scholarly journals Artificial Intelligence Support for Skin Lesion Triage in Primary Care and Dermatology (Preprint)

2021 ◽  
Author(s):  
Harmony Thompson ◽  
Amanda Oakley ◽  
Michael B Jameson ◽  
Adrian Bowling
Keyword(s):  
Artificial Intelligence ◽  
Primary Care ◽  
Health Care ◽  
Skin Cancer ◽  
Sensitivity And Specificity ◽  
Health Care Access ◽  
Real Life ◽  
Primary Care Providers ◽  
Skin Lesions ◽  
Care Providers

BACKGROUND Primary care providers, dermatology specialists, and health care access are key components of primary prevention, early diagnosis, and treatment of skin cancer. Artificial intelligence (AI) offers the promise of diagnostic support for nonspecialists, but real-world clinical validation of AI in primary care is lacking. OBJECTIVE We aimed to (1) assess the reliability of an AI-based clinical triage algorithm in classifying benign and malignant skin lesions and (2) evaluate the quality of images obtained in primary care using the study camera (3Gen DermLite Cam v4 or similar). METHODS This was a single-center, prospective, double-blinded observational study with a predetermined study design. We recruited participants with suspected skin cancer in 20 primary care practices who were referred for assessment via teledermatology. A second set of photographs taken using a standardized camera was processed by the AI algorithm. We evaluated the image quality and compared two teledermatologists’ diagnoses by consensus (the “gold standard”) with AI and histology where applicable. RESULTS Our primary outcome assessment stratified 391 skin lesions by management as benign, uncertain, or malignant. Uncertain lesions were not included in the sensitivity and specificity analyses. Uncertain lesions included lesions that had either diagnostic or management uncertainties. For the remaining 242 lesions, the sensitivity was 97.26% (95% CI 93.13%-99.25%) and the specificity was 97.92% (95% CI 92.68%-99.75%). The AI algorithm was compared with the histological diagnoses for 123 lesions. The sensitivity was 100% (95% CI 95.85%-100%) and the specificity was 72.22% (95% CI 54.81%-85.80%). CONCLUSIONS The AI algorithm demonstrates encouraging results, with high sensitivity and specificity, concordant with previous AI studies. It shows potential as a triage tool in conjunction with teledermatology to augment health care and improve access to dermatology. Further real-life studies need to be conducted on a larger scale to assess the reliability, usability, and cost-effectiveness of the algorithm in primary care.

scholarly journals Artificial Intelligence Support for Skin Lesion Triage in Primary Care and Dermatology

Iproceedings ◽  
10.2196/35395 ◽  
2021 ◽  
Vol 6 (1) ◽  
pp. e35395
Author(s):  
Harmony Thompson ◽  
Amanda Oakley ◽  
Michael B Jameson ◽  
Adrian Bowling
Keyword(s):  
Artificial Intelligence ◽  
Primary Care ◽  
Health Care ◽  
Skin Cancer ◽  
Sensitivity And Specificity ◽  
Conflicts Of Interest ◽  
Real Life ◽  
Primary Care Providers ◽  
Skin Lesions ◽  
Care Providers

Background Primary care providers, dermatology specialists, and health care access are key components of primary prevention, early diagnosis, and treatment of skin cancer. Artificial intelligence (AI) offers the promise of diagnostic support for nonspecialists, but real-world clinical validation of AI in primary care is lacking. Objective We aimed to (1) assess the reliability of an AI-based clinical triage algorithm in classifying benign and malignant skin lesions and (2) evaluate the quality of images obtained in primary care using the study camera (3Gen DermLite Cam v4 or similar). Methods This was a single-center, prospective, double-blinded observational study with a predetermined study design. We recruited participants with suspected skin cancer in 20 primary care practices who were referred for assessment via teledermatology. A second set of photographs taken using a standardized camera was processed by the AI algorithm. We evaluated the image quality and compared two teledermatologists’ diagnoses by consensus (the “gold standard”) with AI and histology where applicable. Results Our primary outcome assessment stratified 391 skin lesions by management as benign, uncertain, or malignant. Uncertain lesions were not included in the sensitivity and specificity analyses. Uncertain lesions included lesions that had either diagnostic or management uncertainties. For the remaining 242 lesions, the sensitivity was 97.26% (95% CI 93.13%-99.25%) and the specificity was 97.92% (95% CI 92.68%-99.75%). The AI algorithm was compared with the histological diagnoses for 123 lesions. The sensitivity was 100% (95% CI 95.85%-100%) and the specificity was 72.22% (95% CI 54.81%-85.80%). Conclusions The AI algorithm demonstrates encouraging results, with high sensitivity and specificity, concordant with previous AI studies. It shows potential as a triage tool in conjunction with teledermatology to augment health care and improve access to dermatology. Further real-life studies need to be conducted on a larger scale to assess the reliability, usability, and cost-effectiveness of the algorithm in primary care. Acknowledgments MoleMap NZ, who developed the AI algorithm, provided some funding for this study. HT's salary was partially sponsored by MoleMap NZ, who developed the AI algorithm. AB is a shareholder and consultant to Molemap Ltd provider of the AI algorithm. Conflicts of Interest None declared.

Primer on Depression

Depression ◽  
2019 ◽  
pp. 459-474
Author(s):  
Robert S. Kinney ◽  
Radu Pop
Keyword(s):  
Primary Care ◽  
Health Care ◽  
Health Care Access ◽  
Primary Care Providers ◽  
Depression Screening ◽  
Care Providers ◽  
Care Access ◽  
Measurement Based Care ◽  
New Guidelines ◽  
Guidelines And Recommendations

Depression is a commonly occurring illness in the general population. Existing systems for identifying and treating depression vary greatly, and the adoption of a universal, standardized method of addressing the disorder within primary care is lacking. New guidelines and recommendations by accrediting bodies have resulted in the development of some initiatives and the increased recognition of depression, yet treatments continue to rely on referrals to specialty psychiatric care providers. Given that primary care may be the only point of health care access for many individuals, this serves as an opportune setting to initiate treatment at the time that depression screening is completed. With adequate support, guidance, and a systemic approach (i.e., measurement-based care), primary care providers can be as effective as psychiatric specialty care in treating depression. This chapter providers evidence for this approach, along with direct recommendations to primary care providers.

scholarly journals The expectations of transgender people in the face of their health-care access difficulties and how they can be overcome. A qualitative study in France

2020 ◽  
Vol 21 ◽  
Author(s):  
Emmanuel Allory ◽  
Ellie Duval ◽  
Marion Caroff ◽  
Candan Kendir ◽  
Raphaël Magnan ◽  
...  
Keyword(s):  
Primary Care ◽  
Health Care ◽  
Primary Health Care ◽  
Health Care Access ◽  
Primary Care Providers ◽  
Care Providers ◽  
Transgender People ◽  
Care Access ◽  
Care Services ◽  
Primary Health

Abstract Aim: Our objective was to explore the difficulties experienced by transgender people in accessing primary health-care services and their expectations towards primary care providers to improve their health-care access. Background: Because transgender people are exposed to many discriminations, their health-care access is particularly poor. Guidelines recommend greater involvement of primary care providers in the processes because of the accessibility feature of primary care services. Methods: A qualitative study using semi-directed interviews was conducted among 27 transgender people (February 2018 – August 2018). These voluntary participants were recruited through different means: local trans or LGBTI (lesbian, gay, bisexual, trans, and/or intersex) associations, primary care providers, and social networks. The data analysis was based on reflexive thematic analysis in an inductive approach. Findings: Difficulties in accessing health-care occurred at all the levels of the primary health-care system: primary care providers – transgender people interaction, access to the primary care team facility (starting with the secretariat), access to secondary care specialists, and continuity of care. Transgender people report ill-adapted health-care services as a result of gender-based identification in health-care settings. Their main expectation was depsychiatrization and self-determination. They supported mixed health network comprising primary care providers and transgender people with a coordinating role for the general practitioner. These expectations should be priorities to consider in our primary health-care system to improve access to health-care for transgender people.

