Mohamed Fihri

Prof. Dr. Mohamed Fihri

orcid

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
22 October 2016 in BMC Women's Health
Verified
Journal Article
Open access
PDF file
TDTouria Derkaoui
Touria Derkaoui
JBJoaira Bakkach
Joaira Bakkach
MMMohamed Mansouri
Mohamed Mansouri
ALAli Loudiyi
Ali Loudiyi
MFMohamed Fihri
Mohamed Fihri
MMMohcine Bennani Mechita
Mohcine Bennani Mechita
Triple Negative Breast Cancer (TNBC) is defined by a lack of estrogen and progesterone receptor gene expression and by the absence of overexpression on HER2. It is associated to a poor prognosis. We propose to analyze the clinicopathologic and prognostic characteristics of this breast cancer subtype in a Mediterranean population originated or resident in the North of Morocco. We conducted a retrospective study of 279 patients diagnosed with breast cancer between January 2010 and January 2015. Clinicopathologic and prognostic features have been analyzed. Disease-Free Survival (DFS) and Overall Survival (OS) have been estimated. Of all cases, forty-nine (17.6 %) were identified as having triple negative breast cancer with a median age of 46 years. The average tumor size was 3.6 cm. The majority of patients have had invasive ductal carcinoma (91.8 %) and 40.4 % of them were grade III SBR. Nodal metastasis was detected in 38.9 % of the patients and vascular invasion was found in 36.6 % of them. About half of the patients had an early disease (53.1 %) and 46.9 % were diagnosed at an advanced stage. Patients with operable tumors (61.2 %) underwent primary surgery and adjuvant chemotherapy. Patients with no operable tumors (26.5 %) received neoadjuvant chemotherapy followed by surgery, and patients with metastatic disease (12.2 %) were treated by palliative chemotherapy. DFS and OS at 5 years were respectively 83.7 and 71.4 %. Among 49, twelve had recurrences, found either when diagnosing them or after a follow-up. Local relapse was 6.1 %. Lung and liver metastases accounted consecutively for 8.2 and 10.2 %. Bone metastases were found in 4.1 % and brain metastases in 2.1 % of the cases. Our results are in accordance with literature data, particularly what concerning young age and poor prognosis among TNBC phenotype. Therefore, the identification of BRCA mutations in our population seems to be essential in order to better adapt management options for this aggressive form of breast cancer.

1 July 2016 in Journal of Statistics Applications & Probability
Verified
Journal Article
Closed access
MFMohamed Fihri
Mohamed Fihri
AMAmal Mellouk
Amal Mellouk
AAAbdelhadi Akharif
Abdelhadi Akharif

25 March 2025 in Physica A: Statistical Mechanics and its Applications
Verified
Journal Article
Closed access
ARAfaf El Rhiouane
Afaf El Rhiouane
Hassan OUKHOUYAHassan OUKHOUYA
Hassan OUKHOUYA
RGRaby Guerbaz
Raby Guerbaz
KBKhalid BELKHOUTOUT
Khalid BELKHOUTOUT
ALAziz Lmakri
Aziz Lmakri
AAAbdellatif El Afia
Abdellatif El Afia


3 October 2025 in Quality & Quantity
Verified
Journal Article
Closed access
PDF file
Hassan OUKHOUYAHassan OUKHOUYA
Hassan OUKHOUYA
FLFatima Ezzahra Lfaze
Fatima Ezzahra Lfaze
RGRaby Guerbaz
Raby Guerbaz
KBKhalid BELKHOUTOUT
Khalid BELKHOUTOUT
ALAziz Lmakri
Aziz Lmakri
AAAbdellatif El Afia
Abdellatif El Afia

24 August 2026 in Discover Artificial Intelligence
Verified
Journal Article
Open access
PDF file
MNMohamed Nachat
Mohamed Nachat
Hassan OUKHOUYAHassan OUKHOUYA
Hassan OUKHOUYA
SMSaid El Melhaoui
Said El Melhaoui
MFMoustapha Faizi
Moustapha Faizi
MFMohamed Fihri
Mohamed Fihri
SASalaheddine El Adlouni
Salaheddine El Adlouni
Time series forecasting plays a central role in finance, energy, and public health. Classical statistical, machine learning, deep learning, and generative approaches have all been applied to forecasting tasks in these fields, but comparisons between them are usually confined to a single domain or to models from the same family, and few studies report both univariate and multivariate results under the same conditions. This paper presents a controlled cross-domain comparison of four representative paradigms: classical statistics (Seasonal Autoregressive Integrated Moving Average with Exogenous variables, SARIMAX), gradient boosting machine learning (Light Gradient Boosting Machine, LightGBM), recurrent deep learning (Recurrent Neural Network, RNN), and generative-adversarial deep learning (Conditional Generative Adversarial Network, CGAN). Each model is evaluated on three monthly datasets with contrasting characteristics: Bitcoin prices (175 observations, high volatility), U.S. energy consumption (612 observations, strong seasonality), and U.S. cardiovascular mortality (300 observations, gradual trend with pandemic shock). Both univariate and multivariate variants are tested under the same preprocessing and one-step-ahead evaluation protocols, using eight performance metrics. The CGAN reaches the lowest MAPE on energy consumption (2.88%). On Bitcoin, the multivariate LightGBM lowers the MAPE from 28.26 to 19.25%, while on cardiovascular mortality the RNN reaches 3.34% MAPE. No paradigm performs best in every domain, and the gain from exogenous variables depends on both the paradigm and the domain.