# Index of Severity for Eosinophilic Esophagitis

I-SEE

Status: LIVE
Price: $0.005 USDC
`GET /api/calc/i_see`
HTML: https://magentlab.com/docs/i-see
Markdown: https://magentlab.com/docs/i-see.md

Not a medical device. Not a diagnosis, dose, or listing recommendation.

## What it computes

Sum Dellon 2022 Table I I-SEE items (symptoms, food impaction, stacking complications, inflammatory endoscopy and peak eos, fibrostenotic endoscopy and histologic fibrosis) and return the point total (max 78) and published band (inactive, mild, moderate, or severe). Not a diagnosis of EoE and not EREFS.

## When to use

When an agent has already assigned Dellon 2022 Table I symptoms, complications, inflammatory findings, and fibrostenotic findings and needs the published I-SEE total and band, not a diagnosis of EoE and not EREFS.

## When not to use

- Not a medical device and not a diagnosis of eosinophilic esophagitis or a treatment order.
- Each item is a caller-assigned Dellon 2022 Table I token. magent does not perform endoscopy or count eosinophils. magent does not assign age; the caller maps age into food_impaction and fibro_endoscopy tokens.
- Not EREFS. I-SEE is a clinical severity index (symptoms, complications, inflammatory findings, and fibrostenotic findings), not the Hirano 2013 endoscopic reference score.
- For boxes with more than one element, each selected feature gets points (complications stack). Other rows are exclusive. Bands follow Dellon 2022 Table I only: <1 inactive, 1–6 mild, 7–14 moderate, ≥15 severe.

## Formula

```
I-SEE = symptoms (none 0, weekly 1, daily 2, multiple_or_social 4) + food_impaction (none 0, adult_ge_18 2, child_lt_18 4) + hospitalization_eoe 4 + esophageal_perforation 15 + malnutrition 15 + persistent_inflammation 15 + inflam_endoscopy (none 0, localized 1, diffuse 2) + peak_eos (lt_15 0, 15_60 1, gt_60 2) + fibro_endoscopy (none 0, passes_easily 1, dilation_or_snug 2, cannot_pass_or_repeated 15) + histologic_fibrosis 2; Dellon 2022 Table I; complications stack (each selected feature gets points); exclusive within other rows; bands <1 inactive, 1-6 mild, 7-14 moderate, ≥15 severe; max 78; not EREFS
```

## Citation

[A Clinical Severity Index for Eosinophilic Esophagitis: Development, Consensus, and Future Directions](https://doi.org/10.1016/j.jaci.2022.03.015)
Dellon ES, Khoury P, Muir AB, Liacouras CA, Safroneeva E, Atkins D, Collins MH, Gonsalves N, Falk GW, Spergel JM, Schoepfer AM, Menard-Katcher C, Furuta GT, Aceves S
J Allergy Clin Immunol. 2022;150(1):33-47
DOI: [10.1016/j.jaci.2022.03.015](https://doi.org/10.1016/j.jaci.2022.03.015)

## Worked example

### Dellon 2022 Table II A (mild)

Given: `esophageal_perforation=false, fibro_endoscopy=none, food_impaction=none, histologic_fibrosis=false, hospitalization_eoe=false, inflam_endoscopy=localized, malnutrition=false, peak_eos=15_60, persistent_inflammation=false, symptoms=daily`

1. symptoms daily 2 + no complications 0 + inflam_endoscopy localized 1 + peak_eos 15_60 1 + fibro_endoscopy none 0 + histologic_fibrosis false 0
2. Score = 4 (max 78); isee_band mild


### Dellon 2022 Table II B (severe)

Given: `esophageal_perforation=false, fibro_endoscopy=cannot_pass_or_repeated, food_impaction=adult_ge_18, histologic_fibrosis=true, hospitalization_eoe=false, inflam_endoscopy=diffuse, malnutrition=false, peak_eos=15_60, persistent_inflammation=false, symptoms=daily`

1. symptoms daily 2 + food_impaction adult_ge_18 2 + inflam_endoscopy diffuse 2 + peak_eos 15_60 1 + fibro_endoscopy cannot_pass_or_repeated 15 + histologic_fibrosis true 2
2. Score = 24 (max 78); isee_band severe


