Personalized Treatment of Mental Health Problems using Adaptive Technology

List of PhD resources I want to share with the research community. I was associated with INTROMAT project, which holds a vision of improving public mental health with innovative technologies and psychological treatments. I was a PhD candidate hired by the INTROMAT team to research the use of adaptive technology for the personalized treatment of mental health issues including Depression, ADHD, Bipolar Disorder and Social Anxiety Disorder.

Course Work

Here are the lists of presentations given in different courses and during my Ph.D.

Introduction to Machine learning

https://www.uib.no/en/course/INF264

Model Driven Software Engineering

Research Ethics

Presentations

PDF: How can we model adaptive Internet Delivered psychological Treatment system, 13^th Jan, 2020. Solstrand Hotel & Bad
PDF: A GraphQL approach to Healthcare Information Exchange with HL7 FHIR, 5^th November, 2019. INSTITUTE PEDRO NUNES (IPN), R. Pedro Nunes 3030-199 Coimbra, Portugal.
PDF: Composing HL7 FHIR Resource Server, 24^th June, 2019. At Helse Vest IKT, Ibsensgate 104
pdf: An architecture design for self-reporting e-health system, 27^th May, 2019. At Montreal, QC, Canada
keynote: Personalized Treatment of mental Health problems using Voice, 20^th May, 2019. At Gailo, Bergen, Norway
keynote: Personalized Treatment of mental Health problems using Adaptive Technology, 8^th March, 2019. 148 Townsend Street, San Francisco

