Fabrizzio Horta

Fabrizzio Horta

Auto-generated profile, based on publicly available information

Fabrizzio Horta

Department of Obstetrics and Gynecology, Monash University, Clayton, 3168, Victoria, Australia; Fertility and Research Center, University of New South Wales, Sydney, 2052, New South Wales, Australia

Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

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

Representative Publications

View All Publications
1 January 2023 in Human Reproduction Open
Verified
Journal Article
Open access
PDF file
MSM Salih
M Salih
CAC Austin
C Austin
RWR R Warty
R R Warty
CTC Tiktin
C Tiktin
DRDaniel Rolnik
Daniel Rolnik
FHF Horta
F Horta
What is the present performance of artificial intelligence (AI) decision support during embryo selection compared to the standard embryo selection by embryologists? AI consistently outperformed the clinical teams in all the studies focused on embryo morphology and clinical outcome prediction during embryo selection assessment. The ART success rate is ∼30%, with a worrying trend of increasing female age correlating with considerably worse results. As such, there have been ongoing efforts to address this low success rate through the development of new technologies. With the advent of AI, there is potential for machine learning to be applied in such a manner that areas limited by human subjectivity, such as embryo selection, can be enhanced through increased objectivity. Given the potential of AI to improve IVF success rates, it remains crucial to review the performance between AI and embryologists during embryo selection. The search was done across PubMed, EMBASE, Ovid Medline, and IEEE Xplore from 1 June 2005 up to and including 7 January 2022. Included articles were also restricted to those written in English. Search terms utilized across all databases for the study were: (‘Artificial intelligence’ OR ‘Machine Learning’ OR ‘Deep learning’ OR ‘Neural network’) AND (‘IVF’ OR ‘in vitro fertili*’ OR ‘assisted reproductive techn*’ OR ‘embryo’), where the character ‘*’ refers the search engine to include any auto completion of the search term. A literature search was conducted for literature relating to AI applications to IVF. Primary outcomes of interest were accuracy, sensitivity, and specificity of the embryo morphology grade assessments and the likelihood of clinical outcomes, such as clinical pregnancy after IVF treatments. Risk of bias was assessed using the Modified Down and Black Checklist. Twenty articles were included in this review. There was no specific embryo assessment day across the studies—Day 1 until Day 5/6 of embryo development was investigated. The types of input for training AI algorithms were images and time-lapse (10/20), clinical information (6/20), and both images and clinical information (4/20). Each AI model demonstrated promise when compared to an embryologist’s visual assessment. On average, the models predicted the likelihood of successful clinical pregnancy with greater accuracy than clinical embryologists, signifying greater reliability when compared to human prediction. The AI models performed at a median accuracy of 75.5% (range 59–94%) on predicting embryo morphology grade. The correct prediction (Ground Truth) was defined through the use of embryo images according to post embryologists’ assessment following local respective guidelines. Using blind test datasets, the embryologists’ accuracy prediction was 65.4% (range 47–75%) with the same ground truth provided by the original local respective assessment. Similarly, AI models had a median accuracy of 77.8% (range 68–90%) in predicting clinical pregnancy through the use of patient clinical treatment information compared to 64% (range 58–76%) when performed by embryologists. When both images/time-lapse and clinical information inputs were combined, the median accuracy by the AI models was higher at 81.5% (range 67–98%), while clinical embryologists had a median accuracy of 51% (range 43–59%). The findings of this review are based on studies that have not been prospectively evaluated in a clinical setting. Additionally, a fair comparison of all the studies were deemed unfeasible owing to the heterogeneity of the studies, development of the AI models, database employed and the study design and quality. AI provides considerable promise to the IVF field and embryo selection. However, there needs to be a shift in developers’ perception of the clinical outcome from successful implantation towards ongoing pregnancy or live birth. Additionally, existing models focus on locally generated databases and many lack external validation. This study was funded by Monash Data Future Institute. All authors have no conflicts of interest to declare. CRD42021256333