### Dellon 2022 Table II C (moderate)

Given: `esophageal_perforation=false, fibro_endoscopy=passes_easily, food_impaction=none, histologic_fibrosis=true, hospitalization_eoe=false, inflam_endoscopy=diffuse, malnutrition=false, peak_eos=gt_60, persistent_inflammation=false, symptoms=multiple_or_social`

1. symptoms multiple_or_social 4 + no complications 0 + inflam_endoscopy diffuse 2 + peak_eos gt_60 2 + fibro_endoscopy passes_easily 1 + histologic_fibrosis true 2
2. Score = 11 (max 78); isee_band moderate


## Also searched as

- I-SEE
- Index of Severity for Eosinophilic Esophagitis
- EoE severity index
- Dellon I-SEE
- eosinophilic esophagitis severity
- I SEE score
- Dellon 2022 I-SEE
- EoE clinical severity index

## Parameters

- `symptoms` (string, required): Caller-assigned Dellon 2022 Table I symptoms: none (0), weekly (1), daily (2), or multiple_or_social (4; multiple times per day or disrupting social functioning).
- `food_impaction` (string, required): Caller-assigned Dellon 2022 Table I food impaction with ER visit or endoscopy: none (0), adult_ge_18 (2; patient ≥18 years), or child_lt_18 (4; patient <18 years). The caller assigns the age-specific token; magent does not take a separate age parameter.
- `hospitalization_eoe` (boolean, required): Caller-assigned hospitalization due to EoE (Dellon 2022 Table I complication; stacks with other selected complication features). true (4) or false (0).
- `esophageal_perforation` (boolean, required): Caller-assigned esophageal perforation (Dellon 2022 Table I complication; stacks). true (15) or false (0).
- `malnutrition` (boolean, required): Caller-assigned malnutrition with BMI <5th percentile or decreased growth trajectory (Dellon 2022 Table I complication; stacks). true (15) or false (0). The caller assigns this flag; magent does not compute BMI percentiles.
- `persistent_inflammation` (boolean, required): Caller-assigned persistent inflammation requiring elemental formula or systemic corticosteroid or immunomodulatory treatment (Dellon 2022 Table I complication; stacks). true (15) or false (0).
- `inflam_endoscopy` (string, required): Caller-assigned Dellon 2022 Table I inflammatory endoscopy (edema, furrows, and/or exudates): none (0), localized (1), or diffuse (2). magent does not perform endoscopy. Not EREFS.
- `peak_eos` (string, required): Caller-assigned Dellon 2022 Table I peak eosinophils per hpf: lt_15 (0; <15), 15_60 (1; 15-60), or gt_60 (2; >60). magent does not count eosinophils.
- `fibro_endoscopy` (string, required): Caller-assigned Dellon 2022 Table I fibrostenotic endoscopy (rings, strictures): none (0), passes_easily (1; present but endoscope passes easily), dilation_or_snug (2; requires dilation or is a snug pass), or cannot_pass_or_repeated (15; cannot pass a standard endoscope; repeated dilations in an adult ≥18; or any dilation in a child <18). The caller assigns the 15-point token; magent does not take a separate age parameter. magent does not perform endoscopy.
- `histologic_fibrosis` (boolean, required): Caller-assigned Dellon 2022 Table I histologic fibrosis: true (2; basal zone hyperplasia or lamina propria fibrosis, or dilated intercellular spaces/surface epithelial alteration if no lamina propria) or false (0). magent does not read histology.

## Bulk (POST)

POST the same path with a JSON items array. The first item is the GET unit; each additional item is $0.002. Invalid items return HTTP 400 before settlement.

Method: `POST /api/calc/i_see`
Max items: 25
Price: unit_amount + extra_item_amount * (n - 1) (unit 5000 atomic, extra 2000 atomic)
Status: PREVIEW

- 1 to 25 items. Each item uses the same keys as the GET query parameters.
- POST of 1 item costs the same as GET. Lists longer than 25: chunk into multiple POSTs. Extra items still execute; do not pad dummy rows.
- The first invalid item fails the whole request (index in the 400 JSON). You are not charged.
- HTTP 200 is {count, path, items}. Each items[i] is the GET 200 body for that row.
- Catalog misses (empty matches, found=false) stay paid 200s inside that slot.
- x402 resource URL is this path plus n and body_sha256. Browsers that prefer text/html get the same paywall as GET; Pay retries POST with the same items.