Papers

[Journal] Lamo Y, Mukhiya SK, Rabbi F, et al. "Towards adaptive technology in routine mental health care." DIGITAL HEALTH. 2022;8., 10.1177/2055207622112867.
[Journal] Mukhiya S, Lamo Y, Rabbi F. "A Reference Architecture for Data-Driven and Adaptive Internet-Delivered Psychological Treatment Systems: Software Architecture Development and Validation Study" JMIR Hum Factors 2022;9(2):e31029, 10.2196/31029.
[Journal] Nordby, Emilie S., Astri J. Lundervold, Robin MF Kenter, Frode Guribye, Suresh K. Mukhiya, and Tine Nordgreen. "The effect of SMS reminders on adherence in a self-guided Internet-delivered intervention for adults with ADHD." Frontiers in Digital Health: 67, https://doi.org/10.3389/fdgth.2022.821031.
[Journal] Nordgreen, Tine, et al. "Challenges and possible solutions in cross-disciplinary and cross-sectorial research teams within the domain of e-mental health." Journal of Enabling Technologies (2021).
[Journal] Mukhiya SK, Lamo Y. An HL7 FHIR and GraphQL approach for interoperability between heterogeneous Electronic Health Record systems. Health Informatics Journal. July 2021. doi:10.1177/14604582211043920
[Journal] Ahmed, U., Kumar Mukhiya, S., Lin, J. C.-W., Srivastava, G., & Lamo, Y. (2021). Attention-based Deep Entropy Active Learning using Lexical Algorithm for Mental Health Treatment. Frontiers in Psychology, 12, 471. https://doi.org/10.3389/FPSYG.2021.642347.
[Book chapter] S. Mukhiya, A. Aminifar, F. Rabbi, V. Pun, and Y. Lamo. Artificial Intelligence in Mental Health. Bentham Science Publishers LTD., pages 13–34, 2021.
[Journal] Mukhiya SK, Wake JD, Inal Y, Pun KI, Lamo Yngve, Adaptive Elements in Internet-Delivered Psychological Treatment Systems: Systematic Review, JMIR, doi: https://doi.org/10.2196/21066.
[Conference] Ahmed U., Lin J.CW., Wu J.MT., Djenouri Y., Srivastava G., Mukhiya S.K. (2020) Efficient Mining of Pareto-Front High Expected Utility Patterns. In: Fujita H., Fournier-Viger P., Ali M., Sasaki J. (eds) Trends in Artificial Intelligence Theory and Applications. Artificial Intelligence Practices. IEA/AIE 2020. Lecture Notes in Computer Science, vol 12144. Springer, Cham. https://doi.org/10.1007/978-3-030-55789-8_74
[Conference] Suresh Kumar Mukhiya, Usman Ahmed, Fazle Rabbi, Ka I Pun, & Yngve Lamo. Adaptation of IDPT System Based on Patient-Authored Text Data Using NLP.
[Journal] S. K. Mukhiya, J. D. Wake, Y. Inal and Y. Lamo, "Adaptive Systems for Internet-Delivered Psychological Treatments," in IEEE Access, doi: 10.1109/ACCESS.2020.3002793.
[Conference] Usman Ahmed, Jerry Chun-Wei Lin, Youcef Djenouri, Gautam Srivastava, and Suresh Kumar Mukhiya, Mining of the Non-dominated High Expected Utility Patterns from Uncertain Databases, 2020, Accepted in IEA/AIE 2020
[Book Chapter] Nordberg O.E. et al. (2020) Designing Chatbots for Guiding Online Peer Support Conversations for Adults with ADHD. In: Følstad A. et al. (eds) Chatbot Research and Design. CONVERSATIONS 2019. Lecture Notes in Computer Science, vol 11970. Springer, Cham
[Conference] Oda E. Nordberg, Suresh Kumar Mukhiya, Frode Guribye, Eivind Flobak, Robin Kenter, Daniel A. Jensen, Astri Lundervold, Tine Nordgreen . The design of a chatbot for guiding peer support chats between adults with ADHD , May 14, 2019 (https://www.norsrii.no/)
[Conference] Suresh Kumar Mukhiya, Fazle Rabbi, Violet Ka I Pun, Adrian Rutle, Yngve Lamo, A GraphQL approach to Healthcare Information Exchange with HL7 FHIR, Procedia Computer Science, Volume 160, 2019, Pages 338-345, ISSN 1877-0509, https://doi.org/10.1016/j.procs.2019.11.082. (http://www.sciencedirect.com/science/article/pii/S187705091931782X)
[Workshop] Suresh Kumar Mukhiya, Fazle Rabbi, Ka I Pun, and Yngve Lamo. 2019. An architectural design for self-reporting e-health systems. In Proceedings of the 1st International Workshop on Software Engineering for Healthcare (SEH ’19). IEEE Press, 1–8. DOI: https://doi.org/10.1109/SEH.2019.00008
[Journal Paper] Mukhiya, Suresh Kumar, & Hoang Hung, K. (2018). An Architectural Style for Single Page Scalable Modern Web Application, 5(4), 6–13, International Journal of Recent Research Aspects ISSN: 2349-7688, Vol. 5

Posters

Best poster award, 2019 An architecture for creating self-reporting ehealth systems

Tutorials

Blogs and News

SAGE

Experiments

This section outlines the background, methods and results of the experiments carried out during this study. Once the architecture was setup, and prototype was developed, we carried out experiment on local computer to keep result homogeneous.

Experimental environment

All the software application components were running on Predator Acer Triton 500 with 32 GB of RAM, 1 TB SDD, 2070 RTX GPU with Ubuntu Linux distribution. Mobile application was installed on Apple iPhone 7 Plus. All the communication happened over HTTPS.

Methods

This paper advocates a method for communicating between heterogeneous EHR systems. Communication over Internet involves HTTP requests and response that includes reading resources (Read), creating resources (Create), updating resources (Update), and deleting resources (Delete). To test those, we created following queries to test CRUD and measured their average response and throughput. The associated GraphQL queries for each of them are listed below:

Q1: Read all patients resource

query PatientList {
  PatientList {
    entry {
      resource {
        ...on Patient {
          id
          resourceType
          name { family }
        }
      }
    }
  }
}

Q2: Read a single patient resource

query Person {
    Patient(_id: "5dcaa7f02eb0b70e90761396"){
        name {
            use
            text
            family
        }
        birthDate
        gender
        active
        address {
            line
        }
    }
}

