Adetola Emmanuel Babalola

Dr. Adetola Emmanuel Babalola

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
16 December 2025 in Artificial Intelligence Surgery
Verified
Journal Article
Open access
PDF file
OKOmar Kasimieh
Omar Kasimieh
MAMohamed Mustaf Ahmed
Mohamed Mustaf Ahmed
ZOZhinya Kawa Othman
Zhinya Kawa Othman
IAIfrah Ali
Ifrah Ali
MHMulki Mukhtar Hassan
Mulki Mukhtar Hassan
DIDon Eliseo Lucero-Prisno III
Don Eliseo Lucero-Prisno III
Aim: Real-time image guidance using deep learning is being increasingly used in surgery. This systematic review aims to characterize intraoperative systems, mapping applications, performance and latency, validation practices, and the reported effects on workflow and patient-relevant outcomes. Methods: A systematic review was conducted on PubMed, Embase, Scopus, ScienceDirect, IEEE Xplore, Google Scholar, and Directory of Open Access Journals from December 31, 2024. Eligible English-language, peer-reviewed diagnostic accuracy, cohort, quasi-experimental, or randomized studies (2017-2024) evaluated the learning for real-time intraoperative guidance. Two reviewers screened, applied the Joanna Briggs Institute checklists, and extracted the design, modality, architecture, training, validation, performance, and latency. Heterogeneity precluded the meta-analysis. Results: Twenty-seven studies spanning laparoscopic, neurosurgical, breast, colorectal, cardiac, and other workflows met the criteria. The modalities included red-green-blue laparoscopy or endoscopy, ultrasound, optical coherence tomography, cone-beam computed tomography, and stimulated Raman histology. The architectures were mainly convolutional neural networks with frequent transfer learning. Reported performance was high, with classification accuracy commonly 90%-97% and segmentation Dice or intersection over union up to 0.95 at operating-room-compatible speeds of about 20-300 frames per second or sub-second per-frame latency; volumetric pipelines sometimes required up to 1 min. Several systems demonstrated intraoperative feasibility and high surgeon acceptance, yet fewer than one quarter reported external validation and only a small subset linked outputs to patient-important outcomes. Conclusion: Deep-learning systems for real-time image guidance exhibit strong technical performance and emerging workflow benefits. Priorities include multicenter prospective evaluations, standardized reporting of latency and external validation, rigorous human factors assessment, and open benchmarking to demonstrate generalizability and patient impact.

6 June 2025 in BMC Oral Health
Verified
Journal Article
Open access
PDF file
TWTorojah Mayaline Williams
Torojah Mayaline Williams
ABAdetola Emmanuel Babalola
Adetola Emmanuel Babalola
OBOlubusayo Bolarinwa
Olubusayo Bolarinwa
VSVictor Adeyanju Somoye
Victor Adeyanju Somoye
OAOluwaseun Akinola Azeez
Oluwaseun Akinola Azeez
AEAdaeze Favour Egemonye
Adaeze Favour Egemonye
Background: This systematic review aimed to assess pregnant women’s knowledge, perceptions, and attitudes toward oral health changes in sub-Saharan Africa (SSA) and examine their oral health-seeking behavior during pregnancy. Methods: A comprehensive search was conducted across PubMed, Google Scholar, African Journals Online (AJOL), the Directory of Open Access Journals (DOAJ), and the Cochrane Library. Both Medical Subject Headings (MeSH) and free-text terms related to oral health, knowledge, attitudes, perceptions, antenatal care, pregnancy, and Africa were used. Boolean operators (“AND,” “NOT,” and “OR”) refined the search strategy. Two independent reviewers screened studies and extracted data using Rayyan software, with a third reviewer resolving conflicts. The Robins-E tool assessed the risk of bias. Results: Fifteen of seventy-five studies initially identified met the inclusion criteria after full-text screening. Most employed a cross-sectional design. Findings revealed low oral health-seeking behavior among pregnant women in Africa, attributed to factors such as negative dental experiences, concerns about harm to the unborn child, and the belief that dental care is unnecessary. Many women visited dental clinics only when they noticed significant oral health changes. Conclusions: The reviewed studies demonstrated a low risk of bias and consistent findings. Pregnancy is a critical period, and poor oral health can adversely affect birth outcomes. Insufficient knowledge and misconceptions deter women from seeking dental care during pregnancy. To address this, targeted oral health education must improve awareness and overcome barriers to seeking care.

