COVID-19, Influenza, Post-COVID-19 Syndrome
Conditions
Brief summary
This is an open-tabled, one-arm observatory trial to assess the effectiveness and safety of the Autonomous Treatment System Based on Machine Learning in patients with Covid-19, Post-Acute Sequelae of SARS-CoV-2 infection and influenza.
Detailed description
This study has enrolled 27 patients diagnosed with Covid-19, Post-Acute Sequelae of SARS-CoV-2 infection, and influenza. Of these patients, 26 are outpatients, and 1 is hospitalized. After screening based on the inclusion and exclusion criteria, eligible patients will receive prescriptions recommended by the Autonomous Treatment System Based on Machine Learning in this observational trial. The objectives of this study are: 1. To compare the classifications made by our machine learning system with those by physicians to assess the model's reliability and accuracy; 2. To evaluate Covid-19-related hospitalizations or deaths from any cause through day 28; 3. To determine if the machine learning system's recommended prescription alleviates symptoms of Covid-19, Post-Acute Sequelae of SARS-CoV-2 infection, and influenza; 4. To monitor participants who tested positive for the Covid-19 for 28 days after initiating treatment, looking for potential rebound cases. Participants will use an online application to receive the recommended prescription results and will forward these results to a physician for verification. Patients are instructed to complete the online analysis every 3 days or whenever their symptoms change, whichever comes first. They are also asked to adhere to the prescribed medication regimen. Research physicians will conduct follow-ups with patients every 3 days via phone calls. The potential treatments patients may receive include any of the following Traditional Chinese Medicine formulas: LizCovidCure-1, LizCovidCure-2, LizCovidCure-3, LizCovidCure-4, and LizCovid-5.
Interventions
OTHERAutonomous Treatment System for Covid-19, Post-Acute Sequelae of SARS-CoV-2 Infection and Influenza Based on Machine Learning
A novel treatment recommendation system for Covid-19, Post-Acute Sequelae of SARS-CoV-2 Infection and Influenza, which is based on machine learning
Sponsors
Sheng'ai Traditional Chinese Medicine Hospital
Lizora LLC
Study design
Observational model
COHORT
Time perspective
PROSPECTIVE
Eligibility
Sex/Gender
ALL
Age
14 Years to 95 Years
Healthy volunteers
No
Inclusion criteria
* Either male or female (14 years or older), and their COVID-19 vaccination status was not a factor for inclusion. * Subjects with any high-risk conditions * Subjects with positive sars-cov-2 rapid antigen results in 30 days * Subjects with post Covid-19 syndrome
Exclusion criteria
* pregnant individuals * subjects with known histories of allergic reactions to medical herbs commonly used in Traditional Chinese Medicine (TCMs)
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Classification Accuracy | 1 Day | compare the classifications made by our machine learning system with those by physicians, to assess the model's reliability |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Hospitalization Rate and Death | 28 Days | we assess Covid-19-related hospitalization or death from any cause through day 28 |
Other
| Measure | Time frame | Description |
|---|---|---|
| Symptom Alleviation | 28 Days | Days of symptom disappearance |
| Re-infection Cases | 28 days | Number of cases with recurrence-infection after treatment |
Countries
China
Outcome results
None listed