Development and External Validation of an Early Prognostic Model for Survivors of Out-of-hospital Cardiac Arrest

Recovery and Survival of Patients After Out-of-Hospital Cardiac Arrest: A Literature Review Showcasing the Big Picture of Intensive Care Unit-Related Factors

As an important public health issue, out-of-hospital cardiac arrest (OHCA) requires several stages of high quality medical care, both on-field and after hospital admission. Post-cardiac arrest shock can lead to severe neurological injury, resulting in poor recovery outcome and increased risk of death. These characteristics make this condition one of the most important issues to deal with in post-OHCA patients hospitalized in intensive care units (ICUs). Also, the majority of initial post-resuscitation survivors have underlying coronary diseases making revascularization procedure another crucial step in early management of these patients. Besides keeping myocardial blood flow at a satisfactory level, other tissues must not be neglected as well, and maintaining mean arterial pressure within optimal range is also preferable. All these procedures can be simplified to a certain level along with using targeted temperature management methods in order to decrease metabolic demands in ICU-hospitalized post-OHCA patients. Additionally, withdrawal of life-sustaining therapy as a controversial ethical topic is under constant re-evaluation due to its possible influence on overall mortality rates in patients initially surviving OHCA. Focusing on all of these important points in process of managing ICU patients is an imperative towards better survival and complete recovery rates.

A locally optimised machine learning approach to early prognostication of long-term neurological outcomes after out-of-hospital cardiac arrest

Background

Out-of-hospital cardiac arrest (OHCA) represents a major burden for society and health care, with an average incidence in adults of 67 to 170 cases per 100,000 person-years in Europe and in-hospital survival rates of less than 10%. Patients and practitioners would benefit from a prognostication tool for long-term good neurological outcomes.

Objective

We aim to develop a machine learning (ML) pipeline on a local database to classify patients according to their neurological outcomes and identify prognostic features.

Methods

We collected clinical and biological data consecutively from 595 patients who presented OHCA and were routed to a single regional cardiac arrest centre in the south of France. We applied recursive feature elimination and ML analyses to identify the main features associated with a good neurological outcome, defined as a Cerebral Performance Category score less than or equal to 2 at six months post-OHCA.

Results

We identified 12 variables 24 h after admission, capable of predicting a six-month good neurological outcome. The best model (extreme gradient boosting) achieved an AUC of 0.96 and an accuracy of 0.92 in the test cohort.

Conclusion

We demonstrated that it is possible to build accurate, locally optimised prediction and prognostication scores using datasets of limited size and breadth. We proposed and shared a generic machine-learning pipeline which allows external teams to replicate the approach locally.

Scoring Systems to Predict Survival or Neurological Recovery after Out-of-hospital Cardiac Arrest

Numerous prediction scores have been developed to better inform clinical decision-making following out-of-hospital cardiac arrest (OHCA), however, there is no consensus among clinicians over which score to use. The aim of this review was to identify and compare scoring systems to predict survival and neurological recovery in patients with OHCA. A structured literature search of the MEDLINE database was carried out from inception to December 2021. Studies developing or validating scoring systems to predict outcome following OHCA were selected. Relevant data were extracted and synthesised for narrative review. In total, 16 scoring systems were identified: one predicting the probability of return of spontaneous circulation, six predicting survival to hospital discharge and nine predicting neurological outcome. NULL-PLEASE and CAST are recommended as the best scores to predict mortality and neurological outcome, respectively, due to the extent of external validation, ease of use and high predictive value of the variables. Whether use of these scores can lead to more cost-effective service delivery remains unclear.

Clinical Predictive Models of Sudden Cardiac Arrest: A Survey of the Current Science and Analysis of Model Performances

Background

More than 500 000 sudden cardiac arrests (SCAs) occur annually in the United States. Clinical predictive models (CPMs) may be helpful tools to differentiate between patients who are likely to survive or have good neurologic recovery and those who are not. However, which CPMs are most reliable for discriminating between outcomes in SCA is not known.

Methods and Results

We performed a systematic review of the literature using the Tufts PACE (Predictive Analytics and Comparative Effectiveness) CPM Registry through February 1, 2020, and identified 81 unique CPMs of SCA and 62 subsequent external validation studies. Initial cardiac rhythm, age, and duration of cardiopulmonary resuscitation were the 3 most commonly used predictive variables. Only 33 of the 81 novel SCA CPMs (41%) were validated at least once. Of 81 novel SCA CPMs, 56 (69%) and 61 of 62 validation studies (98%) reported discrimination, with median c‐statistics of 0.84 and 0.81, respectively. Calibration was reported in only 29 of 62 validation studies (41.9%). For those novel models that both reported discrimination and were validated (26 models), the median percentage change in discrimination was −1.6%. We identified 3 CPMs that had undergone at least 3 external validation studies: the out‐of‐hospital cardiac arrest score (9 validations; median c‐statistic, 0.79), the cardiac arrest hospital prognosis score (6 validations; median c‐statistic, 0.83), and the good outcome following attempted resuscitation score (6 validations; median c‐statistic, 0.76).

Conclusions

Although only a small number of SCA CPMs have been rigorously validated, the ones that have been demonstrate good discrimination.