30 January 2026 in Discover Artificial Intelligence
Verified
Journal Article
Open access
PDF file
ABAdetola Emmanuel Babalola
Adetola Emmanuel Babalola
VJVictor Miracle Johnson
Victor Miracle Johnson
OBOlubusayo Bolarinwa
Olubusayo Bolarinwa
AOAbraham Oloture Ogwuche
Abraham Oloture Ogwuche
VSVictor Adeyanju Somoye
Victor Adeyanju Somoye
OOOladapo Daniel Oludiran
Oladapo Daniel Oludiran
Objectives: The objective of this study was to quantitatively evaluate and compare the performance of three advanced generative AI models, ChatGPT (v4.0), Gemini (v2.0 advanced), and Meta AI (Llama 3.2) in providing accurate information of AIDS-associated Oral Kaposi Sarcoma (OKS). Methods: This was a cross-sectional analytical study with three advanced large language models (LLM) against a gold standard (oral pathologists). A structured questionnaire was adapted from the WHO Oral Health Survey and modified WHO guidelines for the treatment of skin and oral HIV-associated lesions. Data collection was conducted over a 24-hour window utilizing the same protocol for all models. Prompting was introduced in a second round of testing using CARE (Context, Ask, Rule, Example) to examine whether engineered prompts improved response accuracy. Responses were collected on a 5-point Likert scale (strongly agree, agree, neutral, disagree and strongly disagree) and then collapsed into a binary scale where agreement between two or more pathologists served as the correct score. Descriptive statistics, including means and standard deviations, were used to summarize the results. Comparative analyses employed ANOVA to evaluate differences in accuracy scores across AI models and the gold standard. All statistical significance were set at p < 0.05. Results: The results demonstrated that, before prompting, both ChatGPT and Gemini AI achieved an accurate score of 81.48%, while Meta AI lagged with a score of 66.67%. After prompting, Gemini AI exhibited the greatest improvement, achieving an accuracy of 85.18%. Meta AI also improved to 81.48%, while ChatGPT’s accuracy declined slightly to 77.78%. The pathologist achieved an accuracy score of 85.19%, highlighting that the best-performing AI (Gemini after prompting) approached expert-level accuracy. Analysis of variance (ANOVA) revealed no statistically significant differences in mean accuracy scores between AI models and the pathologist (F = 0.64, P = 0.6996). Conclusion: AI models have the potential to provide comprehensive information on presentation, examination, and follow-up on HIV associated oral KS. Finally, models may struggle with more complex clinical aspects, such as investigations and treatment recommendations.

4 July 2025 in Medicine
Verified
Journal Article
Open access
NANicholas Aderinto
Nicholas Aderinto
GOGbolahan Mbbs Olatunji
Gbolahan Mbbs Olatunji
EKEmmanuel Mbbs Kokori
Emmanuel Mbbs Kokori
DODoyin Olatunji
Doyin Olatunji
OOOluwatobi Mbbs Omoworare
Oluwatobi Mbbs Omoworare
NNNaana Mbbs Nkrumah-Ababio
Naana Mbbs Nkrumah-Ababio
Gliomas pose significant therapeutic challenges due to limited survival and risks of treatment-related toxicity. Proton beam therapy (PBT) offers a precise radiation delivery method, minimizing damage to healthy brain tissue compared to conventional radiotherapy. This review synthesizes findings from 15 studies (2000–January 2024) from PubMed, Google Scholar, Science Direct, Cochrane Library, and Directory of Open Access Journals. PBT significantly reduces neurocognitive decline and enhances quality of life while achieving comparable or superior survival outcomes across various glioma types, including low-grade gliomas and glioblastomas. Notable benefits include improved verbal memory, stable intellectual functioning, and reduced high-grade toxicity. However, challenges such as neuroendocrine deficiencies and increased radiation necrosis highlight the need for optimized protocols. Future research should focus on comprehensive outcome assessments, proactive management of adverse effects, and improving PBT accessibility through cost reduction and technological advancements. PBT holds transformative potential in glioma management, balancing effective tumor control with preservation of neurological function, positioning it as a valuable neuro-oncology treatment option.

