{
  "docId": "019dd923-5e88-73ef-bd5c-f6fdd8f57895",
  "docSlug": "3a892393f72c1ff5",
  "documentTitle": "2019 Air Street Capital The State of AI Report 2019",
  "authorId": "AirStreetCapital",
  "authorName": "Nathan Benaich and Ian Hogarth",
  "documentKindSlug": "consulting-deck",
  "documentKindLabel": "Consulting deck",
  "sourceTypeSlug": "vc_research",
  "sourceTypeLabel": "VC research",
  "presentationDate": null,
  "orientation": "landscape",
  "aspectRatio": 1.777,
  "pageNumber": 28,
  "pageCount": 136,
  "prevPage": 27,
  "nextPage": 29,
  "slideType": "case_study",
  "function": "illustrate_case",
  "density": "dense",
  "nDataPoints": 15,
  "notes": "The slide illustrates a specific medical AI application developed by DeepMind and Moorfields Eye Hospital.",
  "elementsJson": [
    "headline_text",
    "bullet_list",
    "process_diagram",
    "bar_chart_grouped",
    "kpi_table",
    "logo_grid"
  ],
  "metadataConfidence": 1,
  "imagePath": null,
  "slideHref": "/slides/019dd923-5e88-73ef-bd5c-f6fdd8f57895/28",
  "deckHref": "/decks/019dd923-5e88-73ef-bd5c-f6fdd8f57895",
  "deckJsonHref": "/decks/019dd923-5e88-73ef-bd5c-f6fdd8f57895.json",
  "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5c-f6fdd8f57895#slide-28",
  "components": [
    {
      "bbox": null,
      "kind": "callout",
      "text": "Expert-level diagnosis and treatment referral suggestions is achieved using a two-stage deep learning approach.",
      "attrs": null,
      "subkind": null,
      "toolName": "Visual emphasis",
      "toolSlug": "visual-emphasis",
      "confidence": null,
      "componentId": "019dd952-41ab-72d9-bbc4-24b1bcc9e4be",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.25,
        "w": 0.45,
        "x": 0.48,
        "y": 0.72
      },
      "kind": "chart",
      "text": "Error rate comparison between OCT only and OCT + fundus + notes across different specialists.",
      "attrs": null,
      "subkind": "bar-grouped",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "3b9fabba-e4bf-4a09-a1ba-11af93e89e12",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.45,
        "w": 0.45,
        "x": 0.52,
        "y": 0.25
      },
      "kind": "diagram",
      "text": "Two-stage deep learning pipeline: Digital OCT scan -> Segmentation network -> Tissue-segmentation map -> Classification network -> Referral/Diagnosis output.",
      "attrs": null,
      "subkind": "process",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "04755db0-8785-4314-a9af-245b85dedbe9",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.45,
        "w": 0.45,
        "x": 0.02,
        "y": 0.28
      },
      "kind": "list",
      "text": "At first, a segmentation network uses a 3D U-Net architecture to create a “tissue map” of the eye from a 3D digital optical computed tomography scan. This map paints the eye’s structure according to expert ophthalmologists.\nA second classification network operates on this tissue map to predict the severity of the condition.\nThis system achieves expert performance on referral decisions. It can also be easily adapted to various imaging machines by only retraining the segmentation network.",
      "attrs": null,
      "subkind": "bullet",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "9f30ac07-01eb-42eb-98d2-e8182fb36987",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": null,
      "kind": "metric",
      "text": "Error rate",
      "attrs": null,
      "subkind": "primary",
      "toolName": "Quantification",
      "toolSlug": "quantification",
      "confidence": null,
      "componentId": "019dd952-41ab-72d9-bbc4-295ed47677df",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.04,
        "w": 0.95,
        "x": 0.02,
        "y": 0.22
      },
      "kind": "title",
      "text": "Expert-level diagnosis and treatment referral suggestions is achieved using a two-stage deep learning approach.",
      "attrs": null,
      "subkind": "action-title",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "ae6e1bac-c7c8-4777-9d63-d5482f0f5d4a",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.04,
        "w": 0.45,
        "x": 0.02,
        "y": 0.14
      },
      "kind": "title",
      "text": "Deep learning in medicine: Diagnosing eye disease",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "c3d90b84-cca7-48a0-b5e3-61e0dbae18ef",
      "frameworkName": null,
      "frameworkSlug": null
    }
  ],
  "metrics": [],
  "tools": [
    {
      "name": "Action Titles",
      "slug": "action-titles",
      "agent": "Architect",
      "layer": "slide",
      "matchId": "019dd95a-0fd5-7148-8ecc-e0b3db61d125",
      "evidence": "Title states 'expert-level diagnosis' as the insight.",
      "confidence": 80
    }
  ],
  "frameworks": [
    {
      "name": "process",
      "slug": null,
      "matchId": "1086acf9-6087-41c7-bf81-f4b5c6b8124b",
      "evidence": "The slide describes a two-stage deep learning pipeline as a sequential process.",
      "confidence": 0.8
    }
  ],
  "arcBeats": [
    {
      "to": 92,
      "from": 5,
      "beatId": "019dd95a-0682-776c-8e34-ce57e5bbe574",
      "arcName": "The Triple Take",
      "arcSlug": "triple-take",
      "beatName": "The Facts (What)",
      "beatSlug": "triple-take-the-facts-what",
      "evidence": "Definitions through Research/Talent/Industry — fact-dense case studies and benchmarks.",
      "position": 1,
      "confidence": 70,
      "parentBeatName": "Setup",
      "parentBeatSlug": "setup"
    },
    {
      "to": 92,
      "from": 9,
      "beatId": "019dd95a-0682-776c-8e34-ddbccb391af1",
      "arcName": "Voyage and Return",
      "arcSlug": "voyage-return",
      "beatName": "The Unknown",
      "beatSlug": "voyage-return-the-unknown",
      "evidence": "Research/Talent/Industry frontiers explored.",
      "position": 2,
      "confidence": 45,
      "parentBeatName": "Complication",
      "parentBeatSlug": "complication"
    }
  ],
  "loops": [
    {
      "to": 33,
      "from": 28,
      "name": "Pattern Hunter",
      "slug": "02-pattern-hunter",
      "bestFor": "Time-pressed audiences, building consensus, when data is strong",
      "matchId": "019dd95a-07fe-70ce-8d3c-a49628ab8218",
      "evidence": "Six contiguous medical AI case studies with quantitative outcomes (0.97 AUC, 73%, 80%).",
      "position": 5,
      "objective": "Compile clinical-grade ML wins across imaging, cardiology, neuro and chemistry",
      "structure": "Evidence A -> Evidence B -> Evidence C -> Pattern/Conclusion",
      "confidence": 75,
      "description": "Group multiple pieces of evidence that together point to a pattern or conclusion"
    }
  ],
  "imagePathAlt": null,
  "thumbSrc": null,
  "thumbSrcAlt": null,
  "locked": true
}