Investigator SmartSelect Glossary

Investigator SmartSelect is an AI-enabled investigator and site selection solution designed to optimize study planning for your protocol. Investigators are recommended based on a comprehensive set of criteria, including historical performance, therapeutic experience, patient availability, and site capacity. Each recommended investigator list is carefully curated using a robust combination of Citeline data, real-world data (RWD), and proprietary performance data, ensuring that high-performing investigators are matched to the user-specified protocol and target countries.

In parallel, a dedicated AI model recommends optimal countries based on historically successful indicators such as past performance, investigator availability, enrollment rates, and study start-up timelines. The countries identified by this model are then used to generate a second, refined list of investigators who are best positioned to meet the protocol requirements within those geographies.

For transparency and flexibility, the platform also displays investigators that the sponsor has previously worked with. This allows users to build a customized investigator or site list by selecting from both sponsor-historical investigators/sites and AI-recommended options. Based on the selected investigators, sites, and countries, the platform provides AI-driven forecasts for enrollment rates and study duration, tailored specifically to the user’s final selection.

The Forecasted Enrollment Rates section presents the predicted performance for the study criteria, broken down by country. This section contains three tables, each offering a different analysis based on the user selected countries, selected investigator’s countries and the model-recommended countries.

All values in this table reflect the user’s selections in the input form, illustrating how the selected countries are expected to perform and the resulting overall study forecast based on the investigators recommended within those countries

This metric represents the model-predicted, country-specific enrollment rate based on the countries selected by the user in the input form. It reflects the weighted average enrollment rate across all selected countries, accounting for country allocation and the number of investigators required to complete the study, as determined by the model. Additional details on how this metric is predicted and how it differs from the Enrollment Rate Based On Completed Trials

(Pt/Site/Month) are available in the in-app information drawer.

This is the median monthly rate at which patients were enrolled in similar trials conducted in the selected countries over the past five years. The calculation is based on Actual Accrual data (or Target Accrual when Actual Accrual is unavailable), the number of reported sites, and the actual enrollment duration.

Additional details on how this metric is calculated and how it differs from the Forecasted Enrollment Rate are available in the in-app information drawer.

This is a model-predicted estimate of the trial's enrollment duration, calculated using the Forecasted Enrollment Rate, the number of investigators, and the number of patients specified in the study criteria.

The total number of countries selected by the user in the input form.

The target number of investigators required for the study, based on the selections made by the user in the input form.

A list of the countries selected by the user in the input form.

This metric represents the forecasted enrollment rate for each country within the selected indication, as predicted by the AI model. It provides insight into each country’s ability to enroll patients and its expected enrollment performance. The value varies depending on whether the forecast is based on a single-country trial or a multi-country trial, which is indicated in the column header.

This refers to the model's recommended allocation of investigators in the selected country. The allocation is determined by the availability of investigators who meet the study criteria requirements. The model allocates investigators to maximize the overall study forecasted enrollment rate. When countries are specified in the study criteria, the model will allocate at least one investigator per country as long as it can find a recommendable investigator for the country.

This represents the approximate distribution of investigators based on the total number of investigators required for the study, as defined in the input form, and the model-recommended allocation by country. The intent is to guide and simplify the selection of investigators from the recommended list.

All values in this table are based on the sites and/or investigators selected by the user from the recommendations. These values are dynamic and update in real time to reflect changes to the selected investigators, investigator sites, countries, and allocations.

This represents the country-specific enrollment rate predicted by the model, based on the selected investigator's countries. It reflects the relative average enrollment rate across all selected investigator's countries, as defined by the model. Additional details on how this metric is predicted and how it differs from the Enrollment Rate Based On Completed Trials (Pt/Site/Month) are available in the in-app information drawer.

This is the median monthly rate at which patients were enrolled in similar trials conducted in the selected investigator's countries over the past five years. The calculation is based on Actual Accrual data (or Target Accrual when Actual Accrual is unavailable), the number of reported sites, and the actual enrollment duration. Additional details on how this metric is calculated and how it differs from the Forecasted Enrollment Rate are available in the in-app information drawer

This is a model-predicted estimate of the trial's enrollment duration, calculated using the Forecasted Enrollment Rate, the number of selected investigators or sites, and the number of patients specified in the study criteria.

The total number of countries based on the selected investigators or sites.

The total number of investigators selected by the user. If sites are selected, this value reflects the total number of investigators selected within those sites.

The list of the selected investigator's or sites countries.

This metric represents the forecasted enrollment rate for the selected investigator's or site's country, as predicted by the AI model. It provides insight into each country’s ability to enroll patients and its expected enrollment performance. The value varies depending on whether the forecast is based on a single-country trial or a multi-country trial, which is indicated in the column header.

The number of sites selected by the user in each country.

The number of investigators selected by the user in each country.

This value reflects the user's selected allocation of investigators, based on the pattern of investigator selection.

