{
  "docId": "019dd923-5ca1-7489-b638-e91d3b8478cc",
  "docSlug": "9fbedbfea0231cbe",
  "documentTitle": "AI Healthcare Errors",
  "authorId": "McKinsey",
  "authorName": "McKinsey",
  "documentKindSlug": "consulting-deck",
  "documentKindLabel": "Consulting deck",
  "sourceTypeSlug": "strategy_consulting",
  "sourceTypeLabel": "Strategy consulting",
  "presentationDate": null,
  "orientation": "landscape",
  "aspectRatio": 1.333,
  "pageNumber": 14,
  "pageCount": 26,
  "prevPage": 13,
  "nextPage": 15,
  "slideType": "diagnosis",
  "function": "diagnose",
  "density": "overcrowded",
  "nDataPoints": 5,
  "notes": "The slide uses a bar chart to compare AUC scores across three different modeling techniques.",
  "elementsJson": [
    "headline_text",
    "bullet_list",
    "photo",
    "bar_chart_vertical",
    "footnote"
  ],
  "metadataConfidence": 1,
  "imagePath": null,
  "slideHref": "/slides/019dd923-5ca1-7489-b638-e91d3b8478cc/14",
  "deckHref": "/decks/019dd923-5ca1-7489-b638-e91d3b8478cc",
  "deckJsonHref": "/decks/019dd923-5ca1-7489-b638-e91d3b8478cc.json",
  "deckAnchorHref": "/decks/019dd923-5ca1-7489-b638-e91d3b8478cc#slide-14",
  "components": [
    {
      "bbox": null,
      "kind": "callout",
      "text": "The model can help target costly therapies to patients with the most urgent need, guide the intensity of clinical monitoring required, and provide prognostic information to patients.",
      "attrs": null,
      "subkind": null,
      "toolName": "Visual emphasis",
      "toolSlug": "visual-emphasis",
      "confidence": null,
      "componentId": "019dd951-d3bc-73c4-a2ba-8e9af7b63416",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.25,
        "w": 0.55,
        "x": 0.03,
        "y": 0.65
      },
      "kind": "chart",
      "text": "AUC scores for Linear regression (0.78), Random forest (0.79), and Boosting (0.79).",
      "attrs": null,
      "subkind": "bar-vertical",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "348b00d3-bc06-430f-8414-ccf8434cf08e",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.4,
        "w": 0.45,
        "x": 0.52,
        "y": 0.15
      },
      "kind": "image",
      "text": "Anatomical illustration of liver and Hepatitis C virus structure.",
      "attrs": null,
      "subkind": "illustration",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "0375ad11-dcd9-4f78-ad81-2502558cf402",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.2,
        "w": 0.35,
        "x": 0.62,
        "y": 0.65
      },
      "kind": "list",
      "text": "94% negative predictive value. p <0.0001 probability that longitudinal predictive model is superior to baseline.",
      "attrs": null,
      "subkind": "bullet",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "6531652d-20e7-435b-a0c4-6664c8aa9f72",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.4,
        "w": 0.45,
        "x": 0.03,
        "y": 0.18
      },
      "kind": "list",
      "text": "Prediction models that incorporate longitudinal clinical data can capture non-linear disease progression in chronic hepatitis C. The approach uses two outcomes measures and a range of predictive variables. The model was constructed using logistic regression, random forest, and boosting. The model can help target costly therapies.",
      "attrs": null,
      "subkind": "bullet",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "f71ed01a-cbf0-4470-bb96-bc2782bd69af",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": null,
      "kind": "metric",
      "text": "AUC: 0.79",
      "attrs": null,
      "subkind": "primary",
      "toolName": "Quantification",
      "toolSlug": "quantification",
      "confidence": null,
      "componentId": "019dd951-d3bc-73c4-a2ba-93d81f6ce67c",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.05,
        "w": 0.95,
        "x": 0.03,
        "y": 0.95
      },
      "kind": "source-note",
      "text": "1 Standard statistical measure of diagnostic accuracy. SOURCE: Konerman M et al, Improvement of predictive models of risk of disease progression in chronic hepatitis C by incorporating longitudinal data, 2015, Hepatology, 61, 1832-1841",
      "attrs": {
        "numbered": true
      },
      "subkind": null,
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "e38ae371-403c-4d5b-b928-06c3eb4e7220",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.05,
        "w": 0.8,
        "x": 0.03,
        "y": 0.03
      },
      "kind": "title",
      "text": "Machine learning models predict patients at risk of Hep C progression",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "6a0fa691-cc4f-4af7-a1c7-7c3a316b6955",
      "frameworkName": null,
      "frameworkSlug": null
    }
  ],
  "metrics": [
    {
      "metricRaw": "AUC",
      "numberRaw": "0.79",
      "numberKind": "plain",
      "actionTitle": "Machine learning models predict patients at risk of Hep C progression",
      "calloutText": "The model can help target costly therapies to patients with the most urgent need, guide the intensity of clinical monitoring required, and provide prognostic information to patients.",
      "numberScale": null,
      "numberValue": 0.79,
      "metricFamily": "other",
      "numberCurrency": null
    }
  ],
  "tools": [
    {
      "name": "Audience Definition",
      "slug": "audience-definition",
      "agent": "Storyteller",
      "layer": "slide",
      "matchId": "6d015149-53ef-40f4-bd90-aceb0e234502",
      "evidence": "Prediction models that incorporate longitudinal clinical data can capture non-linear disease progression in chronic hepatitis C.",
      "confidence": 0.7
    },
    {
      "name": "Chart Selection Guide",
      "slug": "chart-selection-guide",
      "agent": "Designer",
      "layer": "slide",
      "matchId": "5b0eabaa-4655-4795-af72-1438890f01f0",
      "evidence": "AUC scores for Linear regression (0.78), Random forest (0.79), and Boosting (0.79).",
      "confidence": 0.6
    }
  ],
  "frameworks": [],
  "arcBeats": [
    {
      "to": 26,
      "from": 10,
      "beatId": "9b6e4ffe-95ca-40d4-92d5-70f2cd8f60f8",
      "arcName": "Problem-Agitate-Solution",
      "arcSlug": "problem-agitate-solution",
      "beatName": "Solution (Provide relief)",
      "beatSlug": "problem-agitate-solution-solution-provide-relief",
      "evidence": "The deck offers AI as a solution to prevent healthcare errors and improve patient outcomes.",
      "position": 2,
      "confidence": 0.8,
      "parentBeatName": "Resolution",
      "parentBeatSlug": "resolution"
    }
  ],
  "loops": [
    {
      "to": 14,
      "from": 4,
      "name": "Golden Circle",
      "slug": "11-golden-circle",
      "bestFor": "Visionary leadership, brand positioning, mission statements",
      "matchId": "1b36e03c-871f-4ba9-977e-2461066df8bf",
      "evidence": "The deck presents various case studies and examples of AI applications in healthcare, using the golden circle framework.",
      "position": 1,
      "objective": "Explain why AI is different and how it can be applied in healthcare",
      "structure": "The Why (Belief) -> The How (Process) -> The What (Result)",
      "confidence": 0.6,
      "description": "Invert the typical pitch by starting with why you exist, rather than what you do"
    }
  ],
  "imagePathAlt": null,
  "thumbSrc": null,
  "thumbSrcAlt": null,
  "locked": true
}