Deloitte Case Competition final

21
Case Competition 2015 Amazon Cloud Service based Infectious Disease Detection and Predictability Algorithm. Group: A. Chang, D. Jacob, A. Moawad, H. O’Byrne, K. Wright 1

Transcript of Deloitte Case Competition final

Page 1: Deloitte Case Competition final

Case Competition 2015

Amazon Cloud Service based Infectious Disease Detection and Predictability Algorithm.

Group:

A. Chang, D. Jacob, A. Moawad, H. O’Byrne, K. Wright1

Page 2: Deloitte Case Competition final

Copyright © 2010 Deloitte Development LLC. All rights reserved.2 A. Chang, D. Jacob, A. Moawad, H. O’Byrne, K. Wright

Contents

Our Understanding of the Situation 3

Approach 5

The Solution 8

• Objectives

• Project schedule, budget, and delivery method

• Training, maintenance, and operations

• Future enhancements

Appendices 18

Page 3: Deloitte Case Competition final

Copyright © 2010 Deloitte Development LLC. All rights reserved.3 A. Chang, D. Jacob, A. Moawad, H. O’Byrne, K. Wright

Our Understanding of The Situation

Page 4: Deloitte Case Competition final

Copyright © 2010 Deloitte Development LLC. All rights reserved.4 A. Chang, D. Jacob, A. Moawad, H. O’Byrne, K. Wright

Our Understanding of the Situation

• The AIDC currently has a method of diagnosis that is “not intuitive and the hardware was bulky and difficult to handle at patient bedside.”

• This application collects data, which is then sent to a central database.

• We hope to implement a more efficient and secure analytics platform capable of:

‒ Logging patient symptoms and other information.

‒ Diagnosing infectious diseases efficiently and accurately.

‒ Predicting the development of disease in surrounding areas.

Page 5: Deloitte Case Competition final

Copyright © 2010 Deloitte Development LLC. All rights reserved.5 A. Chang, D. Jacob, A. Moawad, H. O’Byrne, K. Wright

Our Approach

Page 6: Deloitte Case Competition final

Copyright © 2010 Deloitte Development LLC. All rights reserved.6 A. Chang, D. Jacob, A. Moawad, H. O’Byrne, K. Wright

Our Approach: Two-Pronged

Improve Existing Technologies• More Intuitive User Experience• Compact Devices

‒ Tablets for staff• More Efficient Telecommunication

‒ Cloud Storage‒ Upgrade Hospital Servers/Devices

Establish Global Network• Via Cloud Services

• Secured Access granted to AIDC, other hospitals

• Storage for past, current and future medical records

• Mobile Interface for On-site Responders• Real-time

communication/feedback• Prompts faster treatment

plans

Page 7: Deloitte Case Competition final

Copyright © 2010 Deloitte Development LLC. All rights reserved.7 A. Chang, D. Jacob, A. Moawad, H. O’Byrne, K. Wright

Our Solution

Page 8: Deloitte Case Competition final

Copyright © 2010 Deloitte Development LLC. All rights reserved.8 A. Chang, D. Jacob, A. Moawad, H. O’Byrne, K. Wright

The Solution Objectives

• Quick and efficient bedside manner ‒User Friendly Interface‒Data Integration

• Disease Determination‒Diagnostic Tool

• More Effective Treatment‒Predictability Models‒Reference Library

Page 9: Deloitte Case Competition final

Copyright © 2010 Deloitte Development LLC. All rights reserved.9 A. Chang, D. Jacob, A. Moawad, H. O’Byrne, K. Wright

The Solution Huffman Trees

Diagnosis

• Input: Patient information– Each node of tree contains ranges of

symptoms – Each symptom has weight that contribute

to probability that patient has Ebola

• Output: Probability Patient has Ebola

– Boolean variable of each symptom

– Count symptoms: integer that counts the number of symptoms of patient that correlate to Ebola

– Cross-references to other patients

Prediction

• Origin: time when symptoms began– New permanent residence– Extensive stay ( >6 months)– Short term stay ( < 6 months)

• Each node contains:– Location– Date of residence/travels

• Output: Visual of spread of Ebola based on:

