SMART-AI vs Usual Care: All-cause Re-hospitalizations Following 6-months From the Index Hospital Encounter
Calculated by ConductScience from the counts the trial posted to ClinicalTrials.gov.
Measures 6
Calculated by ConductScience from the counts the trial posted to ClinicalTrials.gov.
| Measure | Value | 95% interval, lower | 95% interval, upper | Method | Note | Source |
|---|---|---|---|---|---|---|
| Risk in group 1 | 0.305 | 0.3 | 0.31 | wilson | ClinicalTrials.gov | |
| Risk in group 2 | 0.305 | 0.3 | 0.31 | wilson | ClinicalTrials.gov | |
| Risk difference, group 1 minus group 2 | 0.000206 | -0.00688 | 0.00729 | newcombe hybrid score | ClinicalTrials.gov | |
| Risk ratio, group 1 over group 2 | 1 | 0.978 | 1.02 | log | ClinicalTrials.gov | |
| Odds ratio, group 1 over group 2 | 1 | 0.968 | 1.03 | log | ClinicalTrials.gov | |
| Number needed to treat, for one more participant with the outcome on SMART-AI than on Usual Care | 4,850 | from the risk difference interval | the interval includes no difference | ClinicalTrials.gov |
Groups 2
Group 2 names the comparator: usual care.
| Group | Title | Description | With the outcome | Analysed | ClinicalTrials.gov code | Source |
|---|---|---|---|---|---|---|
| Group 1 | SMART-AI | Automated processing of clinical notes collected during routine care in first 24 hours of hospital admission to identify individuals at-risk for substance misuse to receive standard-of-care full screening and assessment, brief intervention, or referral to treatment (SBIRT) intervention.~Processing of clinical notes in the EHR data collected during routine care: Clinical notes collected in the first day of hospital admission during usual care as input to natural language processing and machine learning algorithm. | 10,241 | 33,564 | OG001 | ClinicalTrials.gov |
| Group 2 | Usual Care | Before intervention | 9,584 | 31,432 | OG000 | ClinicalTrials.gov |
Outcome 5
| Field | Value | Source |
|---|---|---|
| Type | SECONDARY | ClinicalTrials.gov |
| Title | All-cause Re-hospitalizations Following 6-months From the Index Hospital Encounter | ClinicalTrials.gov |
| Description | We will compare healthcare utilization outcomes in all patients between pre- and post-periods controlling for all patient demographic and clinical characteristics. | ClinicalTrials.gov |
| Time frame | 12 months enrollment with 6 months follow-up for rehospitalization | ClinicalTrials.gov |
| Population | ClinicalTrials.gov |
Trial 8
| Field | Value | Source |
|---|---|---|
| Title | Data-driven Identification for Substance Misuse | ClinicalTrials.gov |
| NCT number | NCT03833804 | ClinicalTrials.gov |
| Phases | NA | ClinicalTrials.gov |
| Conditions | Substance Use, Substance Abuse, Substance-Related Disorders | ClinicalTrials.gov |
| Interventions | Processing of clinical notes in the EHR data collected during routine care | ClinicalTrials.gov |
| Lead sponsor | University of Wisconsin, Madison | ClinicalTrials.gov |
| Results first posted | 2025-10-24 | ClinicalTrials.gov |
| Results on ClinicalTrials.gov | https://clinicaltrials.gov/study/NCT03833804?tab=results | ClinicalTrials.gov |
Source 4
| Field | Value | Source |
|---|---|---|
| Release | trial-comparisons-2026-03-23-0.1.0 | ClinicalTrials.gov |
| Release manifest SHA-256 | f66225897fbf258b57ea10bdacfd0347d3cdfda93f7f5685234b7e06ea36fa57 | ClinicalTrials.gov |
| AACT copy | 2026-03-23 | ClinicalTrials.gov |
| Tables read | outcome_counts.parquet, outcome_measurements.parquet, outcomes.parquet, reported_event_totals.parquet, reported_events.parquet, result_groups.parquet, studies.parquet, ctgov_trial.parquet | ClinicalTrials.gov |
Release trial-comparisons-2026-03-23-0.1.0
ClinicalTrials.gov's posted results, through CTTI's AACT: ClinicalTrials.gov data via Aggregate Analysis of ClinicalTrials.gov (AACT), CTTI. CTTI makes its materials freely available and requests acknowledgement. https://aact.ctti-clinicaltrials.org/documentation/299 ClinicalTrials.gov's data carry an international copyright outside the United States: https://clinicaltrials.gov/about-site/terms-conditions. The measures are ConductScience's calculation from them.
ClinicalTrials.gov: none stated ClinicalTrials.gov's data carry an international copyright outside the United States: https://clinicaltrials.gov/about-site/terms-conditions. The measures are ConductScience's calculation from them.