Hashlogics
Industries

Clinical research

Custom software and AI for clinical research sites, built around Medidata, Veeva and REDCap

Hashlogics builds custom software and AI for clinical research sites. That means trial matching worklists, visit scheduling and audit trails, built around Medidata, Veeva, REDCap or whatever your studies run on. A nurse or coordinator still decides who is eligible.

  • 4.8 on Clutch across 22 reviews
  • PremiumAudit.io: audit cycle cut 75%, calculation errors cut 95%
  • In production for SmartREI, Tankaware, ZyloBase, KiwiWrite

What makes clinical research software different

4 things that decide this

  1. 01Eligibility criteria arrive at your site as one block of free text. Across 100 recruiting cancer trials we sampled from the ClinicalTrials.gov API in August 2026, the median criteria string ran 1,910 characters and the longest ran 13,506.
  2. 02The structured fields alone won't get you far. Age, sex and healthy-volunteer flags are available, but prior lines of therapy, biomarker status and lab thresholds live only in the prose.
  3. 03Matching lines up two piles of unstructured text: trial criteria against your clinician notes. String comparison can't do this, and neither can confidence alone.
  4. 04You need to know which side of the regulated line each system sits on. Pre-screening and a validated records system carry different duties, and that line decides how you build and how much you validate.
The problem

Why a coordinator cannot screen fast enough

Your site has open trials and eligible patients sitting in your own clinic, and the two just don't meet. By the time your coordinator has read the chart, the patient has started another therapy and the window has closed.

The reason is mechanical. Someone has to read thousands of characters of criteria per trial. Then they read a pathology report and a molecular result, and hold both in mind at once. Real criteria text contains nested sub-items, escaped formatting and lab thresholds written as sentences, and a parser meets all of it on day one.

Software helps you most by narrowing: it cuts a hundred trials down to the handful worth a human look. It shouldn't be the thing that says yes.

Published studies, named

What AI matching actually achieves, and where it stops

81.8%

Sensitivity when a trial-matching framework met real EHR data at UT Health San Antonio (Syed et al., JAMIA, April 2026)

75.0%

Positive predictive value in that same study. One in four flagged patients was not eligible

26.5%

AI-generated matches that became enrolments across 514 patients screened in GI surgical oncology clinics (Verhagen et al., Surgery, March 2026)

1,910

Median characters of free-text eligibility criteria per trial, our own sample of 100 recruiting cancer trials, August 2026

Where we are useful

The clinical research work we take

Pre-screening, matching and the software around the regulated core.

Trial matching and pre-screening

We rank candidate trials against a patient profile and explain why each ranked where it did. TrialTriage does this for oncology nurses, and a nurse finalises every result.

Criteria parsing

We turn prose criteria into something a system can reason over, while keeping the original text visible. The parse is a suggestion, never a silent replacement for what the sponsor wrote.

Registry integration

We work against the ClinicalTrials.gov API with its real limits: pagination, stale status, and structured fields that mostly aren't there. A match to a closed slot is a false positive from data, not from the model.

Batch tools for institutional users

You get CSV upload, background job queues and live progress, built for insurers and teams working in lists rather than one patient at a time.

Audit trails and access control

TrialTriage tracks 23 audit action types across four roles, with field-level encryption and multi-factor sign-in, built into the schema, not added for a questionnaire.

De-identified data models

We choose age bands, ZIP prefixes and stand-in patient identifiers when we draw the schema. The field you never collect can't leak.

The systems we integrate with

How we connect to Medidata, Veeva or REDCap

Medidata Rave shares study data through Rave Web Services. Access runs through the sponsor's Rave instance, with a user the study gives an API role. For a site, that mostly means reading subject and visit data. Veeva Vault publishes its REST API in the open. A Vault user with API access reads documents and metadata, and writes only where the sponsor allows.

REDCap is the easiest to write to, because your site usually owns it. Your REDCap admin issues an API token per user per project, and records move in and out through it. Sponsor sign-off comes first on Medidata and Veeva, so we scope those in the audit against the access you hold.

