Hanife Saglam
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
Research Subjects
Hanife Saglam has a total of 40 co-authors. Here are the top co-authors by number of shared publications:
Ayhan Bingol
Department of Neurology, İstanbul University Cerrahpaşa- Cerrahpaşa Faculty of Medicine, İstanbul, Turkey
2 shared publicationsDerya Uluduz
Department of Neurology, İstanbul University Cerrahpaşa- Cerrahpaşa Faculty of Medicine, İstanbul, Turkey
2 shared publications- Devrimsel Harika Ertem
Silivri Anadolu Hospital, Department of Pain Management, Istanbul, Türkiye
2 shared publications Z. Habip
2 shared publicationsÖzlem Mercan
Department of Neurology, İstanbul University Cerrahpaşa- Cerrahpaşa Faculty of Medicine, İstanbul, Turkey
2 shared publicationsAgni Orfanoudaki
Operations Research Center, Massachusetts Institute of Technology, Cambridge, Massachusetts, United States of America
1 shared publication
Latest Publications
- Open Access
- 19 June 2020
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 15 (6) , e0234908
Machine learning and natural language processing methods to identify ischemic stroke, acuity and location from radiology reports
Accurate, automated extraction of clinical stroke information from unstructured text has several important applications. ICD-9/10 codes can misclassify ischemic stroke events and do not distinguish acuity or location. Expeditious, accurate data extraction could provide considerable improvement in identifying stroke in large datasets, triaging critical clinical reports, and quality improvement efforts. In this study, we developed and report a comprehensive framework studying the performance of simple and complex stroke-specific Natural Language Processing (NLP) and Machine Learning (ML) methods to determine presence, location, and acuity of ischemic stroke from radiographic text. We collected 60,564 Computed Tomography and Magnetic Resonance Imaging Radiology reports from 17,864 patients from two large academic medical centers. We used standard techniques to featurize unstructured text and developed neurovascular specific word GloVe embeddings. We trained various binary classification algorithms to identify stroke presence, location, and acuity using 75% of 1,359 expert-labeled reports. We validated our methods internally on the remaining 25% of reports and externally on 500 radiology reports from an entirely separate academic institution. In our internal population, GloVe word embeddings paired with deep learning (Recurrent Neural Networks) had the best discrimination of all methods for our three tasks (AUCs of 0.96, 0.98, 0.93 respectively). Simpler NLP approaches (Bag of Words) performed best with interpretable algorithms (Logistic Regression) for identifying ischemic stroke (AUC of 0.95), MCA location (AUC 0.96), and acuity (AUC of 0.90). Similarly, GloVe and Recurrent Neural Networks (AUC 0.92, 0.89, 0.93) generalized better in our external test set than BOW and Logistic Regression for stroke presence, location and acuity, respectively (AUC 0.89, 0.86, 0.80). Our study demonstrates a comprehensive assessment of NLP techniques for unstructured radiographic text. Our findings are suggestive that NLP/ML methods can be used to discriminate stroke features from large data cohorts for both clinical and research-related investigations.
- 19 June 2020
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 15 (6) , e0234908
Open AccessMachine learning and natural language processing methods to identify ischemic stroke, acuity and location from radiology reports
Accurate, automated extraction of clinical stroke information from unstructured text has several important applications. ICD-9/10 codes can misclassify ischemic stroke events and do not distinguish acuity or location. Expeditious, accurate data extraction could provide considerable improvement in identifying stroke in large datasets, triaging critical clinical reports, and quality improvement efforts. In this study, we developed and report a comprehensive framework studying the performance of simple and complex stroke-specific Natural Language Processing (NLP) and Machine Learning (ML) methods to determine presence, location, and acuity of ischemic stroke from radiographic text. We collected 60,564 Computed Tomography and Magnetic Resonance Imaging Radiology reports from 17,864 patients from two large academic medical centers. We used standard techniques to featurize unstructured text and developed neurovascular specific word GloVe embeddings. We trained various binary classification algorithms to identify stroke presence, location, and acuity using 75% of 1,359 expert-labeled reports. We validated our methods internally on the remaining 25% of reports and externally on 500 radiology reports from an entirely separate academic institution. In our internal population, GloVe word embeddings paired with deep learning (Recurrent Neural Networks) had the best discrimination of all methods for our three tasks (AUCs of 0.96, 0.98, 0.93 respectively). Simpler NLP approaches (Bag of Words) performed best with interpretable algorithms (Logistic Regression) for identifying ischemic stroke (AUC of 0.95), MCA location (AUC 0.96), and acuity (AUC of 0.90). Similarly, GloVe and Recurrent Neural Networks (AUC 0.92, 0.89, 0.93) generalized better in our external test set than BOW and Logistic Regression for stroke presence, location and acuity, respectively (AUC 0.89, 0.86, 0.80). Our study demonstrates a comprehensive assessment of NLP techniques for unstructured radiographic text. Our findings are suggestive that NLP/ML methods can be used to discriminate stroke features from large data cohorts for both clinical and research-related investigations.