Example request:

```json
{
  "items": [
    {
      "esophageal_perforation": "false",
      "fibro_endoscopy": "none",
      "food_impaction": "none",
      "histologic_fibrosis": "false",
      "hospitalization_eoe": "false",
      "inflam_endoscopy": "localized",
      "malnutrition": "false",
      "peak_eos": "15_60",
      "persistent_inflammation": "false",
      "symptoms": "daily"
    },
    {
      "esophageal_perforation": "false",
      "fibro_endoscopy": "none",
      "food_impaction": "none",
      "histologic_fibrosis": "false",
      "hospitalization_eoe": "false",
      "inflam_endoscopy": "localized",
      "malnutrition": "false",
      "peak_eos": "15_60",
      "persistent_inflammation": "false",
      "symptoms": "daily"
    }
  ]
}
```

Human paywall (two-item fixture): https://api.magentlab.com/paywall/bulk/i-see

Example 200:

```json
{
  "count": 2,
  "path": "/api/calc/i_see",
  "items": [
    {
      "components": [
        {
          "value": "daily",
          "factor": "symptoms",
          "points": 2,
          "present": true
        },
        {
          "value": "none",
          "factor": "food_impaction",
          "points": 0,
          "present": true
        },
        {
          "factor": "hospitalization_eoe",
          "points": 0,
          "present": false
        },
        {
          "factor": "esophageal_perforation",
          "points": 0,
          "present": false
        },
        {
          "factor": "malnutrition",
          "points": 0,
          "present": false
        },
        {
          "factor": "persistent_inflammation",
          "points": 0,
          "present": false
        },
        {
          "value": "localized",
          "factor": "inflam_endoscopy",
          "points": 1,
          "present": true
        },
        {
          "value": "15_60",
          "factor": "peak_eos",
          "points": 1,
          "present": true
        },
        {
          "value": "none",
          "factor": "fibro_endoscopy",
          "points": 0,
          "present": true
        },
        {
          "factor": "histologic_fibrosis",
          "points": 0,
          "present": false
        }
      ],
      "disclaimer": "Not a medical device. Deterministic published-formula or published-code output for autonomous agents. A licensed clinician remains responsible for patient care and billing submissions.",
      "citation": {
        "authors": "Dellon ES, Khoury P, Muir AB, Liacouras CA, Safroneeva E, Atkins D, Collins MH, Gonsalves N, Falk GW, Spergel JM, Schoepfer AM, Menard-Katcher C, Furuta GT, Aceves S",
        "doi": "10.1016/j.jaci.2022.03.015",
        "id": "dellon-2022",
        "pmid": "35606166",
        "source": "J Allergy Clin Immunol. 2022;150(1):33-47",
        "title": "A Clinical Severity Index for Eosinophilic Esophagitis: Development, Consensus, and Future Directions"
      },
      "formula": "i_see",
      "formula_expression": "I-SEE = symptoms (none 0, weekly 1, daily 2, multiple_or_social 4) + food_impaction (none 0, adult_ge_18 2, child_lt_18 4) + hospitalization_eoe 4 + esophageal_perforation 15 + malnutrition 15 + persistent_inflammation 15 + inflam_endoscopy (none 0, localized 1, diffuse 2) + peak_eos (lt_15 0, 15_60 1, gt_60 2) + fibro_endoscopy (none 0, passes_easily 1, dilation_or_snug 2, cannot_pass_or_repeated 15) + histologic_fibrosis 2; Dellon 2022 Table I; complications stack (each selected feature gets points); exclusive within other rows; bands <1 inactive, 1-6 mild, 7-14 moderate, ≥15 severe; max 78; not EREFS",
      "max_score": 78,
      "score": 4,
      "esophageal_perforation": false,
      "fibro_endoscopy": "none",
      "food_impaction": "none",
      "histologic_fibrosis": false,
      "hospitalization_eoe": false,
      "inflam_endoscopy": "localized",
      "isee_band": "mild",
      "malnutrition": false,
      "peak_eos": "15_60",
      "persistent_inflammation": false,
      "symptoms": "daily"
    },
    {
      "components": [
        {
          "value": "daily",
          "factor": "symptoms",
          "points": 2,
          "present": true
        },
        {
          "value": "none",
          "factor": "food_impaction",
          "points": 0,
