Artificial Intelligence in Children's Clinic

NCT04186104 | Completed DMC

• 1 other identifier: SCMCIRB-K2019020-2
• Study Type: interventional
• Target: 626
• Locations: 1 country
• Sites: 2

Brief Summary

In China, the number of children's medical services is still far behind the growing demand for children's health care. The phenomenon of children's parents queuing overnight for registration is no longer surprising. This is because of the increase in the number of children and the shortage of pediatric talents. In the department of pediatrics, the number of patients increases year by year, but pediatrician is short of supply from beginning to end. In addition to outpatient service, pediatricians in large hospitals also perform operations, scientific research and other tasks. As a result, many doctors have to give up their vacations, which makes them miserable and reduces their enthusiasm for work. The long queuing time also reduced the satisfaction of patients, resulting in the intensification of the conflict between pediatric doctors and patients. This research project aims to create a human-computer integrated system and develop a new diagnosis process embedded with artificial intelligence (AI). The function of AI system mainly includes 3 aspects. (1) The patient uses a mobile phone application embedded with AI that allows him to have check-up before see a doctor. The program will ask the patient a number of questions. Then, based on the patient's answers, AI will recommend a series of examination, all of which would be reviewed by the physician beforehand. After the patient pays for it, he could go straight to do the examination. So, next he could go to the doctor with the examination report which saves the patient the trouble of queuing. (2) At the same time, the AI system could also automate the medical history. The patient would complete self-help history collection in the spare time. The AI system collects the medical history and automatically import it to the doctor's computer. Doctors' main job is to modify the medical history generated by AI. To some extent, it lightens the burden of doctors. (3) During the visit, the AI system automatically captures the information in the patient's electronic medical record and generates the possible diagnosis. This process is of great help to junior doctors, and may serve as a cue. In short, this study is helpful to effectively reduce the waiting time of patients and greatly increase their medical experience. While reducing the work intensity of doctors, the outpatient procedure of our hospital has been effectively optimized to alleviate the shortage of pediatricians to some extent.

Conditions

Artificial Intelligence; Outpatient

Keywords

Artificial Intelligence; Outpatient; process improvement

Outcome Measures

Primary Outcomes (1)

• Evaluate the efficiency of the two processes

  Compare the average waiting time for single patient and average visiting time for single patient.

  up to 1 months

Secondary Outcomes (3)

• Evaluate patients' rate of satisfaction for medical processes

  up to 1 months

• Economic measurements

  up to 1 months

• Work efficiency of doctors

  up to 1 months

Study Arms (2)

Patients with routine outpatient service process

EXPERIMENTAL

After registration, the patient waits in line at the door of the doctor's office. His doctor uses traditional methods to enter medical records by hand and make diagnosis independently. Then the patient waits in line to pay the bill and queues up for examination. Finally, the patient would take the examination report back to the doctor.

Other: Routine diagnostic process

Patients with AI assisted outpatient service process

EXPERIMENTAL

After registration, the patient binds his information to the mobile phone application through outpatient' number. First, AI system would ask the patient a series of questions. Then it would make a judgment based on the patient's response. The system transmits the examination items to the doctor's computer and, with the doctor's approval, sends items back to the patient. So, patient could go straight to do the examination. While waiting for his turn, the patient enters the phone program again, and the AI system collects his medical history. The information is sent back to the doctor. When the patient goes to the doctor's office with the examination report, the doctor's computer already has his medical records. The doctor only needs to adjust the history according to the actual situation. After writing the medical history, the AI system could automatically make the diagnosis. Doctor uses the AI' results and his own judgment to make a comprehensive diagnosis.

Other: Artificial intelligence assisted diagnosis process

Interventions

Routine diagnostic process OTHER

Patients follow the procedures of registration, waiting, attendance, waiting, examination, waiting, attendance.

Patients with routine outpatient service process

Artificial intelligence assisted diagnosis process OTHER

Patients follow the procedures of registration, AI recommended examination items, Self-service medical history collection ,examination, waiting, AI-assisted attendance.

Patients with AI assisted outpatient service process

Eligibility Criteria

• Age: 2 Months - 18 Years
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Child (0-17), Adult (18-64)

You may qualify if:

• Patients aged 2 months to 18 years old and will go to Shanghai children's medical center for treatment.

You may not qualify if:

• People who don't agree to participate.
• People who can't cooperate.
• People who are difficult to follow up.

Sponsors & Collaborators

• Shanghai Jiao Tong University School of Medicine: lead

Study Sites (2)

Shanghai Children's Medical Center, Shanghai Jiao Tong University School of Medicine

Shanghai, Shanghai Municipality, 200127, China

Location

Shanghai Children's Medical Center

Shanghai, China

Location

Related Publications (16)

• Keel S, Lee PY, Scheetz J, Li Z, Kotowicz MA, MacIsaac RJ, He M. Feasibility and patient acceptability of a novel artificial intelligence-based screening model for diabetic retinopathy at endocrinology outpatient services: a pilot study. Sci Rep. 2018 Mar 12;8(1):4330. doi: 10.1038/s41598-018-22612-2.

