high-risk groups.