          "present": true
        },
        {
          "factor": "hospitalization_eoe",
          "points": 0,
          "present": false
        },
        {
          "factor": "esophageal_perforation",
          "points": 0,
          "present": false
        },
        {
          "factor": "malnutrition",
          "points": 0,
          "present": false
        },
        {
          "factor": "persistent_inflammation",
          "points": 0,
          "present": false
        },
        {
          "value": "localized",
          "factor": "inflam_endoscopy",
          "points": 1,
          "present": true
        },
        {
          "value": "15_60",
          "factor": "peak_eos",
          "points": 1,
          "present": true
        },
        {
          "value": "none",
          "factor": "fibro_endoscopy",
          "points": 0,
          "present": true
        },
        {
          "factor": "histologic_fibrosis",
          "points": 0,
          "present": false
        }
      ],
      "disclaimer": "Not a medical device. Deterministic published-formula or published-code output for autonomous agents. A licensed clinician remains responsible for patient care and billing submissions.",
      "citation": {
        "authors": "Dellon ES, Khoury P, Muir AB, Liacouras CA, Safroneeva E, Atkins D, Collins MH, Gonsalves N, Falk GW, Spergel JM, Schoepfer AM, Menard-Katcher C, Furuta GT, Aceves S",
        "doi": "10.1016/j.jaci.2022.03.015",
        "id": "dellon-2022",
        "pmid": "35606166",
        "source": "J Allergy Clin Immunol. 2022;150(1):33-47",
        "title": "A Clinical Severity Index for Eosinophilic Esophagitis: Development, Consensus, and Future Directions"
      },
      "formula": "i_see",
      "formula_expression": "I-SEE = symptoms (none 0, weekly 1, daily 2, multiple_or_social 4) + food_impaction (none 0, adult_ge_18 2, child_lt_18 4) + hospitalization_eoe 4 + esophageal_perforation 15 + malnutrition 15 + persistent_inflammation 15 + inflam_endoscopy (none 0, localized 1, diffuse 2) + peak_eos (lt_15 0, 15_60 1, gt_60 2) + fibro_endoscopy (none 0, passes_easily 1, dilation_or_snug 2, cannot_pass_or_repeated 15) + histologic_fibrosis 2; Dellon 2022 Table I; complications stack (each selected feature gets points); exclusive within other rows; bands <1 inactive, 1-6 mild, 7-14 moderate, ≥15 severe; max 78; not EREFS",
      "max_score": 78,
      "score": 4,
      "esophageal_perforation": false,
      "fibro_endoscopy": "none",
      "food_impaction": "none",
      "histologic_fibrosis": false,
      "hospitalization_eoe": false,
      "inflam_endoscopy": "localized",
      "isee_band": "mild",
      "malnutrition": false,
      "peak_eos": "15_60",
      "persistent_inflammation": false,
      "symptoms": "daily"
    }
  ]
}
```

## Response fields

- `formula` (string): i_see
- `formula_expression` (string): Exact expression used
- `score` (integer): Dellon 2022 Table I I-SEE points 0-78 (complications stack)
- `max_score` (integer): Always 78
- `isee_band` (string): Dellon 2022 Table I band: inactive (<1), mild (1-6), moderate (7-14), or severe (≥15). A score band, not a diagnosis of EoE.
- `symptoms` (string): Caller-assigned token: none, weekly, daily, or multiple_or_social
- `food_impaction` (string): Caller-assigned token: none, adult_ge_18, or child_lt_18
- `hospitalization_eoe` (boolean): Caller-assigned hospitalization due to EoE (4 if true)
- `esophageal_perforation` (boolean): Caller-assigned esophageal perforation (15 if true)
- `malnutrition` (boolean): Caller-assigned malnutrition flag (15 if true)
- `persistent_inflammation` (boolean): Caller-assigned persistent-inflammation treatment flag (15 if true)
- `inflam_endoscopy` (string): Caller-assigned token: none, localized, or diffuse
- `peak_eos` (string): Caller-assigned token: lt_15, 15_60, or gt_60
- `fibro_endoscopy` (string): Caller-assigned token: none, passes_easily, dilation_or_snug, or cannot_pass_or_repeated
- `histologic_fibrosis` (boolean): Caller-assigned histologic fibrosis (2 if true)
- `components` (array): Per-item caller-assigned points
- `citation` (object): Dellon et al. J Allergy Clin Immunol 2022 citation
- `disclaimer` (string): Not-a-device notice

