Doctoral Thesis
Refine
Document Type
- Doctoral Thesis (2) (remove)
Has Fulltext
- yes (2)
Is part of the Bibliography
- no (2)
Keywords
- Learning (2) (remove)
The thesis is about ideological change of political parties and the way parties gather information, learn by updating their beliefs and ultimately make "rational choices". Analyzing 1451 policy moves of 137 parties in 22 OECD-countries from 1950 to 2013 it is a story about rational learning, about emulating other parties abroad and chasing public opinion. Yet, the "internal life" of a party conditions the effects when activists have some influence over the formation of party policy. As volunteers facing a scarcity of time and resources, members of the party on the ground have a different information horizon, and may arrive at the opposite decision where to move than party elites which (can) rest their decision on a broader set of information resources. In some parties the party on the ground thus constitutes an "internal wall of resistance" to the strategy party elites would choose, if they were free from constraints.
Background: Highly accurate detection of intracranial hemorrhages (ICH) on head computed tomography (HCT) scans can prove challenging at high-volume centers. This study aimed to determine the number of additional ICHs detected by an artificial intelligence (AI) algorithm and to evaluate reasons for erroneous results at a level I trauma center with teleradiology services.
Methods: In a retrospective multi-center cohort study, consecutive emergency non-contrast HCT scans were analyzed by a commercially available ICH detection software (AIDOC, Tel Aviv, Israel). Discrepancies between AI analysis and initial radiology report (RR) were reviewed by a blinded neuroradiologist to determine the number of additional ICHs detected and evaluate reasons leading to errors.
Results: 4946 HCT (05/2020-09/2020) from 18 hospitals were included in the analysis. 205 reports (4.1%) were classified as hemorrhages by both radiology report and AI. Out of a total of 162 (3.3%) discrepant reports, 62 were confirmed as hemorrhages by the reference neuroradiologist. 33 ICHs were identified exclusively via RRs. The AI algorithm detected an additional 29 instances of ICH, missed 12.4% of ICH and overcalled 1.9%; RRs missed 10.9% of ICHs and overcalled 0.2%. Many of the ICHs missed by the AI algorithm were located in the subarachnoid space (42.4%) and under the calvaria (48.5%). 85% of ICHs missed by RRs occurred outside of regular working-hours. Calcifications (39.3%), beam-hardening artifacts (18%), tumors (15.7%), and blood vessels (7.9%) were the most common reasons for AI overcalls. ICH size, image quality, and primary examiner experience were not found to be significantly associated with likelihood of incorrect AI results.
Conclusion: Complementing human expertise with AI resulted in a 12.2% increase in ICH detection. The AI algorithm overcalled 1.9% HCT.
Trial registration: German Clinical Trials Register (DRKS-ID: DRKS00023593).