- Open Access
- 1 January 2020
- Published by Baycinar Tibbi Yayincilik in Ağrı - The Journal of The Turkish Society of Algology
- Vol. 32 (4) , 193-201
Factors Influencing Sexual Functions in Turkish Female Patients with Migraine
Recent studies have shown a more frequent occurrence of sexual dysfunction in patients with headache. The aim of this study was to assess the effects of demographic and clinical characteristics and psychiatric symptoms on sexual dysfunction in Turkish female patients with migraine. In all, 18 sexually active patients with episodic migraine (EM), 12 patients with chronic migraine (CM), and 22 healthy controls of similar age were enrolled in the study. A numeric rating scale was administered to assess pain intensity. The psychiatric symptoms and sexual function of all of the participants were evaluated using the Beck depression and anxiety scales and the Golombok-Rust Inventory of Sexual Satisfaction (GRISS). The mean GRISS subscale scores did not differ significantly between the migraine groups and the control group (all p values <0.05). A positive correlation was found between the duration of headache and GRISS subscales of noncommunication, dissatisfaction, vaginismus, and anorgasmia in EM patients. In addition, there was a negative correlation with the infrequency and avoidance subscales. No correlation was detected between the GRISS subscale scores and the demographic and clinical characteristics of the patients with CM, with the exception of the level of education. Higher pain intensity scores and the presence of anxiety or depression among the EM and CM patients significantly affected all of the subscale scores of the sexual function inventory. Although there was no relationship between migraine chronicity and sexual dysfunction, our data indicated that patient demographic characteristics, greater pain severity, and comorbidities of depression or anxiety were associated with greater sexual dysfunction among patients with EM and CM.
- 1 January 2020
- Published by Baycinar Tibbi Yayincilik in Ağrı - The Journal of The Turkish Society of Algology
- Vol. 32 (4) , 193-201
Open AccessFactors Influencing Sexual Functions in Turkish Female Patients with Migraine
Recent studies have shown a more frequent occurrence of sexual dysfunction in patients with headache. The aim of this study was to assess the effects of demographic and clinical characteristics and psychiatric symptoms on sexual dysfunction in Turkish female patients with migraine. In all, 18 sexually active patients with episodic migraine (EM), 12 patients with chronic migraine (CM), and 22 healthy controls of similar age were enrolled in the study. A numeric rating scale was administered to assess pain intensity. The psychiatric symptoms and sexual function of all of the participants were evaluated using the Beck depression and anxiety scales and the Golombok-Rust Inventory of Sexual Satisfaction (GRISS). The mean GRISS subscale scores did not differ significantly between the migraine groups and the control group (all p values <0.05). A positive correlation was found between the duration of headache and GRISS subscales of noncommunication, dissatisfaction, vaginismus, and anorgasmia in EM patients. In addition, there was a negative correlation with the infrequency and avoidance subscales. No correlation was detected between the GRISS subscale scores and the demographic and clinical characteristics of the patients with CM, with the exception of the level of education. Higher pain intensity scores and the presence of anxiety or depression among the EM and CM patients significantly affected all of the subscale scores of the sexual function inventory. Although there was no relationship between migraine chronicity and sexual dysfunction, our data indicated that patient demographic characteristics, greater pain severity, and comorbidities of depression or anxiety were associated with greater sexual dysfunction among patients with EM and CM.
