Key Experimental Factors of Machine Learning-Based Identification of Surgery Cancellations

Table 1

Predictors collected in this study.

Category	Number of predictors	Predictor(s)
Patients’ information	4	Name, age, sex, and AT
Admission information	4	NDA, visit number, identification number of patient, and register number
Workup information	7	Drug allergy, names of drugs administered, blood type, WHSB, SN, and ST
Surgery schedule information	7	ONS, OR, surgery date, surgery time, surgeon, NSOD, WSHSB, and purpose of surgery
Administrative issues	10	Operation staff, department, ward, BD, last updated time, staff who last updated the information, WSDLH, WMSD, WC, and surgery expenditure
Surgery process records	23	Actual date/time when surgery began/ended, actual date/time when patient left OR, actual date when anesthesia was started, actual time when anesthesia was ended, actual date/time when predictive medicine was administered, body temperature, blood transfusion in surgery, autologous blood, allogeneic blood, plasma, thrombocyte, pathological examination, state of consciousness, general skin conditions, special skin conditions, drainage situation, surgery item delivery, anesthesia degree, and surgical incision category

AT: anesthesia type. BD: bed number. NDA: number of days admitted. NSOD: number of surgeries in the OR on the day. ONS: order number of surgery. OR: operating room. SN: surgery name. ST: surgery type. WC: whether surgery is cancelled. WHSB: whether there has been a surgery before. WMSD: whether it is the main surgery day. WSDLH: whether the surgery day is a legal holiday. WSHSB: whether the surgeon has surgery before.