28 February 2020 in Human Reproduction
Verified
Journal Article
Closed access
FHF Horta
F Horta
SCS Catt
S Catt
PRP Ramachandran
P Ramachandran
BVB Vollenhoven
B Vollenhoven
PTP Temple-Smith
P Temple-Smith
STUDY QUESTION: Does female ageing have a negative effect on the DNA repair capacity of oocytes fertilised by spermatozoa with controlled levels of DNA damage?SUMMARY ANSWER: Compared to oocytes from younger females, oocytes from older females have a reduced capacity to repair damaged DNA introduced by spermatozoa.WHAT IS KNOWN ALREADY: The reproductive lifespan in women declines with age predominantly due to poor oocyte quality. This leads to decreased reproductive outcomes for older women undergoing assisted reproductive technology (ART) treatments, compared to young women. Ageing and oocyte quality have been clearly associated with aneuploidy, but the range of factors that influence this change in oocyte quality with age remains unclear. The DNA repair activity prior to embryonic genomic activation is considered to be of maternal origin, with maternal transcripts and proteins controlling DNA integrity. With increasing maternal age, the number of mRNAs stored in oocytes decreases. This could result in diminished efficiency of DNA repair and/or negative effects on embryo development, especially in the presence of DNA damage.STUDY DESIGN, SIZE, DURATION: Oocytes from two age groups of 30 super-ovulated female mice (young: 5–8 weeks old, n = 15; old: 42–45 weeks old, n = 15) were inseminated with sperm from five males with three different controlled DNA damage levels; control: ≤10%, 1 Gray (Gy): 11–30%, and 30 Gy: >30%. Inseminated oocytes (young: 125, old: 78) were assessed for the formation of zygotes (per oocyte) and blastocysts (per zygote). Five replicates of five germinal vesicles (GVs) and five MII oocytes from each age group were analysed for gene expression. The DNA damage response (DDR) was assessed in a minimum of three IVF replicates in control and 1 Gy zygotes and two-cell embryos using γH2AX labelling.PARTICIPANTS/MATERIALS, SETTING, METHODS: Swim-up sperm samples from the cauda epididymidis of C57BL6 mice were divided into control (no irradiation) and 1- and 30-Gy groups. Treated spermatozoa were irradiated at 1 and 30 Gy, respectively, using a linear accelerator Varian 21iX. Following irradiation, samples were used for DNA damage assessment (Halomax) and for insemination. Presumed zygotes were cultured in a time-lapse incubator (MIRI, ESCO). Gene expression of 91 DNA repair genes was assessed using the Fluidigm Biomark HD system. The DNA damage response in zygotes (6–8 h post-fertilisation) and two-cell embryos (22–24 h post-fertilisation) was assessed by immunocytochemical analysis of γH2AX using confocal microscopy (Olympus FV1200) and 3D volumetric analysis using IMARIS software.MAIN RESULTS AND THE ROLE OF CHANCE: The average sperm DNA damage for the three groups was statistically different (control: 6.1%, 1 Gy: 16.1%, 30 Gy: 53.1%, P < 0.0001), but there were no significant differences in fertilisation rates after IVF within or between the two age groups [(young; control: 86.79%, 1 Gy: 82.75%, 30 Gy: 76.74%) (old; control: 93.1%, 1 Gy: 70.37%, 30 Gy: 68.18%) Fisher’s exact]. However, blastocyst rates were significantly different (P < 0.0001) among the groups [(young; control: 86.95%, 1 Gy: 33.33%, 30 Gy: 0.0%) (old; control: 70.37%, 1 Gy: 0.0%, 30 Gy: 0.0%)]. Between the age groups, 1-Gy samples showed a significant decrease in the blastocyst rate in old females compared to young females (P = 0.0166). Gene expression analysis revealed a decrease in relative expression of 21 DNA repair genes in old GV oocytes compared to young GV oocytes (P < 0.05), and similarly, old MII oocytes showed 23 genes with reduced expression compared to young MII oocytes (P < 0.05). The number of genes with decreased expression in older GV and MII oocytes significantly affected pathways such as double strand break (GV: 5; MII: 6), nucleotide excision repair (GV: 8; MII: 5) and DNA damage response (GV: 4; MII: 8). There was a decreased DDR in zygotes and in two-cell embryos from old females compared to young regardless of sperm treatment (P < 0.05). The decrease in DNA repair gene expression of oocytes and decreased DDR in embryos derived from older females suggests that ageing results in a diminished DNA repair capacity.LARGE-SCALE DATA: N/ALIMITATIONS, REASONS FOR CAUTION: Ionising radiation was used only for experimental purposes, aiming at controlled levels of sperm DNA damage; however, it can also damage spermatozoa proteins. The female age groups selected in mice were intended to model effects in young and old women, but clinical studies are required to demonstrate a similar effect.WIDER IMPLICATIONS OF THE FINDINGS: Fertilisation can occur with sperm populations with medium and high DNA damage, but subsequent embryo growth is affected to a greater extent with aging females, supporting the theory that oocyte DNA repair capacity decreases with age. Assessment of the oocyte DNA repair capacity may be a useful diagnostic tool for infertile couples.STUDY FUNDING/COMPETING INTEREST(S): Funded by the Education Program in Reproduction and Development, Department of Obstetrics and Gynaecology, Monash University. None of the authors has any conflict of interest to report.

