{
  "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": 32,
  "pageCount": 136,
  "prevPage": 31,
  "nextPage": 33,
  "slideType": "case_study",
  "function": "illustrate_case",
  "density": "overcrowded",
  "nDataPoints": 20,
  "notes": "The slide compares a neural network (uNN) against a Support Vector Machine (SVM) baseline in a medical brain-computer interface application.",
  "elementsJson": [
    "headline_text",
    "bullet_list",
    "data_table",
    "scatter_plot"
  ],
  "metadataConfidence": 1,
  "imagePath": null,
  "slideHref": "/slides/019dd923-5e88-73ef-bd5c-f6fdd8f57895/32",
  "deckHref": "/decks/019dd923-5e88-73ef-bd5c-f6fdd8f57895",
  "deckJsonHref": "/decks/019dd923-5e88-73ef-bd5c-f6fdd8f57895.json",
  "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5c-f6fdd8f57895#slide-32",
  "components": [
    {
      "bbox": null,
      "kind": "callout",
      "text": "The neural network approach was much more robust to failure than an SVM baseline.",
      "attrs": null,
      "subkind": null,
      "toolName": "Visual emphasis",
      "toolSlug": "visual-emphasis",
      "confidence": null,
      "componentId": "019dd952-41ab-72d9-bbc5-b66223d72a95",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.35,
        "w": 0.45,
        "x": 0.508,
        "y": 0.45
      },
      "kind": "chart",
      "text": "Accuracy (%) vs Days since end of initial training period",
      "attrs": null,
      "subkind": "line",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "0ff25648-a052-41a2-9e6c-73cc88471a35",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.6,
        "w": 0.45,
        "x": 0.02,
        "y": 0.28
      },
      "kind": "list",
      "text": "Researchers implanted a microelectrode in the hand and arm area of a tetraplegic patient's left primary motor cortex. They trained a neural network to predict the likely intended movements of the person's arm based on the raw intracranial voltage signals recorded from the patient's brain.\nThe patient could sustain high accuracy reanimation of his paralyzed forearm with functional electrical stimulation for over a year without the need of supervised updating (thus reducing daily setup time).\nThe neural network approach was much more robust to failure than an SVM baseline. It could also be updated to learn new actions with transfer learning.",
      "attrs": null,
      "subkind": "bullet",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "7688732c-6f31-45fd-bd2d-8846f1e95a24",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": null,
      "kind": "metric",
      "text": "Failure rate: 5.67%",
      "attrs": null,
      "subkind": "primary",
      "toolName": "Quantification",
      "toolSlug": "quantification",
      "confidence": null,
      "componentId": "019dd952-41ab-72d9-bbc5-bb34d76b616e",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.15,
        "w": 0.45,
        "x": 0.508,
        "y": 0.3
      },
      "kind": "table",
      "text": "Model | Index extension | Index flexion | Wrist extension | Wrist flexion | All\nSVM | 25.66% (39) | 31.61% (49) | 14.97% (22) | 15.75% (23) | 22.17% (133)\nuNN | 6.58% (10) | 6.45% (10) | 6.12% (9) | 3.42% (5) | 5.67% (34)",
      "attrs": null,
      "subkind": "data",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "7430ef9e-f77e-4684-b952-bfe82ea4e3cf",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.04,
        "w": 0.9,
        "x": 0.02,
        "y": 0.22
      },
      "kind": "title",
      "text": "Long-term reanimation of a tetraplegic patient's forearm with electrical stimulation and neural network decoder.",
      "attrs": null,
      "subkind": "action-title",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "7789cd87-d287-439a-b40c-15777b086ecc",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.05,
        "w": 0.9,
        "x": 0.02,
        "y": 0.14
      },
      "kind": "title",
      "text": "Deep learning in medicine: Neural networks can restore limb control for the disabled",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "ee3958af-d605-4a72-8009-06ad52102974",
      "frameworkName": null,
      "frameworkSlug": null
    }
  ],
  "metrics": [],
  "tools": [],
  "frameworks": [],
  "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
}