47 research outputs found

    A Hybrid Machine Learning Model for Predicting Surgical Procedure Duration: Integrating Random Forest and K-Means Clustering

    No full text
    International audienceEfficient operating room (OR) management depends on the accurate prediction of surgical procedure durations to improve scheduling, enhance patient outcomes, and reduce operational costs. This study presents a hybrid machine learning model that combines Random Forest and K-Means clustering to predict the duration of cholecystectomy procedures. The model is trained using real-world data from the digestive surgery department at Mahmoud El Matri Hospital in Tunis, Tunisia, incorporating patient demographics, surgeon experience, and other contextual factors. Synthetic data generation was also applied to reinforce model reliability. The proposed approach achieved strong performance, with a root mean square error (RMSE) of 0.45 minutes, a mean absolute error (MAE) of 0.36 minutes, and a coefficient of determination (R2) of 0.99. Comparative analysis with individual models such as Random Forest, K-Means, decision trees, and linear regression confirms the hybrid model’s superior predictive capability. These results demonstrate the potential of the proposed hybrid model as a practical tool for optimizing OR scheduling and improving healthcare resource management

    Macular Dystrophy with Bilateral Macular Telangiectasia Related to the CYP2U1 Pathogenic Variant Assessed with Multimodal Imaging Including OCT-Angiography

    No full text
    Purpose: We report the case of a neurologically asymptomatic young boy presenting with an unusual phenotype of CYP2U1 related macular dystrophy associating bilateral macular telangiectasia (MacTel) and fibrotic choroidal neovascularization (CNV), assessed with complete multimodal imaging including optical coherence tomography angiography (OCT-A). Case presentation: A twelve-year-old boy from a non-consanguineous family complained of bilateral progressive visual loss and photophobia. The best-corrected visual acuity was 2/10 on the right eye and 3/10 on the left eye. Fundus examination showed central pigmented fibrotic macular scar and yellowish punctuate deposits in both eyes. En face OCT-A detected typical macular telangiectasia (MacTel) in both eyes with dilated telangiectatic capillaries in the deep capillary plexus associated with vascular anomalies in the superficial and deep capillary plexus. Typical hypo-reflective cavities were observed within the inner foveal layers on structural OCT. En face OCT-A also confirmed the presence of bilateral inactive CNV within the fibrotic scars, showing high-flow vascular network at the level of the subretinal hyperreflective lesions. Whole exome sequencing identified a known homozygous pathogenic variant in CYP2U1 gene (c.1168C > T, p.Arg390*), which is a disease-causing mutation in autosomal recessive spastic paraplegia type 56 (SPG56). The neurological examination was normal, and electromyography and brain magnetic resonance imaging were unremarkable as well. Conclusion: Macular dystrophy can be the first manifestation in SPG56. A particular phenotype with MacTel was observed, and neovascular complications are possible. CYP2U1 should be included in the panels of genes tested for macular dystrophies, especially in the presence of MacTel and/or neurological manifestations

    Different Phenotypes in Pseudodominant Inherited Retinal Dystrophies.

    No full text
    Retinal dystrophies (RD) are a group of Mendelian disorders caused by rare genetic variations leading to blindness. A pathogenic variant may manifest in both dominant or recessive mode and clinical and genetic heterogeneity makes it difficult to establish a precise diagnosis. In this study, families with autosomal dominant RD in successive generations were identified, and we aimed to determine the disease's molecular origin in these consanguineous families. Whole exome sequencing was performed in the index patient of each family. The aim was to determine whether these cases truly represented examples of dominantly inherited RD, or whether another mode of inheritance might be applicable. Six potentially pathogenic variants in four genes were identified in four families. In index patient with enhanced S-cone syndrome in F1, we identified a new digenetic combination: a heterozygous variant p.[G51A];[=] in RHO and a homozygous pathogenic variant p.[R311Q];[R311Q] in NR2E3. Helicoid subretinal fibrosis associated with recessive NR2E3 variant p.[R311Q];[R311Q] was identified in F2. A new frameshift variant c.[105delG];[105delG] in RDH12 was found in F3 with cone-rod dystrophy. In F4, the compound heterozygous variants p.[R964 * ];[W758 * ] were observed in IMPG2 with a retinitis pigmentosa (RP) phenotype. We showed that both affected parents and the offspring, were homozygous for the same variants in all four families. Our results provide evidence that in consanguineous families, autosomal recessive can be transmitted as pseudodominant inheritance in RD patients, and further extend our knowledge of pathogenic variants in RD genes
    corecore