This table provides the model’s suggested values for the optimal mix of countries and the distribution of sites or investigators to complete your study in the fastest and most cost-efficient way. These AI-driven recommendations are based on historical performance data, investigator availability, study start-up times, enrollment rates, and other relevant criteria to predict country-level trends. When an exact patient segment or phase match is not available, the model broadens the criteria to surface the closest viable countries capable of meeting study requirements.

This represents the country-specific enrollment rate predicted by the model, based on the countries recommended by the model. It reflects the relative average enrollment rate across all recommended countries, as defined by the model. Additional details on how this metric is predicted and how it differs from the Enrollment Rate Based On Completed Trials (Pt/Site/Month) are available in the in-app information drawer.

This is the median monthly rate at which patients were enrolled in similar trials conducted in the recommended countries over the past five years. The calculation is based on Actual Accrual data (or Target Accrual when Actual Accrual is unavailable), the number of reported sites, and the actual enrollment duration. Additional details on how this metric is calculated and how it differs from the Forecasted Enrollment Rate are available in the in-app information drawer

This is a model-predicted estimate of the trial's enrollment duration, calculated using the Forecasted Enrollment Rate, the recommended number of investigators, and the number of patients specified in the study criteria.

The total number of countries recommended by the model.

The recommended number of investigators for the selected indication needed to recruit the target number of patients specified in the input form.

The list of countries recommended by the model, sorted from highest to lowest performing. This list represents the exact number of countries needed to complete the study, based on the model’s recommended total country allocation.

This metric represents the forecasted enrollment rate for the recommended countries, as predicted by the AI model. It provides insight into each country’s ability to enroll patients and its expected enrollment performance. The value varies depending on whether the forecast is based on a single-country trial or a multi-country trial, which is indicated in the column header.

This refers to the model's recommended allocation of investigators in the recommended countries. The allocation is determined by the availability of investigators who meet the study criteria requirements to ensure the successful delivery of the study. The model allocates investigators to maximize the overall study Forecasted Enrollment Rate.

This represents the approximate distribution of investigators based on the total number of patients required for the study, as defined in the input form, and the model-recommended allocation by country. The intent is to guide and simplify the selection of investigators from the recommended list

This table displays recommended, historical, and selected investigators. Users can switch between four tabs to view investigators in each list. There are two recommended investigator lists: one based on the selected study criteria, and another based on model-suggested countries.

Users can toggle between the investigator view and the site view. The site view serves as the primary organizational view, where recommended investigators are grouped by site and ranked according to their recommendation scores.
​

In Investigator View, this list shows investigators from user-selected countries who have been evaluated and scored by the algorithm to determine their suitability for conducting the study. Investigator performance is assessed over the past ten years, with a focus on trials within the selected disease area, patient segment, and study phase. The evaluation considers factors such as investigator experience, performance, capacity, availability, patient pool, and recruitment potential to identify the investigators best suited to execute the study under the selected protocol for the selected countries. When an exact match cannot be found, patient segment criteria are relaxed to identify the closest qualified match capable of delivering the study.

In Site view, this list displays the primary organization for each recommended investigator, grouping all recommended investigators from the same site together. Users can select a site, which automatically selects the highest-ranking investigator, or they can choose any investigator grouped under that site.

In Investigator View, this list shows investigators from countries recommended by the model who have been evaluated and scored by the algorithm to determine their suitability for conducting the study. Investigators are evaluated and scored using ten years of performance data, with emphasis on experience in the selected disease area, patient segment, and study phase. The assessment incorporates multiple factors, including investigator experience, historical performance, operational capacity, availability, patient pool, and recruitment potential, to identify investigators best positioned to successfully deliver the study under the defined protocol. When an exact patient segment or phase match is not available, the model broadens the criteria to surface the closest viable investigators capable of meeting study requirements.

In Site view, this list displays the primary organization for each recommended investigator, grouping all recommended investigators from the same site together. Users can select a site, which automatically selects the highest-ranking investigator, or they can choose any investigator grouped under that site.

In Investigator View, this list shows the investigators who have previously participated in studies for your organization and match both the study criteria and the specified look-back period.

In Site view, this list displays the primary organization for each historical investigator, grouping all recommended investigators from the same site together. Users can select a site, which automatically selects the highest-ranking investigator, or they can choose any investigator grouped under that site.

In Investigator View, this list includes investigators manually chosen by the user from the Based on Study Criteria, Based on Model Suggested Countries, and Historical Investigators tabs.

You can export the list for offline use or open it in Sitetrove for deeper insights, enabling a comprehensive review of investigator details and relevant historical performance data.

In Site view, this list displays the primary organizations manually selected by the user, along with the corresponding selected investigators.

This section provides an overview of the columns included in the table, explaining the information presented for each investigator or site and how it can be used to assess suitability, performance, and other key attributes.

Displays the full name (first name, middle initial, and last name) of the experienced clinical investigator.

Provides a detailed analysis of investigator performance over the past ten years by leveraging Citeline, real-world, and proprietary datasets. It offers a comprehensive view of an investigator's sustained impact and trial-specific suitability through 24 performance scores that assess operational performance, experience in the selected indication, patient recruitment potential, real-world data coverage, and past trial outcomes.

