MELD-Plus

Last updated
MELD-Plus
Uri Kartoun princeton nov 2018.jpg
Uri Kartoun presenting MELD-Plus at Princeton University, November 2018
PurposeAssess severity of chronic liver disease

MELD-Plus is a risk score to assess severity of chronic liver disease that was resulted from a collaboration between Massachusetts General Hospital and IBM. [1] The score includes nine variables as effective predictors for 90-day mortality after a discharge from a cirrhosis-related admission. The variables include all Model for End-Stage Liver Disease (MELD)'s components, as well as sodium, albumin, total cholesterol, white blood cell count, age, and length of stay.

Contents

Because total cholesterol and hospital length of stay are typically not uniform factors across different hospitals and may vary in different countries, an additional model that included only seven of the nine variables was evaluated. This yielded a performance close to the one of using all nine variables and resulted in the following associations with increased mortality: INR, creatinine, total bilirubin, sodium, WBC, albumin, and age.

The development of MELD-Plus was based on using unbiased approach toward discovery of biomarkers. In this approach, a feature selection machine learning algorithm observes a large collection of health records and identifies a small set of variables that could serve as the most efficient predictors for a given medical outcome. An example for a notable feature selection method is lasso (least absolute shrinkage and selection operator). [2]

Calculators

A calculator capable of comparing MELD, MELD-Na, and MELD-Plus is available. [3]

Calculators capable of calculating MELD and MELD-Na are available. [4] [5] [6] [7]

Press coverage

Johnson HR. Developing a new score: how machine learning improves risk prediction. [8]

Livernois C. Harvard researchers develop predictive model for cirrhosis outcomes. [9]

Goedert J. IBM taps machine learning to predict cirrhosis mortality rates. [10]

Cohen JK. Harvard, IBM researchers develop prediction model for cirrhosis outcomes. [11]

Massachusetts General Hospital (Snapshot of Science). [12]

External validation

A call for an additional validation of MELD-Plus was published in November 2019 in the European Journal of Gastroenterology & Hepatology . [13]

A study presented in June 2019 in Semana Digestiva [14] (Vilamoura, Portugal) demonstrated that MELD-Plus was superior to assess mortality at 180 days vs. other liver-related scores in a population admitted due to hepatic encephalopathy. [15]

A study published in April 2018 in Surgery, Gastroenterology and Oncology reported on the increased accuracy of using MELD-Plus vs. MELD in predicting early acute kidney injury after liver transplantation. [16]

MELD-Plus was validated by using Explorys. [17]

MELD-Plus was proposed as advantageous for patients with low MELD-Na scores. [18]

Potential of alternative scores to extend life expectancy

MELD 3.0 was introduced in 2021. [19] [20] A comparison between MELD 3.0, MELD-Plus, and other risk assessment scores in liver proposes approaches to more optimally allocate livers. [21]

United Network for Organ Sharing proposed that MELD-Na score (an extension of MELD) may better rank candidates based on their risk of pre-transplant mortality and is projected to save 50–60 lives total per year. [22] Furthermore, a study published in the New England Journal of Medicine in 2008, estimated that using MELD-Na instead of MELD would save 90 lives for the period from 2005 to 2006. [23] In his viewpoint published in June 2018, co-creator of MELD-Plus, Uri Kartoun, suggested that "...MELD-Plus, if incorporated into hospital systems, could save hundreds of patients every year in the United States alone." [24]

A review specifying alternatives to MELD, including MELD-Na, MELD-sarcopenia, UKELD, D-MELD, iMELD, and MELD-Plus, was published in June 2019 in Seminars in Liver Disease. [25]

The optimized prediction of mortality (OPOM) score is another tool that has been proposed to serve as an alternative to Model for End-Stage Liver Disease. [26] [27]

A review published in Transplantation in February 2020 highlighted the importance of incorporating machine-learning techniques into liver-related prediction tools, especially within the context of the limited accuracy of MELD-Na when applied to patients with low scores. [28] Transplantation further published a correspondence emphasizing this point. [18]

Criticism of machine learning in prediction modeling

Chen & Asch 2017 wrote: "With machine learning situated at the peak of inflated expectations, we can soften a subsequent crash into a “trough of disillusionment” by fostering a stronger appreciation of the technology's capabilities and limitations." However, the authors further added "Although predictive algorithms cannot eliminate medical uncertainty, they already improve allocation of scarce health care resources, helping to avert hospitalization for patients with low-risk pulmonary embolisms (PESI) and fairly prioritizing patients for liver transplantation by means of MELD scores." [29]

