Doctor's Orders-Why Radiologists Should Consider Adjusting Commercial Machine Learning Applications in Chest Radiography to Fit Their Specific Needs.

This retrospective study evaluated a commercial deep learning (DL) software for chest radiographs and explored its performance in different scenarios. A total of 477 patients (284 male, 193 female, mean age 61.4 (44.7-78.1) years) were included. For the reference standard, two radiologists performed independent readings on seven diseases, thus reporting 226 findings in 167 patients. An autonomous DL reading was performed separately and evaluated against the gold standard regarding accuracy, sensitivity and specificity using ROC analysis. The overall average AUC was 0.84 (95%-CI 0.76-0.92) with an optimized DL sensitivity of 85% and specificity of 75.4%. The best results were seen in pleural effusion with an AUC of 0.92 (0.885-0.955) and sensitivity and specificity of each 86.4%. The data also showed a significant influence of sex, age, and comorbidity on the level of agreement between gold standard and DL reading. About 40% of cases could be ruled out correctly when screening for only one specific disease with a sensitivity above 95% in the exploratory analysis. For the combined reading of all abnormalities at once, only marginal workload reduction could be achieved due to insufficient specificity. DL applications like this one bear the prospect of autonomous comprehensive reporting on chest radiographs but for now require human supervision. Radiologists need to consider possible bias in certain patient groups, e.g., elderly and women. By adjusting their threshold values, commercial DL applications could already be deployed for a variety of tasks, e.g., ruling out certain conditions in screening scenarios and offering high potential for workload reduction.

Project Report on Telemedicine: What We Learned about the Administration and Development of a Binational Digital Infrastructure Project.

This article describes the development of a German-Polish cross-border telemedicine project. Funded by the European Union Interreg Program, a cooperation between several German and Polish hospitals was developed over the course of 16 years, starting in 2002. Subprojects, governance and outcomes are described, and facilitators and barriers are identified. These points are reviewed with regard to their influence on medical, technical, administrative and medico-legal realisation.

The Accuracy of On-Call CT Reporting in Teleradiology Networks in Comparison to In-House Reporting.

(1) Background: We aimed to compare the accuracy of after-hours CT reports created in a traditional in-house setting versus a teleradiology setting by assessing the discrepancy rates between preliminary and final reports. (2) Methods: We conducted a prospective study to determine the number and severity of discrepancies between preliminary and final reports for 7761 consecutive after-hours CT scans collected over a 21-month period. CT exams were performed during on-call hours and were proofread by an attending the next day. Discrepancies between preliminary and gold-standard reports were evaluated by two senior attending radiologists, and differences in rates were assessed for statistical significance. (3) Results: A total of 7209 reports were included in the analysis. Discrepancies occurred in 1215/7209 cases (17%). Among these, 433/7209 reports (6%) showed clinically important differences between the preliminary and final reports. A total of 335/5509 of them were in-house reports (6.1%), and 98/1700 were teleradiology reports (5.8%). The relative frequencies of report changes were not significantly higher in teleradiology. (4) Conclusions: The accuracy of teleradiology reports was not inferior to that of in-house reports, with very similar clinically important differences rates found in both reporting situations.

Identifying communication-related predictors of patient satisfaction in a briefing prior to contrast-enhanced computed tomography.

BACKGROUND: This study aimed to prospectively investigate patients' satisfaction with briefings before computed tomography (CT) examinations, determine feasibility, and identify factors influencing patient satisfaction independent of patient and physician characteristics. METHODS: One hundred sixty patients received information by a radiologist prior to contrast-enhanced CT examinations in an open, prospective, two-center, cross-sectional study (including the introduction of the radiologist, procedure, radiation exposure, possible side effects, and alternatives). Afterwards, patients and radiologists evaluated the briefing using a standardized questionnaire. Additionally, factors such as age, socioeconomic status, inpatient/outpatient status, length of the radiologist's professional experience, duration of the briefing, clarity of the radiologist's explanations as perceived by patients, and the duration of communication were obtained in this questionnaire. Subsequently, three classes of influencing factors were defined and entered stepwise into a hierarchical regression. RESULTS: Patient satisfaction ratings differed significantly by type of hospitalization, perceived type of communication, and patient gender. Hierarchical regression analysis revealed that perceived clarity was the strongest predictor of patients' satisfaction when controlling for the patient and physician characteristics. CONCLUSIONS: Patients appeared to be satisfied with the briefing prior to CT examination. The mean briefing time (2 min 35 s) seemed feasible. Patients' demographics influenced satisfaction. To improve patients' satisfaction with briefings before contrast-enhanced CT, radiologists should aim to clarify their communication.

[Externally Acquired Radiological Image Data and Reporting for the Clinical Routine, Conference and Boards - Legal Aspects of the Second Opinion in Germany]. / Externe radiologische Aufnahmen und Befunde in der klinischen Routine, Konferenzen und Boards ­ rechtliche Aspekte der Nachbefundung und Zweitmeinung in Deutschland.

BACKGROUND: Because of an increasing number of boards and conferences, the number of second opinion readings of externally acquired image data is growing dramatically. In this review article we intend to give medical and legal recommendations for the documentation and interpretation of externally acquired radiological data for second opinions and board presentations based on German jurisdiction. METHOD: Using the FAQ format as a dialog between radiologists and medical legal experts, we answer the most crucial questions regarding correct documentation and interpretation for externally acquired radiological image data based on an up-to-date literature search. RESULTS: Based on the unity of radiological image data and the corresponding written report according to the radiation protection law, the primary report should be present when composing a second opinion. If the primary external report is not present, this should be mentioned as a limitation. All radiological second opinions should be documented in written form. This is especially important in cases of discrepant findings. Legally, the attending physician is responsible for selecting the radiological opinion. The radiologist should not rely on the written primary report without personal reevaluation. Legally, it would be considered radiological malpractice if the external image data and previous image data are not evaluated personally. CONCLUSION: From a legal point of view, there are explicit recommendations regarding thorough documentation of a second opinion as an independent medical service in all cases.