  PMID: 29531299 BACKGROUND

• Shen TL, Fu XL. [Application and prospect of artificial intelligence in cancer diagnosis and treatment]. Zhonghua Zhong Liu Za Zhi. 2018 Dec 23;40(12):881-884. doi: 10.3760/cma.j.issn.0253-3766.2018.12.001. Chinese.

  PMID: 30605975 BACKGROUND

• Kantarjian H, Yu PP. Artificial Intelligence, Big Data, and Cancer. JAMA Oncol. 2015 Aug;1(5):573-4. doi: 10.1001/jamaoncol.2015.1203. No abstract available.

  PMID: 26181906 BACKGROUND

• Hamet P, Tremblay J. Artificial intelligence in medicine. Metabolism. 2017 Apr;69S:S36-S40. doi: 10.1016/j.metabol.2017.01.011. Epub 2017 Jan 11.

  PMID: 28126242 BACKGROUND

• Szolovits P, Patil RS, Schwartz WB. Artificial intelligence in medical diagnosis. Ann Intern Med. 1988 Jan;108(1):80-7. doi: 10.7326/0003-4819-108-1-80.

  PMID: 3276267 BACKGROUND

• Kreps GL, Neuhauser L. Artificial intelligence and immediacy: designing health communication to personally engage consumers and providers. Patient Educ Couns. 2013 Aug;92(2):205-10. doi: 10.1016/j.pec.2013.04.014. Epub 2013 May 15.

  PMID: 23683341 BACKGROUND

• Das N, Topalovic M, Janssens W. Artificial intelligence in diagnosis of obstructive lung disease: current status and future potential. Curr Opin Pulm Med. 2018 Mar;24(2):117-123. doi: 10.1097/MCP.0000000000000459.

  PMID: 29251699 BACKGROUND

• Kapoor R, Walters SP, Al-Aswad LA. The current state of artificial intelligence in ophthalmology. Surv Ophthalmol. 2019 Mar-Apr;64(2):233-240. doi: 10.1016/j.survophthal.2018.09.002. Epub 2018 Sep 22.

  PMID: 30248307 BACKGROUND

• Goldhahn J, Rampton V, Spinas GA. Could artificial intelligence make doctors obsolete? BMJ. 2018 Nov 7;363:k4563. doi: 10.1136/bmj.k4563. No abstract available.

  PMID: 30404897 BACKGROUND

• Dilsizian SE, Siegel EL. Artificial intelligence in medicine and cardiac imaging: harnessing big data and advanced computing to provide personalized medical diagnosis and treatment. Curr Cardiol Rep. 2014 Jan;16(1):441. doi: 10.1007/s11886-013-0441-8.

  PMID: 24338557 BACKGROUND

• Singh G, Al'Aref SJ, Van Assen M, Kim TS, van Rosendael A, Kolli KK, Dwivedi A, Maliakal G, Pandey M, Wang J, Do V, Gummalla M, De Cecco CN, Min JK. Machine learning in cardiac CT: Basic concepts and contemporary data. J Cardiovasc Comput Tomogr. 2018 May-Jun;12(3):192-201. doi: 10.1016/j.jcct.2018.04.010. Epub 2018 Apr 30.

  PMID: 29754806 BACKGROUND

• Huang Q, Zhang F, Li X. Machine Learning in Ultrasound Computer-Aided Diagnostic Systems: A Survey. Biomed Res Int. 2018 Mar 4;2018:5137904. doi: 10.1155/2018/5137904. eCollection 2018.

  PMID: 29687000 BACKGROUND

• Huang S, Yang J, Fong S, Zhao Q. Artificial intelligence in cancer diagnosis and prognosis: Opportunities and challenges. Cancer Lett. 2020 Feb 28;471:61-71. doi: 10.1016/j.canlet.2019.12.007. Epub 2019 Dec 10.

  PMID: 31830558 BACKGROUND

• Wall J, Krummel T. The digital surgeon: How big data, automation, and artificial intelligence will change surgical practice. J Pediatr Surg. 2020 Jan;55S:47-50. doi: 10.1016/j.jpedsurg.2019.09.008. Epub 2019 Nov 16.

  PMID: 31767194 BACKGROUND

• Adamson AS, Welch HG. Machine Learning and the Cancer-Diagnosis Problem - No Gold Standard. N Engl J Med. 2019 Dec 12;381(24):2285-2287. doi: 10.1056/NEJMp1907407. No abstract available.

  PMID: 31826337 BACKGROUND

• Wulsin DF, Gupta JR, Mani R, Blanco JA, Litt B. Modeling electroencephalography waveforms with semi-supervised deep belief nets: fast classification and anomaly measurement. J Neural Eng. 2011 Jun;8(3):036015. doi: 10.1088/1741-2560/8/3/036015. Epub 2011 Apr 28.

  PMID: 21525569 BACKGROUND

Study Officials

• Shijian Liu, Ph.D

  Shanghai Children's Medical Center

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: NONE
• Purpose: HEALTH SERVICES RESEARCH
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: staff of Research Department

Study Record Dates

• First Submitted: November 12, 2019
• First Posted: December 4, 2019
• Study Start: March 21, 2020
• Primary Completion: June 29, 2021
• Study Completion: June 29, 2021
• Last Updated: July 1, 2021

Record last verified: 2021-06

Data Sharing

• IPD Sharing: Will not share

Locations

CN (2)