Dataset Information

Visual analytics for concept exploration in subspaces of patient groups : Making sense of complex datasets with the Doctor-in-the-loop.

ABSTRACT: Medical doctors and researchers in bio-medicine are increasingly confronted with complex patient data, posing new and difficult analysis challenges. These data are often comprising high-dimensional descriptions of patient conditions and measurements on the success of certain therapies. An important analysis question in such data is to compare and correlate patient conditions and therapy results along with combinations of dimensions. As the number of dimensions is often very large, one needs to map them to a smaller number of relevant dimensions to be more amenable for expert analysis. This is because irrelevant, redundant, and conflicting dimensions can negatively affect effectiveness and efficiency of the analytic process (the so-called curse of dimensionality). However, the possible mappings from high- to low-dimensional spaces are ambiguous. For example, the similarity between patients may change by considering different combinations of relevant dimensions (subspaces). We demonstrate the potential of subspace analysis for the interpretation of high-dimensional medical data. Specifically, we present SubVIS, an interactive tool to visually explore subspace clusters from different perspectives, introduce a novel analysis workflow, and discuss future directions for high-dimensional (medical) data analysis and its visual exploration. We apply the presented workflow to a real-world dataset from the medical domain and show its usefulness with a domain expert evaluation.

SUBMITTER: Hund M

PROVIDER: S-EPMC5106406 | biostudies-literature | 2016 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Visual analytics for concept exploration in subspaces of patient groups : Making sense of complex datasets with the Doctor-in-the-loop.

Hund Michael M Böhm Dominic D Sturm Werner W Sedlmair Michael M Schreck Tobias T Ullrich Torsten T Keim Daniel A DA Majnaric Ljiljana L Holzinger Andreas A

Brain informatics 20160321 4

Medical doctors and researchers in bio-medicine are increasingly confronted with complex patient data, posing new and difficult analysis challenges. These data are often comprising high-dimensional descriptions of patient conditions and measurements on the success of certain therapies. An important analysis question in such data is to compare and correlate patient conditions and therapy results along with combinations of dimensions. As the number of dimensions is often very large, one needs to m ...[more]

PMID: 27747817

Similar Datasets

Project description:BACKGROUND:Homeless people have poor health and mortality indices. Despite this they make poor usage of health services. This study sought to understand why they use health services differently from the domiciled population. METHODS:Ethnographic observations were conducted at several homeless services, in Dublin. This was supplemented with 47 semi-structured interviews with homeless people and two focus groups of homeless people and hospital doctors. A critical-realist approach was adopted for interpretation of the data. RESULTS:Homeless people tended to present late in their illness; default early from treatment; have low usage of primary-care, preventative and outpatient services; have high usage of Emergency and Inpatient services; and poor compliance with medication. They tended to avoid psychiatric services. A number of external barriers were identified. These were classified as physical (distance) administrative (application process for medical care; appointments; queues; the management of addiction in hospital; rules of service; and information providing processes); and attitudinal (stigma; differing attitudes as to appropriate use of services. A new form of barrier, Conversations of Exclusion was identified and described. Internalised barriers were identified which were in nature, either cognitive (fatalistic, denial, deferral to future, presumption of poor treatment or discrimination, self blame and survival cognitions) or emotional (fear; embarrassment, hopelessness and poor self-esteem). Generative mechanisms for these factors were identified which either affected participants prior to homelessness (marginalization causing hopelessness, familial dysfunction, substance misuse, fear of authority, illiteracy; mental health; and poor English) or after becoming homeless (homelessness; ubiquity of premature death; substance misuse; prioritization of survival over health; threat of violence; chaotic nature of homelessness; negative experiences of authority; and stigma. CONCLUSIONS:An explanatory critical realist model integrating the identified generative mechanisms, external and internalised barriers was developed to explain why the Health service Utilization of homeless people differs from the domiciled populations. This new model has implications for health service policy makers and providers in how they design and deliver accessible health services to homeless people.

Project description:ObjectiveTo explore the acceptability of peer mentoring for people with a traumatic brain injury (TBI) in New Zealand.DesignThis is a qualitative descriptive study exploring the experiences reported by mentees and mentors taking part in a feasibility study of peer mentoring. Interviews with five mentees and six mentors were carried out. Data were analysed using conventional content analysis.SettingThe first mentoring session took place predischarge from the rehabilitation unit. The remaining five sessions took place in mentees' homes or community as preferred.ParticipantsTwelve people with TBI took part: six mentees (with moderate to severe TBI; aged 18-46) paired with six mentors (moderate to severe TBI >12 months previously; aged 21-59). Pairing occurred before mentee discharge from postacute inpatient brain injury rehabilitation. Mentors had been discharged from rehabilitation following a TBI between 1 and 5 years previously.InterventionThe peer mentoring programme consisted of up to six face-to-face sessions between a mentee and a mentor over a 6-month period. The sessions focused on building rapport, exploring hopes for and supporting participation after discharge through further meetings and supported community activities.ResultsData were synthesised into one overarching theme: making sense of recovery. This occurred through the sharing of experiences and stories; was pivotal to the mentoring relationship; and appeared to benefit both mentees and mentors. Mentors were perceived as valued experts because of their personal experience of injury and recovery, and could provide support in ways that were different from that provided by clinicians or family members. Mentors required support to manage the uncertainties inherent in the role.ConclusionsThe insight mentors developed through their own lived experience established them as a trusted and credible source of hope and support for people re-engaging in the community post-TBI. These findings indicate the potential for mentoring to result in positive outcomes.

Dataset Information

Visual analytics for concept exploration in subspaces of patient groups : Making sense of complex datasets with the Doctor-in-the-loop.

Publications

Visual analytics for concept exploration in subspaces of patient groups : Making sense of complex datasets with the Doctor-in-the-loop.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets