Louis Henry Kamulegeya

Dr. Louis Henry Kamulegeya

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 July 2023 in African Health Sciences
Verified
Journal Article
Open access
PDF file
LKLouis Henry Kamulegeya
Louis Henry Kamulegeya
JBJohn Bwanika
John Bwanika
MOMark Okello
Mark Okello
DRDavis Rusoke
Davis Rusoke
FNFaith Nassiwa
Faith Nassiwa
ABAlexander Börve
Alexander Börve
Background: In pursuit of applying universal non-biased Artificial Intelligence (AI) in healthcare, it is essential that data from different geographies are represented. Objective: To assess the diagnostic performance of an AI-powered dermatological algorithm called Skin Image Search on Fitzpatrick6 skin type (dark skin) dermatological conditions. Methods: 123 dermatological images selected from a total of 173 images were retrospectively extracted from the electronic database of a Ugandan telehealth company, The Medical Concierge Group (TMCG) after getting their consent. Details of age, gender, and dermatological clinical diagnosis were analysed using R on R studio software to assess the diagnostic accuracy of the AI app along with disease diagnosis and body part. Predictability levels of the AI app were graded on a scale of 0 to 5, where 0- no prediction was made and 1-5 demonstrated a reduction incorrect diagnosis prediction rate of the AI. Results: 76 (62%) of the dermatological images were from females and 47 (38%) from males. Overall diagnostic accuracy of the AI app on black dermatological conditions was low at 17% (21 out of 123 predictable images) compared to 69.9% performance on Caucasian skin type as reported from the training results. There were varying predictability levels correctness i.e., 1-8.9%, 2-2.4%, 3-2.4%, 4-1.6%, 5-1.6% with performance along individual diagnosis highest with dermatitis (80%). Conclusion: There is need for diversity of image datasets used to train dermatology algorithms for AI applications to increase accuracy across skin types and geographies. Keywords: Artificial intelligence; Dermatology; Fitzpatrick 6 skin type; Telehealth; Algorithms.

1 April 2020 in Pan African Medical Journal
Verified
Journal Article
Open access
LKLouis Henry Kamulegeya
Louis Henry Kamulegeya
JBJohn Mark Bwanika
John Mark Bwanika
DMDavis Musinguzi
Davis Musinguzi
PBPauline Bakibinga
Pauline Bakibinga
In response to coronavirus disease-2019 pandemic (COVID-19), the government of Uganda instituted movement restrictions to curb disease spread. However, this affected accessibility to medical services in a setting where the healthcare system is not equipped to handle most healthcare needs of the populace outside hospital premises. This gap led to the prominence and unprecedented rise in the use of digital health technologies to deliver health information and services at a distance (telehealth) during the COVID-19 outbreak. The use of telehealth modalities including tele-consultation, tele-psychiatry, call centers and mobile phone health information dissemination increased. The COVID-19 pandemic augmented the rising role of digital health technologies as a much needed aspect of medical service delivery in our times. However, the efficacy and impact on clinical outcomes across various healthcare thematic areas need to be explored further and more evidence generated.

31 October 2019 in bioRxiv
Verified
Preprint
Open access
PDF file
LKLouis Henry Kamulegeya
Louis Henry Kamulegeya
MOMark Okello
Mark Okello
JBJohn Mark Bwanika
John Mark Bwanika
DMDavis Musinguzi
Davis Musinguzi
WLWilliam Lubega
William Lubega
ABAlexander Börve
Alexander Börve
Introduction: Artificial intelligence (AI) in healthcare has gained momentum with advances in affordable technology that has potential to help in diagnostics, predictive healthcare and personalized medicine. In pursuit of applying universal non-biased AI in healthcare, it is essential that data from different settings (gender, age and ethnicity) is represented. We present findings from beta-testing an AI-powered dermatological algorithm called Skin Image Search, by online dermatology company First Derm on Fitzpatrick 6 skin type (dark skin) dermatological conditions.Methods: 123 dermatological images selected from a total of 173 images retrospectively extracted from the electronic database of a Ugandan telehealth company, The Medical Concierge Group (TMCG) after getting their consent. Details of age, gender and dermatological clinical diagnosis were analyzed using R on R studio software to assess the diagnostic accuracy of the AI app along disease diagnosis and body part. Predictability levels of the AI app was graded on a scale of 0 to 5, where 0-no prediction made and 1-5 demonstrating reducing correct prediction.Results: 76 (62%) of the dermatological images were from females and 47 (38%) from males. The 5 most reported body parts were; genitals (20%), trunk (20%), lower limb (14.6%), face (12%) and upper limb (12%) with the AI app predicting a diagnosis in 62% of image body parts uploaded. Overall diagnostic accuracy of the AI app was low at 17% (21 out of 123 predictable images) with varying predictability levels correctness i.e. 1-8.9%, 2-2.4%, 3-2.4%, 4-1.6%, 5-1.6% with performance along individual diagnosis highest with dermatitis (80%).Conclusion: There is a need for diversity in the image datasets used when training dermatology algorithms for AI applications in clinical decision support as a means to increase accuracy and thus offer correct treatment across skin types and geographies.

