Setting and participants
The research was conducted in a leading maternity and children's hospital in China. The cloud follow-up platform was introduced into the gynecological tumor chemotherapy ward in 2019 and was associated with the hospital information system. We enrolled a total of 2538 patients who had undergone gynecological chemotherapy between January and October 2021; this group of patients was defined as the cloud follow-up group since all patients’ follow-ups were completed by the cloud follow-up system. In addition, 690 patients receiving gynecological chemotherapy between April and September 2020 were included in the manual follow-up group; this group of patients was followed up by nurses over the telephone.
Cloud follow-up group
Establishment of a multidisciplinary treatment (MDT) team for cloud follow-up
A multidisciplinary treatment (MDT) team consisting of eight members was organized, which included one department director, one head nurse, three tumor nurses, one doctor, and two cloud follow-up information technicians. The department director was primarily responsible for constructing and coordinating the cloud follow-up platform. The head nurse was mainly responsible for formulating a cloud follow-up-related management system and implementing project training. Doctors and nurses answered the medical questions of patients or their families online from 14:00 to 16:00 every day. Tumor nurses were responsible for establishing disease publicity and education knowledge base, follow-up form base, follow-up rules, etc. The cloud follow-up information technicians were responsible for providing technical support for the information needs of the follow-up of gynecological chemotherapy patients.
Construction of the cloud follow-up platform
The hospital’s cloud follow-up platform was constructed and implemented by a third-party company, jointly managed by the technicians of the third-party company and the information technicians of the hospital. The cloud follow-up platform was mainly developed in Java language and adopted the Apsara technology platform, integrating elastic computing, data storage, CDN storage, and large-scale computing technology to provide storage resources and computing resources to users on the Internet in the form of public services. The cloud follow-up platform included PC-based doctor-patient collaboration, medical App, patient app, and WeChat official account. Since July 2020, the cloud follow-up platform has expanded the modules and functions related to the follow-up of gynecological chemotherapy patients as shown in Table 1.
Implementation of the cloud follow-up platform
After obtaining the informed consent of the patient or primary caregiver, the patient was instructed to scan the quick response code, follow the hospital's WeChat official account, download the patient app, and fill in the personal information; the patient was taught how to use the App. After the doctor issued the discharge order, the cloud follow-up system automatically added the patient to the follow-up list and collected the patient's basic information, such as age, diagnosis, registration number, cancer stage, and chemotherapy course. Because most of the chemotherapy patients in the intervention department were discharged the day after infusion of chemotherapy drugs, the MDT team set a specific follow-up time (2 days, 1 week, and 2 weeks after discharge) to investigate the occurrence of acute CINV, delayed CINV, and other chemotherapy complications, and the follow-up contents were consulted by experts. The contents of the follow-up form mainly included the investigation of adverse reactions after chemotherapy, such as CINV, constipation, diarrhea, fatigue, and sleep disorders. Each symptom contained hidden subquestions, which popped up automatically only when the patient chose to select the symptom. In addition, the system automatically pushed the corresponding health education materials according to the answers selected by the patient. The forms of health education materials included video, PowerPoint, and health education text. Furthermore, the system reminded patients to seek medical treatment as soon as possible. Subsequently, a report was generated and automatically uploaded to the cloud as shown in Table 2. Medical staff could view the answers filled in by the patients through the medical App and provide feedback to them if necessary.
Textbox 1 Transcription of a sample dialogue.
System: Dear gynecological chemotherapy patients, in order to timely understand your situation at home and provide you with guidance and help, can you spend a few minutes on a follow-up survey?
System: Have you experienced nausea in the past 24 hours?
The system will automatically pop up related sub questions about nausea.
System: Please select the degree of nausea you have experienced in the past 24 hours.
○Loss of appetite, but not accompanied by reduced food intake
○Reduced food intake without significant weight loss and no malnutrition
○Eating decreased significantly and physical weakness
If the patient selects the third case, the system will automatically pop up the red words "please see a doctor as soon as possible"
System: Have you vomited in the past 24 hours?
If the patient selects no, the system will automatically pop up the next question.
System: Have you had constipation in the past week?
System: Have you had diarrhea in the past 24 hours? (feces are thin and more than 3 times / day)
System: Have you felt tired and weak in the past 24 hours?
System: Are you satisfied with the quality of your sleep in the last week?
System: Have you had the following symptoms in the past 24 hours, such as limb swelling, pain, numbness, chest tightness or tightness?
System: Can you correctly carry out finger exercises and ankle pump exercise training to prevent thrombosis?
The system automatically pops up the health education video of finger manipulation and ankle pump movement
After the patient has answered all the questions, click submit.
System: Thank you for your cooperation. We have recorded your problem. Please handle it according to the system prompt, keep the phone unobstructed, and we will follow you up if necessary.
Household graded management
Patients were able to record the adverse reactions of chemotherapy at home through the patient app, and the medical staff viewed the contents filled in by patients in real-time through the medical App and executed household graded management of patients with abnormal data. In the case of CINV, first-level management included patient self-management. According to the Common Terminology Criteria for Adverse Events v4.0 , when the patient's nausea and vomiting symptom was rated as grade 0–2, the medical staff conducted one-to-one online guidance through the cloud follow-up system. In addition, secondary management involved medical specialty outpatient management. When the nausea and vomiting symptom was rated as grade 3–4, the medical staff timely recommended patients to the hospital online and made telephonic confirmation if necessary.
Manual follow-up group
The patients in the control group were investigated by manual follow-up, that is, the nurses called the patients one by one according to the discharge list of patients. The contents of the follow-up form were consistent with those of the cloud follow-up system; however, the uploaded report needed to be filled in manually
The evaluation indexes included follow-up rate, follow-up satisfaction, session duration, and read rate. Following formulae were used: follow-up rate = number of effective follow-ups / (number of effective follow-ups + number of invalid follow-ups) × 100%; follow-up satisfaction = (number of very satisfied + number of satisfied) / number of total actual follow-up cases × 100%; and read rate = number of read times / number of send times × 100%. The number of effective follow-ups was defined as the complete data collection in Table 2 (excluding the number of health education materials pushed parameter). The number of invalid follow-ups was defined as missing or incomplete data in Table 2. Follow-up satisfaction was defined as the patient's satisfaction with the follow-up service, divided into five levels: very satisfied, satisfied, average, dissatisfied, and very dissatisfied. The number of read times was defined as the number of times the patient actively read health education materials. The number of send times was defined as the number of times the cloud follow-up platform automatically pushed health education materials for patients. Session duration was defined as the time required for medical staff to communicate with patients over the telephone.
SPSS statistical software (version 22.0, IBM Inc) was used for data analysis. Age, cancer stage, disease category, and read rate of health education materials were conducted by descriptive analysis. Patient characteristics, follow-up rate, and follow-up satisfaction in both groups were tested by Pearson’s chi-square test. All tests were two-sided. P＜0.05 indicated a statistically significant difference.