This metric estimates the number of trials an investigator is expected to participate in during your study, taking into account the study’s start date and forecasted trial duration. It is calculated by considering the total number of active trials the investigator is engaged in within that timeframe and comparing it to the maximum number of concurrent trials the investigator has conducted over the past 10 years.

The trial load is categorized as High, Medium, or Low based on the following:

Lists the medical specialties of the investigator based on board certifications or specialization information from public sources.

Specifies the investigator's location, including city, state, and country.

Identifies the investigator’s main organization or practice location, which may or may not be where they have conducted trials.

Reflects the total number of trials linked to an investigator that match the entered study criteria (Disease, Patient Segment, Phase) conducted at any of the affiliated sites. If no matching trial are found, the system re-calculate the value with just the selected study's disease.

Shows the number of trials associated with an investigator that match the entered study criteria and are in Planned, Open, Closed, or Temporarily Closed status during the user-specified Estimated start date and Estimated end date, across all affiliated sites. A Closed trial indicates one that has stopped enrollment but is still ongoing.If no matching trial are found, the system re-calculate the value with just the selected study's disease.

Provides the overall Ongoing trial for the investigator during the user provided Estimated start date and Estimated end date across all affiliated sites, showing the total number of active trials across all indications. This includes trials in planned, open, closed, or temporarily closed statuses.

Shows the number of patients the investigator has seen in the past 12 months for the disease and age group relevant to your study, based on claims data. This metric is available for the United States only.

Shows the number of patients matching the selected disease within the investigator's primary organization, using EMR data, this value can be available for both US and non-US countries.

Provides demographic details on the patients seen by the investigator for the disease in your study, including race and ethnicity, based on claims data from the United States.

Displays the name of the primary organization where the recommended investigators are currently active. This represents the main organization for each recommended investigator.

The Site Recommendation Scores are based on the highest investigator scores within each site, reflecting how well the top-ranking investigator is performing currently and historically. The score provides a detailed analysis of investigator performance over the past ten years by leveraging Citeline, real-world, and proprietary datasets.

This metric estimates the number of trials an organization is likely to participate in during your study, factoring in the study’s start date and forecasted duration. It is calculated by assessing the total number of active trials the organization’s investigators are engaged in during that period and comparing it to the maximum number of concurrent trials the organization has conducted over the past 10 years.

The trial load is categorized as:

This metric estimates the number of trials an organization is expected to participate in during your study for the selected disease, considering the study’s start date and forecasted trial duration. It is calculated by assessing the total number of active trials the organization’s investigators are involved in during that timeframe and comparing it to the maximum number of concurrent trials the organization has conducted over the past 10 years.

The trial load is categorized as:

The country, city (and State/Province for US and Canada if available) of the primary organization

The larger entity (academic institutions, hospitals, research institutions) or the head office of the primary organization.

Shows the number of trials associated with the primary organization that match the entered study criteria (Disease, Patient Segment, Phase). If no direct matches are found, Patient Segment and Phase criteria are relaxed to identify the closest relevant trials for the primary organization.

Shows the number of trials associated with the primary organization that match the entered study criteria and are in Planned, Open, Closed, or Temporarily Closed status during the user-specified start and end dates. A Closed trial indicates one that has stopped enrollment but is still ongoing. If no direct matches are found, Patient Segment and Phase criteria are relaxed to identify the closest relevant trials for the primary organization.

Provides the overall Ongoing trial for the primary organization during the user provided Estimated start date and Estimated end date, showing the total number of active trials across all indications. This includes trials in planned, open, closed, or temporarily closed statuses.

Shows the total number of patients treated at the primary organization for the selected disease and age group. Counts are based on a 12-month rolling period using claims data.

Shows the number of investigators at the primary organization with experience in the specified disease.

The average number of reported sites in completed studies that align with the selected Disease, Patient segment and Phase over the past five years.

If no matching trial are found, the system re-calculate the value with just the selected study's disease, patient segment and phase.

A comparison between the recommended investigator's level of experience and the industry standard for the selected Disease and Phase. This metric assesses how an investigator's experience aligns with industry norms for the selected study phase (e.g., Phase I, II, III).

The total number of trials conducted for the selected disease by phase, excluding trials related to COVID-19. This provides insight into trial activity in a given therapeutic area and disease, without the impact of COVID-related studies.

A comparison between the number of trials that were completed as planned in the selected disease and phase and those that were terminated due to poor enrollment before completion. This ratio helps gauge the success rate and stability of trials in the same disease or phase.

The total number of active trials currently being conducted in the market that match the selected study's disease, patient segment, phase, mechanism of action, and biomarkers.

If no matching trial are found, the system re-calculate the value with just the selected study's disease, and phase.

A chart that visualizes enrollment trends in trials with similar disease, patient segment, and phase characteristics as the selected study over the past three years. It highlights the average enrollment rate (ER) of completed trials within the quarter of their primary completion date, offering insights into historical enrollment performance.

This chart displays ongoing trials conducted by other sponsors that align with the selected disease and patient segment, starting from the chosen estimated start date.