Smart respiratory monitoring: clinical development and validation of the IPI™ (Integrated Pulmonary Index) algorithm

M Ronen, R Weissbrod, F J Overdyk, S Ajizian, M Ronen, R Weissbrod, F J Overdyk, S Ajizian

Abstract

Continuous electronic monitoring of patient respiratory status frequently includes PetCO2 (end tidal CO2), RR (respiration rate), SpO2 (arterial oxygen saturation), and PR (pulse rate). Interpreting and integrating these vital signs as numbers or waveforms is routinely done by anesthesiologists and intensivists but is challenging for clinicians in low acuity areas such as medical wards, where continuous electronic respiratory monitoring is becoming more common place. We describe a heuristic algorithm that simplifies the interpretation of these four parameters in assessing a patient's respiratory status, the Integrated Pulmonary Index (IPI). The IPI algorithm is a mathematical model combining SpO2, RR, PR, and PetCO2 into a single value between 1 and 10 that summarizes the adequacy of ventilation and oxygenation at that point in time. The algorithm was designed using a fuzzy logic inference model to incorporate expert clinical opinions. The algorithm was verified by comparison to experts' scoring of clinical scenarios. The validity of the index was tested in a retrospective analysis of continuous SpO2, RR, PR, and PetCO2 readings obtained from 523 patients in a variety of clinical settings. IPI correlated well with expert interpretation of the continuous respiratory data (R = 0.83, p <<< 0.001), with agreement of -0.5 ± 1.4. Receiver operating curves analysis resulted in high levels of sensitivity (ranging from 0.83 to 1.00), and corresponding specificity (ranging from 0.96 to 0.74), based on IPI thresholds 3-6. The IPI reliably interpreted the respiratory status of patients in multiple areas of care using off-line continuous respiratory data. Further prospective studies are required to evaluate IPI in real time in clinical settings.

Keywords: Capnography; Composite index; IPI; Respiratory compromise; Respiratory monitoring.

Conflict of interest statement

Michal Ronen, Rachel Weissbrod and Sam Ajizian are employed by Medtronic (previously Covidien). Dr. Overdyk has received consulting fees from Medtronic.

Figures

Fig. 1
Fig. 1
IPI algorithm rules. IPI is the intersection point of RR and EtCO2 values, assuming Normal PR and SpO2. Gray areas reflect partial membership in the adjacent range
Fig. 2
Fig. 2
IPI algorithm rules—IPI values adapt to changing SpO2 patient values
Fig. 3
Fig. 3
Cluster diagram showing the distribution of IPI value assignments for 85 cases by 18 medical experts reviewing the adult data, the average of their scores (Avg) and the fuzzy logic inference (FL model). Columns are cases, rows are expert or model. Color range: blue IPI = 10; red IPI = 1
Fig. 4
Fig. 4
ROC plot for detection of clinically significant events using IPI (o—IPI threshold)

References

    1. Overdyk FJ, Carter R, Maddox RR, et al. Continuous oximetry/capnometry monitoring reveals frequent desaturation and bradypnea during patient-controlled analgesia. Anesth Analg. 2007;105:412–418. doi: 10.1213/01.ane.0000269489.26048.63.
    1. D’Arcy Y. Turning the tide on respiratory depression. Nursing. 2013;43(9):38–45. doi: 10.1097/01.NURSE.0000432909.39184.e1.
    1. Weinger MB. Dangers of postoperative opioids. Anesth Patient Saf Found Newsl. 2006-2007;21:61−88. . Accessed June 2015.
    1. Stoelting R, Overdyk F. Essential monitoring strategies to detect clinically significant drug-induced respiratory depression in the postoperative period. . Accessed June 2015.
    1. Jarzyna D, Jungquist CR, Pasero C, et al. American Society for Pain Management Nursing guidelines on monitoring of opioid-induced sedation and respiratory depression. Pain Manag Nurs. 2011;12(3):118–145. doi: 10.1016/j.pmn.2011.06.008.
    1. Joint Commission Sentinel Event Alert: Issue #49, pp 1−4, August 8, 2012. . Accessed June 2015.
    1. ASA Standards for Basic Anesthetic Monitoring Approved by the ASA House of Delegates on October 21, 1986, and last amended on October 20, 2010 with an effective date of July 1, 2011.
    1. Norris PR, Dawant BM. Knowledge-based systems for intelligent patient monitoring and management in critical care environments. In: Bronzino JD, editor. The biomedical engineering handbook, Chap 186. 2. Boca Raton: CRC Press; 1999.
    1. Faust D. The limits of scientific reasoning. Minneapolis: University of Minnesota Press; 1984.
    1. McCarter T, Shaik Z, Scarfo K, Thompson LJ. Capnography monitoring enhances safety of postoperative patient-controlled analgesia. Am Health Drug Benefits. 2008;1(5):28–35.
    1. Tarassenko L, Hann A, Young D. Integrated monitoring and analysis for early warning of patient deterioration. Br J Anaesth. 2006;97(1):64–68. doi: 10.1093/bja/ael113.
    1. Tsoukalas LH, Uhrig RE. Fuzzy and neural approaches in engineering. London: Wiley; 1997.
    1. Dieckmann R, Brownstein D, Gausche-Hill M, editors. Pediatric education for prehospital professionals. Sudbury: Jones & Bartlett, American Academy of Pediatrics; 2000. pp. 43–45.
    1. Behrman R, Kliegman R, Jenson H, editors: Nelson textbook of pediatrics. 17th ed. Elsevier Health; 2003. p. 280–281.
    1. Bland JM, Altman DG. Agreement between methods with multiple observations. J Biopharm Stat. 2007;17:571–582. doi: 10.1080/10543400701329422.
    1. Taenzer AH, Pyke J, Herrick MD, Dodds TM, McGrath SP. A comparison of oxygen saturation data in inpatients with low oxygen saturation using automated continuous monitoring and intermittent manual data charting. Anesth Analg. 2014;118:326–331. doi: 10.1213/ANE.0000000000000049.
    1. American Academy of Pediatrics National Institutes of Health consensus development conference on infantile apnea and home monitoring, Sept 29 to Oct 1, 1986. Pediatrics. 1987;79:292–299.
    1. Lightdale JR, Goldmann DA, Feldman HA, Newburg AR, DiNardo JA, Fox VL. Microstream capnography improves patient monitoring during moderate sedation: a randomized, controlled trial. Pediatrics. 2006;117(6):e1170–e1178. doi: 10.1542/peds.2005-1709.
    1. Vargo JJ, Zuccaro G, Jr, Dumot JA, et al. Automated graphic assessment of respiratory activity is superior to pulse oximetry and visual assessment for the detection of early respiratory depression during therapeutic upper endoscopy. Gastrointest Endosc. 2002;55(7):826–831. doi: 10.1067/mge.2002.124208.
    1. Overdyk F. Improving outcomes in in med-surg patients with opioid induced respiratory depression. Am Nurse Today. 2011;6(11):26–31.
    1. Berkenstadt H, Ben-Menachem E, Herman A, Dach R. An evaluation of the Integrated Pulmonary Index (IPI) for the detection of respiratory events in sedated patients undergoing colonoscopy. J Clin Monit Comput. 2012;26:177–181. doi: 10.1007/s10877-012-9357-x.

Source: PubMed

スポンサーと協力者

医学的状態

薬物療法

3
購読する