– Population density

– Patient’s time spent at location

– Can be combined with other patient inputs

Page 10: Deloitte Case Competition final

Copyright © 2010 Deloitte Development LLC. All rights reserved.10 A. Chang, D. Jacob, A. Moawad, H. O’Byrne, K. Wright

Patients

Symptoms logged

On-site Personnel

MDs/ EMTs

Cloud Storage

Allows access to past/current dataTies together network

Prediction Models

Live FeedbackAlerts to trendsDiagnosis

Data collected forCloudPrediction Models

Mobile AppLocal Servers

Can be updated before the cloud or in case cloud is unavailable

Disease Centres

AIDCCan alert other regions if threats are detected

Regional MDs

Other MDs can receive the data alerts from AIDC

The Solution Information Flow/Delivery method

Page 11: Deloitte Case Competition final

Copyright © 2010 Deloitte Development LLC. All rights reserved.11 A. Chang, D. Jacob, A. Moawad, H. O’Byrne, K. Wright

The SolutionBudget

Tablets

Amazon Web Services

Total

Asus Google Nexus 7• Tablet Price: $149.99• Cost of 750 Tablets: $299,992.50

All Ebola Cases• 0.078 TB Data Transfer In/Out Yearly Price: $68.04All of Africa• 300 TB Data Transfer In/Out Yearly Price: $246,145.68Amazon Support• Yearly Price: $180,068

Yearly Cost• Including enough memory for all Ebola cases: $300,060.54• Including enough memory for all of Africa: $546,138.18

Page 12: Deloitte Case Competition final

Copyright © 2010 Deloitte Development LLC. All rights reserved.12 A. Chang, D. Jacob, A. Moawad, H. O’Byrne, K. Wright

Month1 2 3 4 5 6 7 8 9 10 11 12

App R&D

• Data Collection

• Algorithm

Coding

• Debugging

β Testing

• Pilot

• Debugging

Expanding

Operation

• Marketing

• Deployment

• Disease

Management

Maintenance

• Updates

The Solution Project Schedule

Page 13: Deloitte Case Competition final

Copyright © 2010 Deloitte Development LLC. All rights reserved.13 A. Chang, D. Jacob, A. Moawad, H. O’Byrne, K. Wright

The Solution Training, Operations, and Maintenance

Training

• Doctors in infected countries will be taught:– How to use app:

• Create, record, and search patient information

– How to store/upload data• On both hospital

servers and cloud storage

– Downloading and installing app updates/fixes

Maintenance

• App Maintenance– Updated app versions to

response to errors/crashes/bugs

• Cloud storage maintenance

Operations

• Doctors collecting data in the field and treating patients

• Cloud storage that holds data for all patients and uses data to track spread of disease

• HQ and other US AIDC locations that maintain app and use analyzed data to stop spread of disease

Page 14: Deloitte Case Competition final

Copyright © 2010 Deloitte Development LLC. All rights reserved.14 A. Chang, D. Jacob, A. Moawad, H. O’Byrne, K. Wright

The Solution SWOT Analysis

Strengths Weaknesses

• Easy to use • Surplus of data storage• Affordable• Efficient

• Doctors require training• App may not handle beta

testing• Availability of internet

connection

Opportunities Threats

• User feedback system• Expansion to diagnose and

predict other infectious diseases

• Budget allows for expansion

• Cloud storage provider may not handle data influx

• Infringement of confidentiality• Constant data flow

Page 15: Deloitte Case Competition final

Copyright © 2010 Deloitte Development LLC. All rights reserved.15 A. Chang, D. Jacob, A. Moawad, H. O’Byrne, K. Wright

The Solution Future Enhancements

• Expansion of data library

• Augmented prediction models

‒Environmental factors

‒Genetic factors

‒ Increased computational power

• Expanding global network

Page 16: Deloitte Case Competition final

Copyright © 2010 Deloitte Development LLC. All rights reserved.16 A. Chang, D. Jacob, A. Moawad, H. O’Byrne, K. Wright

Questions?

