The study aims to determine how historical cases of respiratory abnormalities are documented by clinicians in the electronic health records (EHR) of Memorial Hermann Healthcare System (MHHS) inpatient facilities. The knowledge gained from this study will support the design of modern data-driven surveillance approach to continuously collect, monitor and timely recognize postoperative respiratory abnormalities using electronic healthcare recorded data.

• Currently available studies are not clear about avoidable risk factors as actionable tools to reduce patient deterioration triggered by respiratory complications. The lack of this crucial knowledge leads to errors in further cases, and errors in medical documentation leads to limited learning from errors and potentially preventable harm to patients.
• The respiratory measurement is an early indicator of disease, yet many clinicians underestimate its importance and hospitals report a poor level of respiratory rate recordings. As respiratory abnormalities are early markers of patient deterioration, it is hoped that improved and continued data collection and monitoring will have an impact on the nature and timeliness of the response to critical illness. Data concordance plays a major role in documentation quality, especially for data-mining and knowledge extraction analysis, therefore it is essential to address the reliability of 'respiratory abnormalities' labelled data within the Electronic Health Record (EHR) system.
• It is hypothesized that an exploratory analysis of historical medical records by using an advanced algorithm could reveal novel and improved knowledge about the nature of Respiratory Abnormalities. However, the quality, computability, reliability, accuracy and completeness of the data are questionable.
• It's also hypothesized that efficacious and preventive intervention can reduce the increased burden of illness followed by respiratory abnormalities, reduce the enormous number of treatable incidences and be cost-effective when delivered in the real-life clinical environment.

Inclusion Criteria:

The study aims to investigate patient records for all postoperative patients aged 18 years and older undergoing unplanned admission to an intensive care unit (ICU).

Criteria to be Met (ASA = American Society of Anesthesiology Class) Age greater than 18 years old on admission; ASA 1: A normal healthy patient; or ASA 2: A patient with a mild systemic disease; or ASA 3: A patient with a severe systemic disease that is not life-threatening; or ASA 4: A patient with a severe systemic disease that is a constant threat to life; or

Major complication associated with either operating room procedure or anesthesia. Example: Cardiac or circulatory event and/or Cardiac arrest during or within 24 hours of operation or administration of anesthesia; or Acute myocardial infarction (AMI) during or within 48 hours of operation or administration of anesthesia; or Central nervous system event (e.g., CVA, seizures, coma) during or within 48 hours of operation or administration of anesthesia; or Respiratory failure not present prior to the 25th hour of hospitalization or not present before surgery; or

Whichever is earlier, indicated by any of:

the reinstitution of ventilator support following discontinuance after operation; or Continuous ventilator support for more than 7 days following operation; or use of a ventilator postoperatively only.

Exclusion Criteria:

Patient records who are under 18 years of age;

Any surgical or invasive procedure performed as an emergency; or Respiratory abnormality present on admission; ASA 5: A moribund patient who is not expected to survive without the operation. The patient is not expected to survive beyond the next 24 hours without surgery.

ASA 6: A brain-dead patient whose organs are being removed with the intention of transplanting them into another patient.

Sample Size: 50,000 Gender: M - 25,000; F - 25000 approx. Age: 18 and older General Health Status: Respiratory Abnormalities

Total Number of Subjects Projected: It is expected that approximately 75,000 subjects will be enrolled (identified for further review) to produce 50,000 evaluable subjects.