25 December 2021 in Molecular Human Reproduction
Verified
Journal Article
Closed access
PDF file
HNH Newman
H Newman
SCS Catt
S Catt
BVB Vining
B Vining
BVB Vollenhoven
B Vollenhoven
FHF Horta
F Horta
Sperm DNA damage is considered a predictive factor for the clinical outcomes of patients undergoing ART. Laboratory evidence suggests that zygotes and developing embryos have adopted specific response and repair mechanisms to repair DNA damage of paternal origin. We have conducted a systematic review in accordance with guidelines from Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) to identify and review the maternal mechanisms used to respond and repair sperm DNA damage during early embryonic development, how these mechanisms operate and their potential clinical implications. The literature search was conducted in Ovid MEDLINE and Embase databases until May 2021. Out of 6297 articles initially identified, 36 studies were found to be relevant through cross referencing and were fully extracted. The collective evidence in human and animal models indicate that the early embryo has the capacity to repair DNA damage within sperm by activating maternally driven mechanisms throughout embryonic development. However, this capacity is limited and likely declines with age. The link between age and decreased DNA repair capacity could explain decreased oocyte quality in older women, poor reproductive outcomes in idiopathic cases and patients who present high sperm DNA damage. Ultimately, further understanding mechanisms underlying the maternal repair of sperm DNA damage could lead to the development of targeted therapies to decrease sperm DNA damage, improved oocyte quality to combat incoming DNA insults or lead to development of methodologies to identify individual spermatozoa without DNA damage.