754 Insomnia and Depression Symptoms in Primary Care Patients Referred for Mental Health Care

SLEEP ◽  
2021 ◽  
Vol 44 (Supplement_2) ◽  
pp. A294-A294
Author(s):  
Ivan Vargas ◽  
Alexandria Muench ◽  
Mark Seewald ◽  
Cecilia Livesey ◽  
Matthew Press ◽  
...  
Keyword(s):  
Mental Health ◽  
Primary Care ◽  
Health Care ◽  
Mental Health Care ◽  
Primary Care Providers ◽  
Depression Symptoms ◽  
Care Providers ◽  
Mild Depression ◽  
Significant Depression ◽  
Clinically Significant

Abstract Introduction Past epidemiological research indicates that insomnia and depression are both highly prevalent and tend to co-occur in the general population. The present study further assesses this association by estimating: (1) the concurrence rates of insomnia and depression in outpatients referred by their primary care providers for mental health care; and (2) whether the association between depression and insomnia varies by insomnia subtype (initial, middle, and late). Methods Data were collected from 3,174 patients (mean age=42.7; 74% women; 50% Black) who were referred to the integrated care program for assessment of mental health symptoms (2018–2020). All patients completed an Insomnia Severity Index (ISI) and a Patient Health Questionnaire (PHQ-9) during their evaluations. Total scores for the ISI and PHQ-9 were computed. These scores were used to categorize patients into diagnostic groups for insomnia (no-insomnia [ISI < 8], subthreshold-insomnia [ISI 8–14], and clinically-significant-insomnia [ISI>14]) and depression (no-depression [PHQ-914]). Items 1–3 of the ISI were also used to assess the association between depression and subtypes of insomnia. Results Rates of insomnia were as follows: 34.6% for subthreshold-insomnia, 35.5% for clinically-significant insomnia, and 28.9% for mild-depression and 26.9% for clinically-significant-depression. 92% of patients with clinically significant depression reported at least subthreshold levels of insomnia. While the majority of patients with clinical depression reported having insomnia, the proportion of patients that endorsed these symptoms were comparable across insomnia subtypes (percent by subtype: initial insomnia 63%; middle insomnia 61%; late insomnia 59%). Conclusion According to these data, the proportion of outpatients referred for mental health evaluations that endorse treatable levels of insomnia is very high (approximately 70%). This naturally gives rise to at least two questions: how will such symptomatology be addressed (within primary or specialty care) and what affect might targeted treatment for insomnia have on health were it a focus of treatment in general? Support (if any) Vargas: K23HL141581; Perlis: K24AG055602

Introducing Shared Mental Health Care in Northwestern Ontario: An Analysis of Changing Referral Patterns of Primary Care Providers

2015 ◽  
Vol 34 (2) ◽  
pp. 63-72 ◽  
Author(s):  
Graham Gaylord ◽  
S. Kathleen Bailey ◽  
John M. Haggarty
Keyword(s):  
Mental Health ◽  
Primary Care ◽  
Health Care ◽  
Mental Health Services ◽  
Health Services ◽  
Mental Health Care ◽  
Community Mental Health Services ◽  
Primary Care Providers ◽  
Care Providers ◽  
Referral Patterns

This study describes a shared mental health care (SMHC) model introduced in Northern Ontario and examines how its introduction affected primary care provider (PCP) mental health referral patterns. A chart review examined referrals (N = 4,600) from 5 PCP sites to 5 outpatient community mental health services from January 2001 to December 2005. PCPs with access to SMHC made significantly more mental health referrals (p < 0.001). Two demographically similar PCPs were then compared, one co-located with SMHC. Referrals for depression to non-SMHC mental health services were 1.69 times more likely to be from the PCP not co-located with SMHC (p < 0.001). Findings suggest SMHC increases access to care and decreases demand on existing mental health services.

The Experience of Primary Care Providers With an Integrated Mental Health Care Program in Safety-Net Clinics

2015 ◽  
Vol 38 (2) ◽  
pp. 158-168 ◽  
Author(s):  
Wayne D. Bentham ◽  
Anna Ratzliff ◽  
David Harrison ◽  
Ya-Fen Chan ◽  
Steven Vannoy ◽  
...  
Keyword(s):  
Mental Health ◽  
Primary Care ◽  
Health Care ◽  
Care Program ◽  
Primary Care Providers ◽  
Safety Net ◽  
Care Providers ◽  
Health Care Program ◽  
Safety Net Clinics ◽  
Integrated Mental Health
Sign in / Sign up

Export Citation Format

Share Document