2 December 2024 in Discover Medicine
Verified
Journal Article
Open access
PDF file
NANicholas Aderinto
Nicholas Aderinto
GOGbolahan Deji Olatunji
Gbolahan Deji Olatunji
EKEmmanuel Kokori
Emmanuel Kokori
BUBonaventure Ukoaka
Bonaventure Ukoaka
ABAdetola Emmanuel Babalola
Adetola Emmanuel Babalola
YAYewande Abigail Adebayo
Yewande Abigail Adebayo
Ischemic stroke can leave patients with lasting disabilities. Rehabilitation is crucial, but new approaches are needed. One promising avenue is hypoxia exposure therapy. This involves controlled exposure to low oxygen levels. While it may sound counterintuitive, this approach triggers the brain to adapt. Studies suggest hypoxia stimulates the growth of new blood vessels, boosting oxygen delivery to the damaged area. Additionally, it may promote neuroplasticity, the brain's ability to reorganize and form new connections. This can lead to the creation of new nerve cells, potentially replacing those lost in the stroke. Furthermore, hypoxia exposure might help regulate inflammation, a key contributor to stroke damage. Early research, particularly with intermittent hypoxia training, shows promise for improved motor function recovery. However, challenges remain. Stroke severity, location, and individual health vary greatly, requiring personalized treatment plans. Determining the optimal dose, timing, and frequency of hypoxia exposure is crucial for maximizing benefits. Additionally, the precise mechanisms by which hypoxia aids recovery need further investigation. Future research will focus on tailoring protocols to individual patients, exploring combinations with other rehabilitation methods, and conducting large-scale trials to solidify the safety and effectiveness of hypoxia therapy.

27 November 2025 in Annals of Medicine & Surgery
Verified
Journal Article
Open access
TOTemitomi Jane Oyedele
Temitomi Jane Oyedele
SASyed Hasham Ali
Syed Hasham Ali
AAAbigail Oghenefejiro Asini
Abigail Oghenefejiro Asini
AAAdepeju Anuoluwa Agunbiade
Adepeju Anuoluwa Agunbiade
KDKomolafe Praise Dolapo
Komolafe Praise Dolapo
NANicholas Aderinto
Nicholas Aderinto
Background: Acute appendicitis remains a leading cause of emergency surgery globally. While laparoscopic appendectomy (LA) has become the preferred technique in high-income countries due to reduced postoperative complications and shorter recovery times, its adoption in Sub-Saharan Africa is limited by resource constraints. This systematic review and meta-analysis evaluates the safety, feasibility, and cost-effectiveness of LA compared to open appendectomy (OA) in this region. Methods: Following Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, a systematic search was conducted across PubMed/MEDLINE, Cochrane Library, AJOL, Scopus, Embase, and Web of Science from database inception to July 2025. Eligible studies included original research comparing LA and OA for acute appendicitis in Sub-Saharan Africa, with outcomes such as surgical site infection (SSI), operative time, hospital stay, and costs. Results: LA significantly reduced SSI risk [risk ratio 0.40, 95% confidence interval (CI): 0.23–0.69, P = 0.001, I 2 = 0%] and hospital stay [mean defference (MD) 1.32 days, 95% CI: 1.64–0.99, P < 0.00001, I 2 = 86%) compared to OA across 452 and 521 patients, respectively. Operative time was longer with LA (MD 13.79 minutes, 95% CI: 7.23–20.35, P < 0.0001, I 2 = 78%). Cost data from two studies were inconclusive, with OA being less expensive in one ( P < 0.001) and LA showing a borderline advantage in another ( P = 0.049), with no significant difference in theatre costs (USD 634.92 versus USD 589.20, P = 0.264). Conclusions: LA offers significant safety and efficiency benefits over OA for acute appendicitis in Sub-Saharan Africa.