26 November 2019 in Human Reproduction
Verified
Journal Article
Closed access
FHF Horta
F Horta
BVB Vollenhoven
B Vollenhoven
MHM Healey
M Healey
LBL Busija
L Busija
SCS Catt
S Catt
PTP Temple-Smith
P Temple-Smith
STUDY QUESTION: Is male age associated with the clinical outcomes of IVF/ICSI cycles for idiopathic infertility after adjustment for female age? SUMMARY ANSWER: Male ageing is negatively associated with clinical IVF/ICSI outcomes in couples with idiopathic infertility independent of female age. WHAT IS KNOWN ALREADY: The effect of male age on the outcomes of infertility treatments is controversial and poorly explored. In contrast, fertility is known to decline significantly with female age beyond the mid-30s, and reduced oocyte quality plays an important role. The negative effect of male age on sperm quality is largely associated with an increasing susceptibility to sperm DNA damage. Although increasing maternal age has been linked with poorer oocyte quality, studies on the effect of male age have disregarded the need to control for female age making it difficult to define clearly the role of male age in infertile couples. STUDY DESIGN, SIZE, DURATION: This retrospective cohort study analysed 2425 cycles of couples with idiopathic infertility selected from a total of 24 411 IVF/ICSI cycles performed at Monash IVF in Australia between 1992 and 2017. The primary outcome was live birth and secondary outcomes were clinical pregnancy and miscarriage. PARTICIPANTS/MATERIALS, SETTING, METHODS: Couples with primary/secondary infertility who underwent IVF/ICSI cycles with male partners classified as normozoospermic were selected (inclusion criteria). Couples in which the female partner had endometriosis, tubal factors, polycystic ovarian syndrome, ovarian hyperstimulation syndrome, poor responders (≤3 mature oocytes retrieved) and couples with more than 15 cumulus oocyte complexes retrieved or who used cryopreserved gametes were excluded. Binary logistic multilevel modelling was used to identify the effect of male age and female age on clinical outcomes after controlling for confounding factors. Male age and female age were examined as continuous and categorical (male age: <40, 40–44, 45–49, 50–54, ≥55; female age:<30, 30–34, 35–39, ≥40) predictors. MAIN RESULTS AND THE ROLE OF CHANCE: There was a negative effect of male age and female age on live birth as odds ratios (OR) with 95% CI for each additional year of age (OR-male age: 0.96 [0.94–0.98]; OR-female age: 0.90 [0.88–0.93] P < 0.001). Potential interactions with male age such as type of treatment (IVF/ICSI), embryo transfer day (Day 3/Day 5) and female age did not have significant associations with outcomes (P > 0.05). Secondary outcomes showed a significant reduction in the odds of clinical pregnancy (OR-male age: 0.97 [0.96–0.99]; OR-female age: 0.92 [0.89–0.94] P < 0.001) and an increase in the odds of miscarriage with older age: male age (OR: 1.05 [1.01–1.08]; P = 0.002); female age (OR: 1.11 [1.05–1.18]; P < 0.001). Worse outcomes were associated with more cycles (clinical pregnancy-OR: 0.96 [0.93–0.99] P = 0.03; live birth-OR: 0.96 [0.92–0.99] P = 0.023) while more inseminated oocytes were associated with better outcomes (clinical pregnancy-OR: 1.06 [1.03–1.06] P < 0.001; live birth-OR: 1.07 [1.04–1.11] P < 0.001). Analyses for age categories showed a gradual worsening of clinical outcomes with increasing male age, with a significantly worse live birth and clinical pregnancy outcomes in males aged older than 50 years compared to males younger than 40 years (P < 0.05). LIMITATIONS, REASONS FOR CAUTION: This study is limited to the information on confounding factors included. The study may also be limited in its generalizability to a wider population due the strict selection criteria. Age as a category could potentially result in residual confounding due to categorizing a continuous variable. WIDER IMPLICATIONS OF THE FINDINGS: This study provides information for counselling of couples with idiopathic infertility. STUDY FUNDING/COMPETING INTEREST(S): Funded by the Education Program in Reproduction and Development, Department of Obstetrics and Gynaecology, Monash University. None of the authors has any conflict of interest to report. TRIAL REGISTRATION NUMBER: N/A.