Q3: Read all Encounter resource

query EncounterList {
  EncounterList {
    entry {
      resource {
        ...on Encounter {
          id
          resourceType
          status
        }
      }
    }
  }
}

Q4: Read a single Encounter resource

query Encounter{
    
    Encounter(_id: "5dcd0b739f814f507c1cb86e"){
        id
        status
    }
}

Q5: Read all Location resource

query LocationList {
  LocationList {
    entry {
      resource {
        ...on Location {
          id
          resourceType
          status
        }
      }
    }
  }
}

Q6: Read a single Location resource

query Location{
    
    Location(_id: "5dcbfe529f0ecb264c1790ef"){
        id
        name
    }
    
}

Q7: Read all observations resource

query ObservationList {
  ObservationList {
    entry {
      resource {
        ...on Observation {
          id
          resourceType
        }
      }
    }
  }
}

Q8: Read a single observation resource

query Observation {
    Observation(_id: "5dcc0734d39e0045d82b6eae") {
        id
        status
    }
}

Q9: Create a patient resource

mutation PatientCreate {
  PatientCreate(resource: {
      resourceType: Patient
      name: [
        {
          use: "official",
          family: "Chalmers",
          given: [
            "Peter",
            "James"
          ]
        },
        {
          use: "usual",
          given: [
            "Jim"
          ]
        },
        {
          use: "maiden",
          family: "Windsor",
          given: [
            "Peter",
            "James"
          ],
          period: {
            end: "2002"
          }
        }
      ]
      gender: "male"
    contact: [
    {

      name: {
        text: "mr. F. de Hond"
      },
      telecom: [
        {
          system: "phone",
          value: "022-655 7654"
        },
        {
          system: "email",
          value: "[email protected]"
        },
        {
          system: "fax",
          value: "022-655 0998"
        }
      ],
      address: {
        line: [
          "West Wing, floor 5"
        ]
      }
    }
  ]
      telecom: [
      {
        use: "home"
      },
      {
        system: "phone",
        value: "(03) 5555 6473",
        use: "work",
        rank: "1"
      },
      {
        system: "phone",
        value: "(03) 3410 5613",
        use: "mobile",
        rank: "2"
      },
      {
        system: "phone",
        value: "(03) 5555 8834",
        use: "old",
        period: {
          end: "2014"
        }
      }
    ]
    active: true
      address: [
        {
          type: "postal"
          line: ["3300 Washtenaw Avenue, Suite 227"]
          city: "Ann Arbor"
          state: "MI"
          postalCode: "48104"
          country: "USA"
        }
      ],
    identifier: [
      {
        use: "usual",
        type: {
          coding: [
            {
              system: "http://terminology.hl7.org/CodeSystem/v2-0203",
              code: "MR"
            }
          ]
        },
        system: "urn:oid:1.2.36.146.595.217.0.1",
        value: "12345",
        period: {
          start: "2001-05-06"
        },
        assigner: {
          display: "Acme Healthcare"
        }
      }
    ],
    }
  ) {
    id
    resourceType
    name { family }
    address {
      id
      line
      type
    }
    identifier {
      use,
      assigner {
        display
      }
    }
    identifier {
      use,
      assigner {
        display
      }
    }
  }
}

Q10: Update an Encounter resource

mutation EncounterUpdate{
    EncounterUpdate( id: "5dcd0b739f814f507c1cb86e", resource: {
  resourceType: Encounter,
  status: "arrived",
  class: {
    system: "http://terminology.hl7.org/CodeSystem/v3-ActCode",
    code: "IMP",
    display: "inpatient encounter",
  },
  }
)
  {
    id
    status
  }
}

Q11: Delete an Encounter resource

mutation EncounterRemove{
    EncounterRemove( id: "60c75d3db794ab67ed828458"){
        
    id       
    }
}

Query by Mobile Client GraphQL based Resource Server (C1)
Query by Mobile Client to OpenMRS (C2)
Query by Mobile client to OpenMRS and then write to Resource Server (C3)

sureshhardiya / phd-resources Goto Github PK

phd-resources's Introduction