Page 17: Deloitte Case Competition final

Copyright © 2010 Deloitte Development LLC. All rights reserved.17 A. Chang, D. Jacob, A. Moawad, H. O’Byrne, K. Wright

Appendices

Page 18: Deloitte Case Competition final

Copyright © 2010 Deloitte Development LLC. All rights reserved.18 A. Chang, D. Jacob, A. Moawad, H. O’Byrne, K. Wright

Appendix A Diagnosis Huffman Tree

Temperature

Origin

Symptom 2

Reaches this node with 98-100 F temperature

Symptom 3

Reaches this node at a certain range

Symptom 3

Reaches this node at a certain rangeReaches this node at a

certain range

Symptom 3

Symptom 2

Reaches this node with 100-102 F temperature

Symptom 4

Reaches this node at a certain range

Symptom 4

Reaches this node at a certain range

Symptom 4

Reaches this node at a certain range

Symptom 4

Reaches this node at a certain range

Symptom 4

Reaches this node at a certain range

Symptom 2

Reaches this node with 96-98 F temperature

Page 19: Deloitte Case Competition final

Copyright © 2010 Deloitte Development LLC. All rights reserved.19 A. Chang, D. Jacob, A. Moawad, H. O’Byrne, K. Wright

Appendix B Prediction Huffman Tree

Place 1

Origin

Type 1 Place

DatePeriod of timeDensity of population

Type 0 Place

DatePeriod of timeDensity of population

Type 2 Place

DatePeriod of timeDensity of population

DatePeriod of timeDensity of population

Type 1 Place

Type 2 Place

DatePeriod of timeDensity of population

Type 0 Place

DatePeriod of timeDensity of population

Type 1 Place

DatePeriod of timeDensity of population

Type 2 Place

DatePeriod of timeDensity of population

Type 0 Place

DatePeriod of timeDensity of population

Time

Page 20: Deloitte Case Competition final

Copyright © 2010 Deloitte Development LLC. All rights reserved.

Asus Google Nexus 7 Specifications

Operating SystemAndroidTM 4.1Display7" WXGA (1280x800) Screen

IPS Panel10 finger multi-touch support

CPUNVIDIA® Tegra® 3 T30L Quad-Core @1.2GhzMemory1GBStorage16GB*1Wireless Data NetworkWLAN 802.11 b/g/[email protected]

BluetoothCamera1.2 MP Front CameraInterface2-in-1 Audio Jack (head-out/MIC),

1x micro-USB, 2x Digital microphone,2x High Quality Speakers,1x Docking PIN

SensorG-Sensor, Light Sensor, Gyroscope,E-compass, GPS, NFC, Hall Sensor

Battery9.5 hours, 4325mAh,*216Wh Li-polymer

Dimensions198.5 x 120 x 10.45 mmWeight340 g

20 A. Chang, D. Jacob, A. Moawad, H. O’Byrne, K. Wright

Page 21: Deloitte Case Competition final

Copyright © 2010 Deloitte Development LLC. All rights reserved.

Deloitte refers to one or more of Deloitte Touche Tohmatsu Limited, a UK private company limited by guarantee, and its network of member firms, each of which is a legally separate and independent entity.  Please see www.deloitte.com/about for a detailed description of the legal structure of Deloitte Touche Tohmatsu Limited and its member firms.

Deloitte provides audit, tax, consulting, and financial advisory services to public and private clients spanning multiple industries. With a globally connected network of member firms in more than 140 countries, Deloitte brings world-class capabilities and deep local expertise to help clients succeed wherever they operate. Deloitte's approximately 169,000 professionals are committed to becoming the standard of excellence.

This publication contains general information only, and none of Deloitte Touche Tohmatsu Limited, Deloitte Global Services Limited, Deloitte Global Services Holdings Limited, the Deloitte Touche Tohmatsu Verein, any of  their member firms, or any of the foregoing’s affiliates (collectively the “Deloitte Network”) are, by means of this publication, rendering accounting, business, financial, investment, legal, tax, or other professional advice or services. This publication is not a substitute for such professional advice or services, nor should it be used as a basis for any decision or action that may affect your finances or your business. Before making any decision or taking any action that may affect your finances or your business, you should consult a qualified professional adviser. No entity in the Deloitte Network shall be responsible for any loss whatsoever sustained by any person who relies on this publication.

A. Chang, D. Jacob, A. Moawad, H. O’Byrne, K. Wright21