Joel Pitkänen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Joel Pitkänen has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- M. Johanna Liinamaa
Department of Ophthalmology, Oulu University Hospital, Oulu, Finland
5 shared publications - Ville Saarela
Department of Ophthalmology, Oulu University Hospital, Oulu, Finland
3 shared publications Ilmari Leiviskä
PEDEGO Research Unit University of Oulu and Medical Research Center Oulu Finland
2 shared publicationsVille Saarela
Department of Ophthalmology and Medical Research Center, Oulu University Hospital, Oulu, Finland
2 shared publicationsAnja Tuulonen
Tays Eye Center, Tampere University Hospital, Tampere, Pirkanmaa, Finland
1 shared publication- Elina Karvonen
Department of Ophthalmology, Oulu University Hospital, Oulu, Finland
1 shared publication
Latest Publications
- 15 April 2026
- Published by BMJ in British Journal of Ophthalmology
Deep learning in population-based screening for glaucoma
Background/aims: Deep learning algorithms have shown promise for glaucoma detection using retinal imaging. The Northern Finland Birth Cohort Eye Study is a randomised prospective cohort designed to evaluate the efficacy and cost-effectiveness of glaucoma screening in a middle-aged population. This study assessed the performance and generalisability of G-RISK, a deep learning model for glaucoma screening from fundus images, in individuals aged 45–49 years with low glaucoma prevalence (1.1%). Methods: Four screening scenarios were evaluated: detection of (1) glaucoma eyes, (2) glaucoma patients, (3) glaucoma and glaucoma suspect eyes and (4) glaucoma and glaucoma suspect patients. Performance across four photographic modalities was assessed using the area under the receiver operating characteristic curve (AUC), the precision–recall AUC (PR-AUC), and sensitivity at 95% specificity. Results: G-RISK achieved its highest performance when screening for glaucoma eyes using colour fundus photographs, with an AUC of 0.83 (95% CI 0.75 to 0.90), PR-AUC of 0.16 (95% CI 0.05 to 0.28) and sensitivity at 95% specificity of 0.43 (95% CI 0.28 to 0.59). Furthermore, discrimination remained consistent across other modalities (AUC 0.75–0.78). Performance was higher for confirmed glaucoma than combined glaucoma and glaucoma suspect cases (AUC 0.83 vs 0.67). Conclusions: G-RISK achieved the best results on colour fundus images, while maintaining discrimination across other imaging modalities. Screening metrics were constrained by the relatively young age and low glaucoma prevalence of the cohort. The reduced performance observed when including glaucoma suspects may relate to variability and uncertainty in their clinical definition.
- 15 April 2026
- Published by BMJ in British Journal of Ophthalmology
Deep learning in population-based screening for glaucoma
Background/aims: Deep learning algorithms have shown promise for glaucoma detection using retinal imaging. The Northern Finland Birth Cohort Eye Study is a randomised prospective cohort designed to evaluate the efficacy and cost-effectiveness of glaucoma screening in a middle-aged population. This study assessed the performance and generalisability of G-RISK, a deep learning model for glaucoma screening from fundus images, in individuals aged 45–49 years with low glaucoma prevalence (1.1%). Methods: Four screening scenarios were evaluated: detection of (1) glaucoma eyes, (2) glaucoma patients, (3) glaucoma and glaucoma suspect eyes and (4) glaucoma and glaucoma suspect patients. Performance across four photographic modalities was assessed using the area under the receiver operating characteristic curve (AUC), the precision–recall AUC (PR-AUC), and sensitivity at 95% specificity. Results: G-RISK achieved its highest performance when screening for glaucoma eyes using colour fundus photographs, with an AUC of 0.83 (95% CI 0.75 to 0.90), PR-AUC of 0.16 (95% CI 0.05 to 0.28) and sensitivity at 95% specificity of 0.43 (95% CI 0.28 to 0.59). Furthermore, discrimination remained consistent across other modalities (AUC 0.75–0.78). Performance was higher for confirmed glaucoma than combined glaucoma and glaucoma suspect cases (AUC 0.83 vs 0.67). Conclusions: G-RISK achieved the best results on colour fundus images, while maintaining discrimination across other imaging modalities. Screening metrics were constrained by the relatively young age and low glaucoma prevalence of the cohort. The reduced performance observed when including glaucoma suspects may relate to variability and uncertainty in their clinical definition.