1 January 2020 in Pan African Medical Journal
Verified
Journal Article
Open access
LKLouis Henry Kamulegeya
Louis Henry Kamulegeya
PKPeter James Kitonsa
Peter James Kitonsa
EOEric Okolimong
Eric Okolimong
GKGloria Kaudha
Gloria Kaudha
SMSonia Maria
Sonia Maria
ENEtheldreda Nakimuli-Mpungu
Etheldreda Nakimuli-Mpungu
Majority of alcohol use pattern studies among university students are from developed countries. Information about the different alcohol use patterns and their correlates among university students in sub-Saharan Africa is limited. The aim of this study was to examine the prevalence and cardinal demographic and psychosocial factors associated with specific alcohol use patterns among Ugandan university students. a cross section study conducted over 5-months among university students using a standardized socio-demographic questionnaire screened for alcohol use problems, depression symptoms and academic stress using the alcohol use disorders identification test (AUDIT), self-reporting questionnaire (SRQ-20) and the higher education stress inventory (HESI) respectively. Multivariate multinomial regression models were used to determine factors independently associated with a specific alcohol use pattern with low-risk drinkers as the reference group. a thousand out of 1200 students completed all study requirements for which 60% were males; median age was 22.3 (SD=2.36). The prevalence estimates of any alcohol use, low-risk drinking, heavy episodic drinking and alcohol misuse were 31%, 17.3%, 4.5% and 8.9% respectively. In comparison to low-risk drinkers, students reporting heavy episodic drinking were more likely to report high levels of academic stress (P-value <0.10). Those with alcohol misuse were more likely to be males and with significant depression symptoms (P-value ≤0.05). Non-alcohol users were more likely to report high levels of academic stress (P-value ≤0.05). the prevalence of maladaptive alcohol use patterns is high among Ugandan university students. Integrating peer led psychological interventions into student health services is desperately needed.

15 April 2025 in Journal of Medical Internet Research
Verified
Journal Article
Open access
LKLouis Henry Kamulegeya
Louis Henry Kamulegeya
IKIvan Kagolo
Ivan Kagolo
BKBrenda Kabakaari
Brenda Kabakaari
JAJoan Atuhaire
Joan Atuhaire
RNRacheal Nasamula
Racheal Nasamula
JBJ M Bwanika
J M Bwanika
Background: Sub-Saharan Africa (SSA) accounts for up to 67% of the global HIV burden yet grapples with health system challenges like distant health facilities, low doctor-to-patient ratio, and poor or non-functioning post-hospital follow-up mechanisms. The rising phone ownership and internet penetration in SSA (46% and 67%, respectively) offer an opportunity to leverage technology to address these gaps and drive toward achieving the UNAIDS (Joint United Nations Programme on HIV and AIDS) 95-95-95 targets. Objective: We undertook a scoping review to understand how digital technologies have been integrated into HIV prevention, care, and treatment services delivery in SSA. Methods: A scoping review involving 4 databases (PubMed, CINAHL, Cochrane, and Google Scholar) was carried out, encompassing studies related to technology use in the delivery of HIV prevention, care, and treatment published from January 1, 2019, to December 30, 2023. Search terms like “telemedicine,” “telehealth,” “mobile health,” “eHealth,” “mHealth,” “telecommunication,” “mobile application,” and “digital health,” among others, were used. Of the 310 papers identified, 11 were excluded due to duplicity, 299 were from outside SSA and the intervention was not well described, and 149 were due to the year of publication and study type being a literature review or study protocols, leaving 17 papers that were considered for the review. Results: From the 17 studies summarized, the technologies identified included social media (n=1), interactive voice response (n=1), hotlines (n=1), mobile apps (n=7), health information systems (n=2), chatbots (n=1), and SMS text messages (n=5). Adolescents (11-14 years) and youths (20-35 years) formed the majority of users. The use cases included reminders on facility events, teleconsultations, patient registration, and health information dissemination, among others. Different parameters of individual digital tools were tracked, including feasibility, usability, adoption, and impact on the desired outcome. Conclusions: The integration of digital technologies in health care can address the known challenges in the delivery of HIV prevention, care, and treatment services, facilitate customization of care to individual needs, and thus increase or diversify options available to patients.

31 May 2022 in South African Journal of Psychiatry
Verified
Journal Article
Open access
PDF file
JBJohn M. Bwanika
John M. Bwanika
CHCharlotte Hawkins
Charlotte Hawkins
LKLouis Henry Kamulegeya
Louis Henry Kamulegeya
POPatricia Onyutta
Patricia Onyutta
DMDavis Musinguzi
Davis Musinguzi
JKJascintha Kabeega
Jascintha Kabeega
The South African Journal of Psychiatry publishes topical content in psychiatry for clinical practice and academic pursuits, including work in the subspecialty areas of psychiatry.