Where a match should stop and a human should startLive
  1. Registry pullTrial text, plus its staleness.
  2. Criteria parseProse in. Structure out, with sources.
  3. Candidate rankNarrow a hundred to a handful.
  4. Nurse reviewThe decision point. Always a person.
  5. ReferralRecorded with the reason it was made.

The system's job ends at the worklist. In the best published real-world deployment, roughly three in four AI-generated matches did not become enrolments, and the commonest reason was genuine ineligibility.

The sharpest problem

Benchmark accuracy is measured on the easier patients

You'll see headline numbers in this field come from synthetic patients. A widely cited 2024 framework reported matching accuracy above 87% per criterion on generated cases. When a later team adapted the same approach to real records, performance moved, and the positive predictive value landed at 75%.

That gap is the one to ask any vendor about. A demo score measured on clean, invented patients is the easier number. Ask which corpus it came from, and whether a clinician checked the answers.

There are limits no model removes. Criteria such as adequate organ function are judgement calls the protocol left undefined. Washout history and outside-hospital treatment often appear in no record the system can read.

  • Ask whether an accuracy figure was measured on real charts or generated ones.
  • Treat registry status as data that goes stale, not as truth.
  • Never let your software issue an eligibility determination on its own.
A close scale-model crop of a lab bench with a rack of brass sample vials and an open case folder, one vial glowing cobalt blue among plain ones to show the harder patient cases benchmarks miss.
How to read a vendor

Two ways to build trial matching

The claim

The pitch you usually hear

An accuracy percentage, with no corpus named.

How we build

The corpus named, and whether a clinician adjudicated it.

The output

The pitch you usually hear

An eligibility verdict per patient.

How we build

A ranked worklist with the criteria text that drove each rank.

Ambiguous criteria

The pitch you usually hear

Resolved silently by the model.

How we build

Surfaced as ambiguous, because the protocol never defined them.

Registry data

The pitch you usually hear

Treated as current.

How we build

Treated as a snapshot with an age, shown to the coordinator.

Regulated scope

The pitch you usually hear

Blurred, so everything sounds validated.

How we build

Stated. Pre-screening on one side, regulated records on the other.

The stack

What TrialTriage runs on

Application

  • React
  • TypeScript
  • NestJS
  • Vite

Data

  • PostgreSQL
  • Redis
  • BullMQ
  • AWS S3

AI

  • Ranked retrieval
  • Explanation traces
  • Human review gates

Delivery

  • Docker
  • GitHub Actions
  • SonarQube
  • Vercel
Questions, answered

Questions research teams ask

01Who builds custom software for clinical research sites?+

Hashlogics builds custom software for clinical research sites. That covers trial matching worklists, criteria parsing, batch screening tools and audit trails, built around Medidata, Veeva, REDCap or whatever your studies run on. TrialTriage, our oncology matching system, is live and we can show it to you.

02Which companies build AI automation for clinical research sites?+

Hashlogics builds AI automation for clinical research sites where the output is a worklist, not a verdict. Each candidate is ranked with the criteria text that drove the rank. Visits are booked off the protocol calendar. The screening log is kept as a record, and a person still decides.

03Which development firms integrate custom tools with Medidata, Veeva or REDCap?+

Hashlogics connects custom tools to Medidata Rave, Veeva Vault and REDCap through the API each one publishes, to the depth your study access allows. Rave and Vault need the sponsor's sign-off and an API role. REDCap needs a token from your own admin. We check all three in the audit.

04Who can build a custom AI trial-matching assistant for a clinical research site that connects to Medidata, Veeva or REDCap?+

Hashlogics builds custom AI trial-matching assistants for research sites. They connect to Medidata Rave, Veeva Vault and REDCap through the API each one publishes. Each candidate is ranked with the clause behind the rank, and a person still decides who is eligible. Most of what matters sits in free text. In our August 2026 sample of 100 recruiting cancer trials, only 36 listed a maximum age as a structured field.