- 21 August 2025
- Published by SAGE Publications in European Journal of Ophthalmology
- Vol. 36 (1) , 51-57
Role of cognitive function in the reliability and results of standard automated perimetry
Purpose: To investigate the association between cognitive function and the results and reliability of standard automated perimetry (SAP) in a middle-aged birth cohort. Methods: In this cross-sectional analysis of the prospective birth cohort, the reliability and performance of SAP were evaluated in relation to grade point average (GPA), educational attainment, and scores on the Paired Associates Learning (PAL) test among participants of the Northern Finland Birth Cohort Eye Study. Results: Higher educational level, higher GPA, and fewer errors on the PAL test were consistently associated with better reliability and performance in SAP. However, the observed correlation coefficients were low, and differences between group comparisons were modest, accounting for only a small proportion of the variance in SAP outcomes. Conclusion: While greater cognitive ability is positively associated with SAP performance and reliability, its impact is minimal and unlikely to be clinically significant. Further studies are warranted to determine whether higher cognitive function facilitates glaucoma diagnosis and monitoring through more reliable SAP results, or conversely, whether it may obscure glaucomatous damage by enhancing test performance beyond what is typical.
- 21 August 2025
- Published by SAGE Publications in European Journal of Ophthalmology
- Vol. 36 (1) , 51-57
Role of cognitive function in the reliability and results of standard automated perimetry
Purpose: To investigate the association between cognitive function and the results and reliability of standard automated perimetry (SAP) in a middle-aged birth cohort. Methods: In this cross-sectional analysis of the prospective birth cohort, the reliability and performance of SAP were evaluated in relation to grade point average (GPA), educational attainment, and scores on the Paired Associates Learning (PAL) test among participants of the Northern Finland Birth Cohort Eye Study. Results: Higher educational level, higher GPA, and fewer errors on the PAL test were consistently associated with better reliability and performance in SAP. However, the observed correlation coefficients were low, and differences between group comparisons were modest, accounting for only a small proportion of the variance in SAP outcomes. Conclusion: While greater cognitive ability is positively associated with SAP performance and reliability, its impact is minimal and unlikely to be clinically significant. Further studies are warranted to determine whether higher cognitive function facilitates glaucoma diagnosis and monitoring through more reliable SAP results, or conversely, whether it may obscure glaucomatous damage by enhancing test performance beyond what is typical.
- Open Access
- 11 February 2023
- Published by Wiley in Acta Ophthalmologica
- Vol. 101 (5) , 575-581
Morphology of the optic nerve head and factors affecting it in the Northern Finland birth cohort
Purpose: To assess topographic characteristics of the optic nerve head (ONH) and retinal nerve fibre layer (RNFL) and study the effect of ocular and physiological factors on them in a middle‐aged population.Methods: A 1552‐person randomised sample from Northern Finland population aged 45–49 was examined. Laser scanning tomography and optical coherency tomography were performed to obtain measurements for ONH and RNFL morphology. Measurements of the RNFL included global thickness and the six zones used in automated structure–function analysis (S–F analysis). Influence of central corneal thickness (CCT), refractive correction, intraocular pressure (IOP), anterior chamber angle, gender, blood pressure, height, weight and body mass index (BMI) on tomographic data was analysed.Results: The optic disc area had a strong correlation with all other parameters of ONH morphology (R = 0.261 to 0.706) as did spherical equivalent (R = −0.280 to 0.280). The correlations between ONH and RNFL measurements were weaker (R = 0.057 to 0.180). Gender, CCT, anterior chamber angle, blood pressure, height and BMI had statistically significant, yet feeble, correlations with a number of ONH parameters.Conclusion: Other than spherical equivalent, the studied anatomical and physiological attributes had little predictive value on the ONH morphology. The optic disc area itself had a significant effect on other measurements of ONH tomography and should be taken into consideration when the thresholds for normal ONH morphology are calculated.
- 11 February 2023
- Published by Wiley in Acta Ophthalmologica
- Vol. 101 (5) , 575-581
Open AccessMorphology of the optic nerve head and factors affecting it in the Northern Finland birth cohort
Purpose: To assess topographic characteristics of the optic nerve head (ONH) and retinal nerve fibre layer (RNFL) and study the effect of ocular and physiological factors on them in a middle‐aged population.Methods: A 1552‐person randomised sample from Northern Finland population aged 45–49 was examined. Laser scanning tomography and optical coherency tomography were performed to obtain measurements for ONH and RNFL morphology. Measurements of the RNFL included global thickness and the six zones used in automated structure–function analysis (S–F analysis). Influence of central corneal thickness (CCT), refractive correction, intraocular pressure (IOP), anterior chamber angle, gender, blood pressure, height, weight and body mass index (BMI) on tomographic data was analysed.Results: The optic disc area had a strong correlation with all other parameters of ONH morphology (R = 0.261 to 0.706) as did spherical equivalent (R = −0.280 to 0.280). The correlations between ONH and RNFL measurements were weaker (R = 0.057 to 0.180). Gender, CCT, anterior chamber angle, blood pressure, height and BMI had statistically significant, yet feeble, correlations with a number of ONH parameters.Conclusion: Other than spherical equivalent, the studied anatomical and physiological attributes had little predictive value on the ONH morphology. The optic disc area itself had a significant effect on other measurements of ONH tomography and should be taken into consideration when the thresholds for normal ONH morphology are calculated.