- 21 March 2019
- Published by SAGE Publications in Clinical Child Psychology and Psychiatry
- Vol. 24 (4) , 767-775
The impact of parental attitudes toward children with primary headaches
There is a lack of data on parental attitudes toward children with primary headaches. The aim of this study is to determine whether there is a relationship between primary headaches and parental attitudes in the pre-adolescent pediatric population. In this cross-sectional study, 195 children with primary headache and 43 healthy children aged 9–16 years were included. A questionnaire for sociodemographic variables, visual analog scale (VAS), Social Anxiety Scale and Depression Inventory for Adolescents and Children, and Parental Attitudes Determining Scale (PATS), which is an attitude measure specifically designed to evaluate psychological adjustment, were administered. Of 195 children (female/male ratio: 89/106, mean age: 12.59 ± 1.09 years), episodic migraine (n = 90), chronic migraine (n = 25), and tension-type headache (n = 80) were evaluated. There was no significant difference among headache groups and healthy subjects in terms of depression, anxiety, and fathers’ attitude scale scores. However, there were significant differences in mean mothers’ attitude scale scores and VAS scores (p = .002, p = .000). Mean oppressive-authoritarian attitude subscale scores of mothers’ was significantly higher in children with chronic migraine (p = .000). A relationship between depression and VAS scores among all patient groups was detected (p = .000). Parental age was negatively related to PATS scores of children with episodic migraine and tension-type headache (p = .037 and p = .036). Parental attitudes may elevate psychiatric symptoms and influence children’s perception of pain intensity and result in chronification of headache. Our findings support that mothers’ attitude toward children with chronic migraine has strong impacts on the child’s pain experience.
- 21 March 2019
- Published by SAGE Publications in Clinical Child Psychology and Psychiatry
- Vol. 24 (4) , 767-775
The impact of parental attitudes toward children with primary headaches
There is a lack of data on parental attitudes toward children with primary headaches. The aim of this study is to determine whether there is a relationship between primary headaches and parental attitudes in the pre-adolescent pediatric population. In this cross-sectional study, 195 children with primary headache and 43 healthy children aged 9–16 years were included. A questionnaire for sociodemographic variables, visual analog scale (VAS), Social Anxiety Scale and Depression Inventory for Adolescents and Children, and Parental Attitudes Determining Scale (PATS), which is an attitude measure specifically designed to evaluate psychological adjustment, were administered. Of 195 children (female/male ratio: 89/106, mean age: 12.59 ± 1.09 years), episodic migraine (n = 90), chronic migraine (n = 25), and tension-type headache (n = 80) were evaluated. There was no significant difference among headache groups and healthy subjects in terms of depression, anxiety, and fathers’ attitude scale scores. However, there were significant differences in mean mothers’ attitude scale scores and VAS scores (p = .002, p = .000). Mean oppressive-authoritarian attitude subscale scores of mothers’ was significantly higher in children with chronic migraine (p = .000). A relationship between depression and VAS scores among all patient groups was detected (p = .000). Parental age was negatively related to PATS scores of children with episodic migraine and tension-type headache (p = .037 and p = .036). Parental attitudes may elevate psychiatric symptoms and influence children’s perception of pain intensity and result in chronification of headache. Our findings support that mothers’ attitude toward children with chronic migraine has strong impacts on the child’s pain experience.
- 1 October 2018
- Published by Elsevier in The European Journal of Psychiatry
- Vol. 32 (4) , 182-186
Self-stigma, depression, and anxiety levels of people living with HIV in Turkey
- 1 October 2018
- Published by Elsevier in The European Journal of Psychiatry
- Vol. 32 (4) , 182-186
Self-stigma, depression, and anxiety levels of people living with HIV in Turkey
- Open Access
- 1 April 2016
- Published by Elsevier in International Journal of Infectious Diseases
- Vol. 45, 263
Anxiety levels of HIV-infected patients after learning their diagnosis: A preliminary study for the first time in Turkey
- 1 April 2016
- Published by Elsevier in International Journal of Infectious Diseases
- Vol. 45, 263
Open AccessAnxiety levels of HIV-infected patients after learning their diagnosis: A preliminary study for the first time in Turkey