A Review of Mortality Risk Prediction Models in Smartphone Applications

Development and application of a risk nomogram for the prediction of risk of carbapenem-resistant Acinetobacter baumannii infections in neuro-intensive care unit: a mixed method study

OBJECTIVE

This study aimed to develop and apply a nomogram with good accuracy to predict the risk of CRAB infections in neuro-critically ill patients. In addition, the difficulties and expectations of application such a tool in clinical practice was investigated.

METHODS

A mixed methods sequential explanatory study design was utilized. We first conducted a retrospective study to identify the risk factors for the development of CRAB infections in neuro-critically ill patients; and further develop and validate a nomogram predictive model. Then, based on the developed predictive tool, medical staff in the neuro-ICU were received an in-depth interview to investigate their opinions and barriers in using the prediction tool during clinical practice. The model development and validation is carried out by R. The transcripts of the interviews were analyzed by Maxqda.

RESULTS

In our cohort, the occurrence of CRAB infections was 8.63% (47/544). Multivariate regression analysis showed that the length of neuro-ICU stay, male, diabetes, low red blood cell (RBC) count, high levels of procalcitonin (PCT), and number of antibiotics ≥ 2 were independent risk factors for CRAB infections in neuro-ICU patients. Our nomogram model demonstrated a good calibration and discrimination in both training and validation sets, with AUC values of 0.816 and 0.875. Additionally, the model demonstrated good clinical utility. The significant barriers identified in the interview include "skepticism about the accuracy of the model", "delay in early prediction by the indicator of length of neuro-ICU stay", and "lack of a proper protocol for clinical application".

CONCLUSIONS

We established and validated a nomogram incorporating six easily accessed indicators during clinical practice (the length of neuro-ICU stay, male, diabetes, RBC, PCT level, and the number of antibiotics used) to predict the risk of CRAB infections in neuro-ICU patients. Medical staff are generally interested in using the tool to predict the risk of CRAB, however delivering clinical prediction tools in routine clinical practice remains challenging.

Developing a Comprehensive List of Criteria to Evaluate the Characteristics and Quality of eHealth Smartphone Apps: Systematic Review

BACKGROUND

The field of eHealth is growing rapidly and chaotically. Health care professionals need guidance on reviewing and assessing health-related smartphone apps to propose appropriate ones to their patients. However, to date, no framework or evaluation tool fulfills this purpose.

OBJECTIVE

Before developing a tool to help health care professionals assess and recommend apps to their patients, we aimed to create an overview of published criteria to describe and evaluate health apps.

METHODS

We conducted a systematic review to identify existing criteria for eHealth smartphone app evaluation. Relevant databases and trial registers were queried for articles. Articles were included that (1) described tools, guidelines, dimensions, or criteria to evaluate apps, (2) were available in full text, and (3) were written in English, French, German, Italian, Portuguese, or Spanish. We proposed a conceptual framework for app evaluation based on the dimensions reported in the selected articles. This was revised iteratively in discussion rounds with international stakeholders. The conceptual framework was used to synthesize the reported evaluation criteria. The list of criteria was discussed and refined by the research team.

RESULTS

Screening of 1258 articles yielded 128 (10.17%) that met the inclusion criteria. Of these 128 articles, 30 (23.4%) reported the use of self-developed criteria and described their development processes incompletely. Although 43 evaluation instruments were used only once, 6 were used in multiple studies. Most articles (83/128, 64.8%) did not report following theoretical guidelines; those that did noted 37 theoretical frameworks. On the basis of the selected articles, we proposed a conceptual framework to explore 6 app evaluation dimensions: context, stakeholder involvement, features and requirements, development processes, implementation, and evaluation. After standardizing the definitions, we identified 205 distinct criteria. Through consensus, the research team relabeled 12 of these and added 11 more-mainly related to ethical, legal, and social aspects-resulting in 216 evaluation criteria. No criteria had to be moved between dimensions.

CONCLUSIONS

This study provides a comprehensive overview of criteria currently used in clinical practice to describe and evaluate apps. This is necessary as no reviewed criteria sets were inclusive, and none included consistent definitions and terminology. Although the resulting overview is impractical for use in clinical practice in its current form, it confirms the need to craft it into a purpose-built, theory-driven tool. Therefore, in a subsequent step, based on our current criteria set, we plan to construct an app evaluation tool with 2 parts: a short section (including 1-3 questions/dimension) to quickly disqualify clearly unsuitable apps and a longer one to investigate more likely candidates in closer detail. We will use a Delphi consensus-building process and develop a user manual to prepare for this undertaking.

TRIAL REGISTRATION

PROSPERO International Prospective Register of Systematic Reviews CRD42021227064; https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42021227064.

Quality evaluation of pregnancy-related mobile applications in South Korea: a descriptive study

PURPOSE

This study aimed to describe the characteristics of mobile applications (apps) related to pregnancy in South Korea and evaluate their quality.

METHODS

We conducted a systematic search for pregnancy-related apps available in Korea in two app stores as of April 29, 2022. The quality of apps was assessed using the Korean translation of the Mobile Application Rating Scale for objective quality with four subdomains (engagement, function, aesthetics, and information) and four items for subjective quality.

RESULTS

In total, 163 apps were selected and reviewed. Both the objective and subjective quality of the apps were found to be desirable, with scores exceeding 3 out of 5 (range, 34-82). All subdomain scores in the objective quality assessment were also desirable. Among the four objective quality subdomains, aesthetics received the highest scores, followed by information, function, and engagement. In terms of subjective quality, the scores for a comprehensive overall evaluation, continuous use, and recommendation exceeded 3 out of 5, with the exception of payment. Only a small number of apps (n=4, 2.9%) were backed by a reliable authority, such as an expert review. Significant differences were observed in the objective quality of apps across different content categories (F=3.86, p=.003).

CONCLUSION

Most pregnancy-related apps had desirable levels of objective and subjective quality. However, app content experts seldom provide reviews. It is crucial for nurses to recommend apps to expectant mothers that offer dependable content, regularly updated with the latest information.