FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3215349079> ?p ?o ?g. }

• W3215349079 endingPage "146045822110532" @default.
• W3215349079 startingPage "146045822110532" @default.
• W3215349079 abstract "This study proposes a predictive model that uses structured data and unstructured narrative notes from Electronic Medical Records to accurately identify patients diagnosed with Post-Traumatic Stress Disorder (PTSD). We utilize data from primary care clinicians participating in the Manitoba Primary Care Research Network (MaPCReN) representing 154,118 patients. A reference sample of 195 patients that had their PTSD diagnosis confirmed using a manual chart review of structured data and narrative notes, and PTSD negative patients is used as the gold standard data for model training, validation and testing. We assess structured and unstructured data from eight tables in the MaPCReN namely, patient demographics, disease case, examinations, medication, billing records, health condition, risk factors, and encounter notes. Feature engineering is applied to convert data into proper representation for predictive modeling. We explore serial and parallel mixed data models that are trained on both structured and unstructured data to identify PTSD. Model performances were calculated based on a highly skewed hold-out test dataset. The serial model that uses both structured and text data as input, yielded the highest values in sensitivity (0.77), F-measure (0.76), and AUC (0.88) and the parallel model that uses both structured and text data as the input obtained the highest positive predicted value (PPV) (0.75). Diseases such as PTSD are difficult to diagnose. Information recorded in the chart note over multiple visits of the patients with the primary care physicians has higher predictive power than structured data and combining these two data types can increase the predictive capabilities of machine learning models in diagnosing PTSD. While the deep-learning model outperformed the traditional ensemble model in processing text data, the ensemble classifier obtained better results in ingesting a combination of features obtained from both data types in the serial mixed model. The study demonstrated that unstructured encounter notes enhance a model's ability to identify patients diagnosed with PTSD. These findings can enhance quality improvement, research, and disease surveillance related to PTSD in primary care populations." @default.
• W3215349079 created "2021-12-06" @default.
• W3215349079 creator A5063480277 @default.
• W3215349079 creator A5083579611 @default.
• W3215349079 creator A5086521852 @default.
• W3215349079 creator A5091664289 @default.
• W3215349079 date "2021-10-01" @default.
• W3215349079 modified "2023-10-04" @default.
• W3215349079 title "Diagnosing post-traumatic stress disorder using electronic medical record data" @default.
• W3215349079 cites W1569321962 @default.
• W3215349079 cites W1772122366 @default.
• W3215349079 cites W1832693441 @default.
• W3215349079 cites W1875061881 @default.
• W3215349079 cites W1980199313 @default.
• W3215349079 cites W1980867644 @default.
• W3215349079 cites W2033468884 @default.
• W3215349079 cites W2041674474 @default.
• W3215349079 cites W2077086070 @default.
• W3215349079 cites W2081956352 @default.
• W3215349079 cites W2082614665 @default.
• W3215349079 cites W2087203915 @default.
• W3215349079 cites W2137046787 @default.
• W3215349079 cites W2157394212 @default.
• W3215349079 cites W2164254606 @default.
• W3215349079 cites W2165837041 @default.
• W3215349079 cites W2168376827 @default.
• W3215349079 cites W2302722331 @default.
• W3215349079 cites W2511950764 @default.
• W3215349079 cites W2588815870 @default.
• W3215349079 cites W2625625371 @default.
• W3215349079 cites W2655824372 @default.
• W3215349079 cites W2750853837 @default.
• W3215349079 cites W2753205644 @default.
• W3215349079 cites W2754784771 @default.
• W3215349079 cites W2807596753 @default.
• W3215349079 cites W2887611685 @default.
• W3215349079 cites W2898683220 @default.
• W3215349079 cites W2900533911 @default.
• W3215349079 cites W2915848625 @default.
• W3215349079 cites W2920971207 @default.
• W3215349079 cites W2940907888 @default.
• W3215349079 cites W2961351527 @default.
• W3215349079 cites W2963042536 @default.
• W3215349079 cites W3097271252 @default.
• W3215349079 cites W3165797065 @default.
• W3215349079 doi "https://doi.org/10.1177/14604582211053259" @default.
• W3215349079 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34818936" @default.
• W3215349079 hasPublicationYear "2021" @default.
• W3215349079 type Work @default.
• W3215349079 sameAs 3215349079 @default.
• W3215349079 citedByCount "7" @default.
• W3215349079 countsByYear W32153490792022 @default.
• W3215349079 countsByYear W32153490792023 @default.
• W3215349079 crossrefType "journal-article" @default.
• W3215349079 hasAuthorship W3215349079A5063480277 @default.
• W3215349079 hasAuthorship W3215349079A5083579611 @default.
• W3215349079 hasAuthorship W3215349079A5086521852 @default.
• W3215349079 hasAuthorship W3215349079A5091664289 @default.
• W3215349079 hasBestOaLocation W32153490791 @default.
• W3215349079 hasConcept C105795698 @default.
• W3215349079 hasConcept C111472728 @default.
• W3215349079 hasConcept C119857082 @default.
• W3215349079 hasConcept C124101348 @default.
• W3215349079 hasConcept C126322002 @default.
• W3215349079 hasConcept C138885662 @default.
• W3215349079 hasConcept C154945302 @default.
• W3215349079 hasConcept C185592680 @default.
• W3215349079 hasConcept C190812933 @default.
• W3215349079 hasConcept C195910791 @default.
• W3215349079 hasConcept C198531522 @default.
• W3215349079 hasConcept C2778136018 @default.
• W3215349079 hasConcept C2781252014 @default.
• W3215349079 hasConcept C2908647359 @default.
• W3215349079 hasConcept C33923547 @default.
• W3215349079 hasConcept C40993552 @default.
• W3215349079 hasConcept C41008148 @default.
• W3215349079 hasConcept C43617362 @default.
• W3215349079 hasConcept C45827449 @default.
• W3215349079 hasConcept C71924100 @default.
• W3215349079 hasConcept C75684735 @default.
• W3215349079 hasConcept C9357733 @default.
• W3215349079 hasConcept C99454951 @default.
• W3215349079 hasConceptScore W3215349079C105795698 @default.
• W3215349079 hasConceptScore W3215349079C111472728 @default.
• W3215349079 hasConceptScore W3215349079C119857082 @default.
• W3215349079 hasConceptScore W3215349079C124101348 @default.
• W3215349079 hasConceptScore W3215349079C126322002 @default.
• W3215349079 hasConceptScore W3215349079C138885662 @default.
• W3215349079 hasConceptScore W3215349079C154945302 @default.
• W3215349079 hasConceptScore W3215349079C185592680 @default.
• W3215349079 hasConceptScore W3215349079C190812933 @default.
• W3215349079 hasConceptScore W3215349079C195910791 @default.
• W3215349079 hasConceptScore W3215349079C198531522 @default.
• W3215349079 hasConceptScore W3215349079C2778136018 @default.
• W3215349079 hasConceptScore W3215349079C2781252014 @default.
• W3215349079 hasConceptScore W3215349079C2908647359 @default.
• W3215349079 hasConceptScore W3215349079C33923547 @default.
• W3215349079 hasConceptScore W3215349079C40993552 @default.

• next