Abstract 1858P
Background
With the aim of reducing the workload of cancer oncologists for personalized precision medicine, and it’s important to incorporate different treatments for lung cancer patients. in this study, we focus on developing an efficiency clinical decision platform for management and diagnosis of the disease to support clinical decision making.
Methods
The scope of this project covers the multi-disciplinary management of lung cancer patients in the hospital. The project includes members from multiple disciplines, including: surgeons, medical oncologists, radio-oncologist, dietitians, and Pharmacologists. First, conducted multiple observations and interviews with members of different specialties to understand the efforts. Second, mapped the MDT meeting workflow and data flow to establish a common view of the pain points and data requirements. Third, analyzed the current status of the information systems used in the abovementioned MDT meeting. Fourth, based on the analysis, we then developed and implemented a plan to drive the integration of different systems.
Results
Through process optimization, and data integration, the total number of steps was reduced to 31 (Table). It not only provides clinicians with more complete patient data, but also enhances the efficiency of multi-disciplinary team discussions and meetings. Table: 1858P
The process optimization results (Unit: Step)
| Pre- Integrated platform | Integrated platform | |
| Request Patient | 4 | 2 |
| Collect Data | 35 | 12 |
| Prep Tumor Board | 11 | 3 |
| Conduct TB | 17 | 8 |
| Take Note | 11 | 4 |
| Follow up | 5 | 2 |
| Whole Steps | 83 | 31 |
| Total Eliminate Steps | N/A | 52 |
| Total Improvement % | N/A | 63% |
Conclusions
We achieved efficiency improvement with the significant number-63%. It not only saves the man hour time, but also a key step drives us toward to the trend of personalized cancer diagnosis and treatment. it will help the medical team to obtain relevant information more effectively and extend the application areas of decision-making data in the hospital which become a foundation of data research and intelligent precision medical decision-making.
Clinical trial identification
Editorial acknowledgement
Legal entity responsible for the study
Changhua Christian Hospital.
Funding
Has not received any funding.
Disclosure
All authors have declared no conflicts of interest.