16 March 2022 in Advances in Nutrition
Verified
Journal Article
Open access
PDF file
NKNicole Kellow
Nicole Kellow
JCJake Le Cerf
Jake Le Cerf
FHFabrizzio Horta
Fabrizzio Horta
ADAimee L Dordevic
Aimee L Dordevic
CBChristie J Bennett
Christie J Bennett
The nutritional status of reproductive-aged couples can have a significant impact on fertility status, but the effect of dietary patterns on pregnancy outcomes in people using assisted reproductive technologies (ARTs) is currently unknown. This review aimed to synthesize the published research investigating the relation between preconception dietary patterns and clinical pregnancy or live birth in men and women of reproductive age undergoing ART. Six electronic databases were systematically searched for original research published between January 1978 and June 2021. Original research reporting on the effect of predefined dietary patterns on either clinical pregnancy and/or live birth rates following in vitro fertilization (IVF) or intracytoplasmic sperm injection (ICSI) in men and women aged 18–49 y was eligible for inclusion. Studies were assessed for risk of bias according to the Cochrane guidelines. Included studies underwent qualitative and quantitative synthesis using random-effects model meta-analyses. Thirteen studies (12 cohort studies, 1 randomized controlled trial) reporting on 3638 participants (93% female) were included in the review. All studies had a moderate–high risk of bias. In individual studies, maternal adherence to 4 dietary patterns [Mediterranean diet (RR: 1.22; 95% CI: 1.05, 1.43), novel profertility diet (OR: 1.43; 95% CI: 1.19, 1.72), Iranian traditional medicine diet (OR: 3.9; 95% CI: 1.2, 12.8), Dutch national dietary recommendations diet (OR: 1.65; 95% CI: 1.08, 2.52)] was associated with increased likelihood of achieving a clinical pregnancy, while 2 dietary patterns [novel profertility diet (OR: 1.53; 95% CI: 1.26, 1.85), Mediterranean diet (RR: 1.25; 95% CI: 1.07, 1.45)] were associated with increased probability of live birth. Meta-analyses showed an association between adherence to the Mediterranean dietary pattern and live birth across 2 studies (OR: 1.98; 95% CI: 1.17, 3.35; I2 = 29%, n = 355), but no association with clinical pregnancy. As the relation between dietary patterns and ART outcomes is currently inconsistent, higher-quality nutrition research is required to further explore this emerging field of interest (PROSPERO registration: CRD42020188194).

21 May 2025 in Scientific Reports
Verified
Journal Article
Open access
PDF file
MSMohamed Salih
Mohamed Salih
CAChristopher Austin
Christopher Austin
KMKrishna Mantravadi
Krishna Mantravadi
ESEva Seow
Eva Seow
SJSutthipat Jitanantawittaya
Sutthipat Jitanantawittaya
FHFabrizzio Horta
Fabrizzio Horta
An advanced Artificial Intelligence (AI) model that leverages cutting-edge computer vision techniques to analyse embryo images and clinical data, enabling accurate prediction of clinical pregnancy outcomes in single embryo transfer procedures. Three AI models were developed, trained, and tested using a database comprised of a total of 1503 international treatment cycles (Thailand, Malaysia, and India): 1) A Clinical Multi-Layer Perceptron (MLP) for patient clinical data. 2) An Image Convolutional Neural Network (CNN) AI model using blastocyst images. 3) A fused model using a combination of both models. All three models were evaluated against their ability to predict clinical pregnancy and live birth. Each of the models were further assessed through a visualisation process where the importance of each data point clarified which clinical and embryonic features contributed the most to the prediction. The MLP model achieved a strong performance of 81.76% accuracy, 90% average precision and 0.91 AUC (Area Under the Curve). The CNN model achieved a performance of 66.89% accuracy, 74% average precision and 0.73 AUC. The Fusion model achieved 82.42% accuracy, 91% average precision and 0.91 AUC. From the visualisation process we found that female and male age to be the most clinical factors, whilst Trophectoderm to be the most important blastocyst feature. There is a gap in performance between the Clinical and Images model, which is expected due to the difficulty in predicting clinical pregnancy from just the blastocyst images. However, the Fusion AI model made more informed predictions, achieving better performance than separate models alone. This study demonstrates that AI for IVF application can increase prediction performance by integrating blastocyst images with patient clinical information.