## Example JSON

Frozen fixture. Not a live lookup.

```json
{
  "components": [
    {
      "value": "daily",
      "factor": "symptoms",
      "points": 2,
      "present": true
    },
    {
      "value": "none",
      "factor": "food_impaction",
      "points": 0,
      "present": true
    },
    {
      "factor": "hospitalization_eoe",
      "points": 0,
      "present": false
    },
    {
      "factor": "esophageal_perforation",
      "points": 0,
      "present": false
    },
    {
      "factor": "malnutrition",
      "points": 0,
      "present": false
    },
    {
      "factor": "persistent_inflammation",
      "points": 0,
      "present": false
    },
    {
      "value": "localized",
      "factor": "inflam_endoscopy",
      "points": 1,
      "present": true
    },
    {
      "value": "15_60",
      "factor": "peak_eos",
      "points": 1,
      "present": true
    },
    {
      "value": "none",
      "factor": "fibro_endoscopy",
      "points": 0,
      "present": true
    },
    {
      "factor": "histologic_fibrosis",
      "points": 0,
      "present": false
    }
  ],
  "disclaimer": "Not a medical device. Deterministic published-formula or published-code output for autonomous agents. A licensed clinician remains responsible for patient care and billing submissions.",
  "citation": {
    "authors": "Dellon ES, Khoury P, Muir AB, Liacouras CA, Safroneeva E, Atkins D, Collins MH, Gonsalves N, Falk GW, Spergel JM, Schoepfer AM, Menard-Katcher C, Furuta GT, Aceves S",
    "doi": "10.1016/j.jaci.2022.03.015",
    "id": "dellon-2022",
    "pmid": "35606166",
    "source": "J Allergy Clin Immunol. 2022;150(1):33-47",
    "title": "A Clinical Severity Index for Eosinophilic Esophagitis: Development, Consensus, and Future Directions"
  },
  "formula": "i_see",
  "formula_expression": "I-SEE = symptoms (none 0, weekly 1, daily 2, multiple_or_social 4) + food_impaction (none 0, adult_ge_18 2, child_lt_18 4) + hospitalization_eoe 4 + esophageal_perforation 15 + malnutrition 15 + persistent_inflammation 15 + inflam_endoscopy (none 0, localized 1, diffuse 2) + peak_eos (lt_15 0, 15_60 1, gt_60 2) + fibro_endoscopy (none 0, passes_easily 1, dilation_or_snug 2, cannot_pass_or_repeated 15) + histologic_fibrosis 2; Dellon 2022 Table I; complications stack (each selected feature gets points); exclusive within other rows; bands <1 inactive, 1-6 mild, 7-14 moderate, ≥15 severe; max 78; not EREFS",
  "max_score": 78,
  "score": 4,
  "esophageal_perforation": false,
  "fibro_endoscopy": "none",
  "food_impaction": "none",
  "histologic_fibrosis": false,
  "hospitalization_eoe": false,
  "inflam_endoscopy": "localized",
  "isee_band": "mild",
  "malnutrition": false,
  "peak_eos": "15_60",
  "persistent_inflammation": false,
  "symptoms": "daily"
}
```

## Errors

- HTTP 400 `invalid_isee`: each I-SEE item must be a published Dellon 2022 Table I category (symptoms none/weekly/daily/multiple_or_social; food_impaction none/adult_ge_18/child_lt_18; inflam_endoscopy none/localized/diffuse; peak_eos lt_15/15_60/gt_60; fibro_endoscopy none/passes_easily/dilation_or_snug/cannot_pass_or_repeated). Returned before settlement; you are not charged.
- HTTP 400 `invalid_flag`: boolean clinical flags must be true or false Returned before settlement; you are not charged.
- HTTP 400 `invalid_items`: POST body must be a JSON object with only an items array Returned before settlement; you are not charged.
- HTTP 400 `invalid_item_count`: items must be an array of 1 to 25 objects Returned before settlement; you are not charged.
- HTTP 400 `invalid_item`: each items entry must be a JSON object Returned before settlement; you are not charged.