- Open Access
- 10 May 2022
- Published by Wiley in Acta Ophthalmologica
- Vol. 100 (8) , E1657-E1664
Antenatal and neonatal factors and morphology of the optic nerve head in the Northern Finland birth cohort
The optic nerve head (ONH) is a part of the brain that can be evaluated through the transparent medium of the eye. The purpose of this study was to explore the possible correlations among the properties of the optic nerve head, maternal factors during pregnancy and neonatal parameters in a randomized sample of a birth cohort. The Northern Finland 1966 Birth Cohort has been prospectively monitored since their antenatal period. Data on pregnancy and neonatal period were collected during gestation and right after birth in 1966. A randomized sample of 3070 subjects underwent an ophthalmic assessment at the age of 46–48 years. The examination protocol included scanning laser ophthalmoscopy with the Heidelberg Retina Tomograph. The ophthalmological parameters assessed were the disc area and the neuroretinal rim volume of the ONH. We found that chronic pulmonary disease of the mother (p = 0.007), the number of gestational weeks (p = 0.030) and the mother's highest measured systolic blood pressure (p = 0.035) during pregnancy had a statistically significant effect on the disc area. Smaller disc size was associated with pulmonary disease and early gestation. There was a significant difference in rim volume between genders (p < 0.001). Women had larger neuroretinal rim volumes compared to men. In this population‐based study, the vast majority of antenatal and neonatal factors showed no correlation with optic disc area or rim volume. Furthermore, even the factors with statistically significant correlation with ONH morphology had limited predictive value.
- 10 May 2022
- Published by Wiley in Acta Ophthalmologica
- Vol. 100 (8) , E1657-E1664
Open AccessAntenatal and neonatal factors and morphology of the optic nerve head in the Northern Finland birth cohort
The optic nerve head (ONH) is a part of the brain that can be evaluated through the transparent medium of the eye. The purpose of this study was to explore the possible correlations among the properties of the optic nerve head, maternal factors during pregnancy and neonatal parameters in a randomized sample of a birth cohort. The Northern Finland 1966 Birth Cohort has been prospectively monitored since their antenatal period. Data on pregnancy and neonatal period were collected during gestation and right after birth in 1966. A randomized sample of 3070 subjects underwent an ophthalmic assessment at the age of 46–48 years. The examination protocol included scanning laser ophthalmoscopy with the Heidelberg Retina Tomograph. The ophthalmological parameters assessed were the disc area and the neuroretinal rim volume of the ONH. We found that chronic pulmonary disease of the mother (p = 0.007), the number of gestational weeks (p = 0.030) and the mother's highest measured systolic blood pressure (p = 0.035) during pregnancy had a statistically significant effect on the disc area. Smaller disc size was associated with pulmonary disease and early gestation. There was a significant difference in rim volume between genders (p < 0.001). Women had larger neuroretinal rim volumes compared to men. In this population‐based study, the vast majority of antenatal and neonatal factors showed no correlation with optic disc area or rim volume. Furthermore, even the factors with statistically significant correlation with ONH morphology had limited predictive value.
- Open Access
- 20 April 2021
- Published by Taylor & Francis in Ophthalmic Epidemiology
- Vol. 29 (2) , 189-197
Optic Nerve Parameters and Cognitive Function in the Northern Finland Birth Cohort Eye Study
The optic nerve head (ONH) is a part of the brain that can be easily studied through the transparent medium of the eye. We explored the relationship between the properties of the optic nerve head, ...
- 20 April 2021
- Published by Taylor & Francis in Ophthalmic Epidemiology
- Vol. 29 (2) , 189-197
Open AccessOptic Nerve Parameters and Cognitive Function in the Northern Finland Birth Cohort Eye Study
The optic nerve head (ONH) is a part of the brain that can be easily studied through the transparent medium of the eye. We explored the relationship between the properties of the optic nerve head, ...