Healthcare & Medical Apps Moderation

The moderation problem

Medical surfaces are a false-positive minefield. Patients describe symptoms using anatomical terms, drug names, and frank language about bodily functions. A filter tuned for a comment section will quarantine half of every legitimate medical conversation.

Why a word list isn't enough

Generic word lists flag 'breast', 'penetration', or candid symptom descriptions as sexual or profane. Clinicians and patients then can't communicate, and your support queue fills with appeals.

How The Profanity API handles it

Use context `medical` so clinical and anatomical vocabulary is treated as professional rather than profane, with `balanced` mode catching the rare case where a medical surface is actually used to harass or send abuse.

const res = await fetch("https://api.theprofanityapi.com/v1/check", {
  method: "POST",
  headers: {
    "Authorization": "Bearer " + process.env.PROFANITY_API_KEY,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({ text, context: "medical", mode: "balanced" }),
});

const { flagged, intent, score } = await res.json();