Externally Acquired Radiological Image Data and Reporting for the Clinical Routine, Conference and Boards - Legal Aspects of the Second Opinion in Germany. / Externe radiologische Aufnahmen und Befunde in der klinischen Routine, Konferenzen und Boards ­ rechtliche Aspekte der Nachbefundung und Zweitmeinung in Deutschland.

BACKGROUND: Because of an increasing number of boards and conferences, the number of second opinion readings of externally acquired image data is growing dramatically. In this review article we intend to give medical and legal recommendations for the documentation and interpretation of externally acquired radiological data for second opinions and board presentations based on German jurisdiction. METHOD: Using the FAQ format as a dialog between radiologists and medical legal experts, we answer the most crucial questions regarding correct documentation and interpretation for externally acquired radiological image data based on an up-to-date literature search. RESULTS: Based on the unity of radiological image data and the corresponding written report according to the radiation protection law, the primary report should be present when composing a second opinion. If the primary external report is not present, this should be mentioned as a limitation. All radiological second opinions should be documented in written form. This is especially important in cases of discrepant findings. Legally, the attending physician is responsible for selecting the radiological opinion. The radiologist should not rely on the written primary report without personal reevaluation. Legally, it would be considered radiological malpractice if the external image data and previous image data are not evaluated personally. CONCLUSION: From a legal point of view, there are explicit recommendations regarding thorough documentation of a second opinion as an independent medical service in all cases. KEY POINTS: · The written external report should be present when composing a second opinion report or case presentation.. · Second opinions or external case interpretations should be documented in written form.. · It is considered malpractice to completely rely on the external written report for a second opinion.. · In discrepant radiological findings the treating physician is responsible for choosing the correct radiological interpretation.. CITATION FORMAT: · Schreyer AG, Rosenberg B, Steinhäuser RT. Externally Acquired Radiological Image Data and Reporting for the Clinical Routine, Conference and Boards - Legal Aspects of the Second Opinion in Germany. Fortschr Röntgenstr 2018; 190: 610 - 615.

Externally Acquired Radiological Data for the Clinical Routine - A Review of the Reimbursement Situation in Germany.

BACKGROUND: Interdisciplinary radiological conferences and boards can improve therapeutic pathways. Because of the reinterpretation and presentation of external image data, which already was read, an additional workload is created which is currently not considered by health care providers. In this review we discuss the ongoing basics and possibilities in health economy for a radiological second opinion for the outpatient and inpatient sector in Germany. METHOD: Based on up-to-date literature and jurisdiction, we discuss the most important questions for the reimbursement for second opinions and conference presentations of external image data in an FAQ format. Additionally, we focus on the recently introduced E-Health law accordingly. RESULTS: Radiological services considering second opinion or board presentation of externally acquired image data are currently not adequately covered by health care providers. In particular, there is no reimbursement possibility for the inpatient sector. Only patients with private insurance or privately paid second opinions can be charged when these patients visit the radiologist directly. CONCLUSION: Currently there is no adequate reimbursement possibility for a radiological second opinion or image demonstrations in clinical conferences. It will be essential to integrate adequate reimbursement by health care providers in the near future because of the importance of radiology as an essential diagnostic and therapeutic medical partner. KEY POINTS: · Currently there is no reimbursement for image interpretation and presentation in boards.. · Second opinions can only be reimbursed for patients with private insurance or privately recompensed.. · The E-Health law allows reimbursement for tele-counsel in very complex situations.. · It will be crucial to integrate radiological second opinion in future reimbursement policies by health care providers.. CITATION FORMAT: · Schreyer AG, Steinhäuser RT, Rosenberg B. Externally Acquired Radiological Data for the Clinical Routine - A Review of the Reimbursement Situation in Germany. Fortschr Röntgenstr 2018; DOI: 10.1055/s-0044-101552.

Teleradiology from the provider's perspective-cost analysis for a mid-size university hospital.

OBJECTIVES: Real costs of teleradiology services have not been systematically calculated. Pricing policies are not evidence-based. This study aims to prove the feasibility of performing an original cost analysis for teleradiology services and show break-even points to perform cost-effective practice. METHODS: Based on the teleradiology services provided by the Greifswald University Hospital in northeastern Germany, a detailed process analysis and an activity-based costing model revealed costs per service unit according to eight examination categories. The Monte Carlo method was used to simulate the cost amplitude and identify pricing thresholds. RESULTS: Twenty-two sub-processes and four staff categories were identified. The average working time for one unit was 55 (x-ray) to 72 min (whole-body CT). Personnel costs were dominant (up to 68 %), representing lower limit costs. The Monte Carlo method showed the cost distribution per category according to the deficiency risk. Avoiding deficient pricing by a likelihood of 90 % increased the cost of a cranial CT almost twofold as compared with the lower limit cost. CONCLUSIONS: Original cost analysis is possible when providing teleradiology services with complex statutory requirements in place. Methodology and results provide useful data to help enhance efficiency in hospital management as well as implement realistic reimbursement fees. KEY POINTS: • Analysis of original costs of teleradiology is possible for a providing hospital • Results discriminate pricing thresholds and lower limit costs to perform cost-effective practice • The study methods represent a managing tool to enhance efficiency in providing facilities • The data are useful to help represent telemedicine services in regular medical fee schedules.