Objective To analyze the application of intelligent speech follow-up system in secondary prevention of ischemic stroke (IS).

Methods A total of 842 IS patients who received intravenous thrombolysis were randomly divided into intelligent group and artificial group. In the artificial group, corresponding intelligent follow-up templates were developed for the main risk factors affecting the occurrence of IS. The intelligent follow-up system determined the follow-up time and period according to the reserved information of patients when they were discharged, automatically called out the patients' home conditions for follow-up, and converted the response contents into text mode for output. The artificial group was followed up by professionally trained nursing staff, and the follow-up content was the same as that of the intelligent group. Call out, hypertension, diabetes, medication, exercise, average call time and satisfaction of follow-up in the two groups were collected.

Results The telephone connection rates showed no statistical significances between two groups (P>0.05). During the follow-up calls, the correct recognition rate of follow-up contents in the intelligent group was lower, and therateof unwillingness to cooperate and call interruption rate were higher than those in the control group (P < 0.05). There were no statistically significant differences in the percentages of automatic message leaving, inconvenient answering, resident death, family members unable to answer and number error between the two groups (P>0.05), and there was no statistical significance in the distribution of disconnected calls between the two groups (P>0.05). In the effective follow-up calls, there was no statistical significance in the answers to questions related to hypertension and diabetes, compliance and exercise between the two groups (P>0.05). The average call duration in the intelligent group was significantly shorter, and follow-up satisfaction was lower than that in the control group (P < 0.05).

Conclusion Intelligent voice follow-up system can replace manual telephone follow-up to a certain extent, and help medical staff understand the compliance of home blood pressure, blood sugar, medication, exercise and secondary prevention in IS patients, and can save follow-up time and improve follow-up efficiency compared with manual follow-up, but its language recognition and improvement of cooperation rate still need to be optimized.