Shared HTTP 402 and 503: https://magentlab.com/docs/payments

## Related tools

- [EREFS](https://magentlab.com/docs/erefs) — Sum five caller-assigned Hirano 2013 modified EREFS descriptors (edema 0-1, rings 0-3, exudates 0-2, furrows 0-1 after collapsing original 0-2, stricture 0-1) and return the total (max 8). Does not return activity bands, inflammatory or fibrostenotic subscores, or later 0-9 furrows 0-2 expansions.

## Payment

Unpaid requests return HTTP 402 even if query parameters or POST items are missing or invalid, so CDP and agents can index the path. After a PAYMENT-SIGNATURE, invalid params return HTTP 400 JSON before settlement. magent does not charge. Fix the params, then request a new 402 quote for that complete URL. Catalog misses (empty matches, found=false) are valid paid 200s.

- GET the tool with Accept: application/json (do not send Accept: text/html unless you want the human paywall).
- HTTP 402 means you have not paid. Decode the base64 PAYMENT-REQUIRED header. HTTP 503 is not a new quote.
- Sign accepts[0] (exact, EIP-3009) with validBefore = now + maxTimeoutSeconds (600 seconds), or accepts[1] (batch-settlement deposit/voucher) on product GET. Ping and POST {items} stay exact. Magent retries transient facilitator 429/5xx before answering.
- Retry the same URL with PAYMENT-SIGNATURE (base64 JSON of accepted and payload). Magent attaches canonical extensions.bazaar on CDP verify/settle; echoing 402 bazaar is optional.
- Success is HTTP 200 JSON plus PAYMENT-RESPONSE. exact settles before the tool. batch-settlement verifies (and deposit-settles) before the tool and commits the charge after HTTP 2xx. HTTP 503: retry the same PAYMENT-SIGNATURE. Mint a new exact nonce only after a new HTTP 402.

- offered `exact` on eip155:8453: Fixed-price USDC on Base. The buyer authorizes the advertised amount (EIP-3009). magent settles before the tool runs (paymentFlow upfront). extra.assetTransferMethod=eip3009 extra.paymentFlow=upfront.
- offered `batch-settlement` on eip155:8453: Payment-channel vouchers claimed later in batches. Exact stays accepts[0]. Same-path POST {items} is still exact. extra.assetTransferMethod=eip3009 extra.paymentFlow=authorization.

- not offered `upto`: Not offered. Usage-based: buyer authorizes a ceiling, seller settles the actual amount after work. Reserved for a future metered tool. Not for current calculators or code search.

Same-path POST {items} is still scheme exact: one EIP-3009 authorization for GET unit plus $0.002 per extra item. That is not x402 batch-settlement (payment channels / vouchers).

Shared HTTP 402 and 503 table: https://magentlab.com/docs/payments

Stdio MCP (one process per host): https://magentlab.com/docs/mcp

## Guarantees

- HTTP 402 is unpaid, including a missing query. After PAYMENT-SIGNATURE, invalid parameters return HTTP 400 before settlement. You are not charged. HTTP 402 never includes the tool JSON.
- exact: settlement finishes before the tool (paymentFlow upfront). batch-settlement: verify/deposit before the tool; chargedCumulativeAmount commits after HTTP 2xx. Uncertain or failed settlement fails closed (HTTP 503). Retry the same PAYMENT-SIGNATURE.
- HTTP 402 is unpaid only. Do not sign a second authorization because of a 503.
- Execution is timeout-bounded and concurrency-capped.
- Calculator inputs are stored encrypted for allowlisted operators (Magent Console). They are not in public logs, SSH lookups, catalog, or rollups. Request logs store path without query.