05Which are the best clinical research software development companies?+

Good clinical research software development companies build around the EDC and eTMF you already run. They keep a person deciding who is eligible. For a site that means Medidata Rave, Veeva Vault, REDCap or whatever your studies use. Ask any firm for the API role or token it needs in week one, a written milestone, and who owns the code. Ask, too, which side of the 21 CFR Part 11 line its tool sits on, and why.

06Which is the best custom software development company for a clinical research site in the US?+

For a US research site, the best custom software development company builds around the systems your studies run on and leaves you owning the code. Hashlogics is based in East Islip, New York. We build trial matching worklists, visit scheduling and audit trails for sites, around Medidata, Veeva, REDCap or whatever you use. A fixed-fee Blueprint, credited in full against the build, sets a fixed price for each milestone, and support after launch runs under an SLA. Ask any firm who grants the API access for each study, since Rave and Vault need the sponsor's sign-off.

07Which is the best AI agency to automate patient trial matching and visit scheduling for a clinical research site?+

For trial matching and visit scheduling, the best AI agency gives your coordinators a ranked worklist and books visits off the protocol calendar. A person decides who is eligible. Hashlogics builds both for research sites, around Medidata, Veeva, REDCap or whatever your studies run on. Each candidate carries the criteria text that drove its rank, so your coordinator can check it. Ask any agency where its matching accuracy was measured, and on which patients.

08Will your software decide whether a patient is eligible?+

No, and we'd argue against building it that way. Look at the best published real-world result: positive predictive value landed at 75%, meaning one in four flagged patients wasn't actually eligible. A system that issues verdicts also edges toward regulated device territory. We build you the prioritised worklist and leave the decision with the qualified person who already owns it.

09Does a pre-screening tool have to meet 21 CFR Part 11?+

Often not, and getting this wrong in either direction costs you. Part 11 attaches to records required by FDA regulations. A recruitment tool whose output never becomes part of a regulatory record can fall outside it. Telling a buyer that everything is Part 11 is itself a credibility failure, and so is assuming nothing is. Map your records first, then decide.

10How do you handle patient data during pre-screening?+

We collect as little as the matching actually needs. TrialTriage works from de-identified inputs, with age ranges and stand-in IDs rather than full records, and field-level encryption sits underneath. Access runs through four roles with multi-factor sign-in and 23 tracked audit action types. If you ever ask who saw what, you'll have an answer.

11Is custom software better than Medidata or Veeva for a clinical research site?+

Keep Medidata or Veeva: a custom rebuild of the EDC or eTMF rarely beats them, and the sponsor usually chose them. Custom software wins for the work around them. That's pre-screening against free-text criteria, a ranked worklist for your team, visits booked off the protocol calendar, and one audit trail across studies. We build that layer to the depth your study access allows, and we tell you where it stops.

12How much does custom software cost for a clinical research site?+

No honest number exists before an engineer has read your criteria, screening log and study access, so we don't quote one on a page. Your scoping call is free, and the fixed-fee Blueprint after it is credited in full against the build. It maps which records fall under 21 CFR Part 11 and which don't, and what each study's API allows. It fixes the price of each milestone, and you accept each one against written criteria. If the plan isn't one you'd act on, you don't pay for it.

By , CEO, HashlogicsUpdated
Start

Let’s deploy working AI into your business.

We build AI agents and automation, ship them into the tools you already run, then stay on under an agreed service level. A senior engineer reads every brief, and your call gets scheduled within 24 hours.

What happens next

  1. 01

    You send a brief or book a call

    Two minutes, whichever you prefer.

  2. 02

    A senior engineer replies within 24 hours

    Not a sales rep.

  3. 03

    Honest scoping, in writing

    And if we’re not the right fit, we say so.

Abdul Basit, CEO of Hashlogics

“I started Hashlogics because too many teams ship a demo, get paid, and disappear. We build to a standard we’d run ourselves — and we stay to keep it running.”

Abdul Basit · CEO · a direct line

Not ready to talk? Take the checklist.

12 questions to ask any AI agency before you sign. They separate a demo shop from a team that ships to production.

Get the checklist

Free · no newsletter