Source code

A sample code for calculating MELD-Plus is available in GitHub. [30]

Related Research Articles

<span class="mw-page-title-main">Hepatitis</span> Inflammation of the liver

Hepatitis is inflammation of the liver tissue. Some people or animals with hepatitis have no symptoms, whereas others develop yellow discoloration of the skin and whites of the eyes (jaundice), poor appetite, vomiting, tiredness, abdominal pain, and diarrhea. Hepatitis is acute if it resolves within six months, and chronic if it lasts longer than six months. Acute hepatitis can resolve on its own, progress to chronic hepatitis, or (rarely) result in acute liver failure. Chronic hepatitis may progress to scarring of the liver (cirrhosis), liver failure, and liver cancer.

<span class="mw-page-title-main">Ascites</span> Abnormal build-up of fluid in the abdomen

Ascites is the abnormal build-up of fluid in the abdomen. Technically, it is more than 25 ml of fluid in the peritoneal cavity, although volumes greater than one liter may occur. Symptoms may include increased abdominal size, increased weight, abdominal discomfort, and shortness of breath. Complications can include spontaneous bacterial peritonitis.

<span class="mw-page-title-main">Hepatocellular carcinoma</span> Medical condition

Hepatocellular carcinoma (HCC) is the most common type of primary liver cancer in adults and is currently the most common cause of death in people with cirrhosis. HCC is the third leading cause of cancer-related deaths worldwide.

<span class="mw-page-title-main">Alcoholic liver disease</span> Medical condition

Alcoholic liver disease (ALD), also called alcohol-related liver disease (ARLD), is a term that encompasses the liver manifestations of alcohol overconsumption, including fatty liver, alcoholic hepatitis, and chronic hepatitis with liver fibrosis or cirrhosis.

<span class="mw-page-title-main">Alcoholic hepatitis</span> Medical condition

Alcoholic hepatitis is hepatitis due to excessive intake of alcohol. Patients typically have a history of at least 10 years of heavy alcohol intake, typically 8-10 drinks per day. It is usually found in association with fatty liver, an early stage of alcoholic liver disease, and may contribute to the progression of fibrosis, leading to cirrhosis. Symptoms may present acutely after a large amount of alcoholic intake in a short time period, or after years of excess alcohol intake. Signs and symptoms of alcoholic hepatitis include jaundice, ascites, fatigue and hepatic encephalopathy. Mild cases are self-limiting, but severe cases have a high risk of death. Severe cases may be treated with glucocorticoids. The condition often comes on suddenly and may progress in severity very rapidly.

<span class="mw-page-title-main">Autoimmune hepatitis</span> Chronic, autoimmune disease of the liver

Autoimmune hepatitis, formerly known as lupoid hepatitis, plasma cell hepatitis, or autoimmune chronic active hepatitis, is a chronic, autoimmune disease of the liver that occurs when the body's immune system attacks liver cells, causing the liver to be inflamed. Common initial symptoms may include fatigue, nausea, muscle aches, or weight loss or signs of acute liver inflammation including fever, jaundice, and right upper quadrant abdominal pain. Individuals with autoimmune hepatitis often have no initial symptoms and the disease may be detected by abnormal liver function tests and increased protein levels during routine bloodwork or the observation of an abnormal-looking liver during abdominal surgery.

<span class="mw-page-title-main">Primary biliary cholangitis</span> Autoimmune disease of the liver

Primary biliary cholangitis (PBC), previously known as primary biliary cirrhosis, is an autoimmune disease of the liver. It results from a slow, progressive destruction of the small bile ducts of the liver, causing bile and other toxins to build up in the liver, a condition called cholestasis. Further slow damage to the liver tissue can lead to scarring, fibrosis, and eventually cirrhosis.

In medicine, specifically gastroenterology, the Child–Pugh score is used to assess the prognosis of chronic liver disease, mainly cirrhosis. Although it was originally used to predict mortality during surgery, it is now used to determine the prognosis, as well as the required strength of treatment and the necessity of liver transplantation.

<span class="mw-page-title-main">Primary sclerosing cholangitis</span> Medical condition

Primary sclerosing cholangitis (PSC) is a long-term progressive disease of the liver and gallbladder characterized by inflammation and scarring of the bile ducts, which normally allow bile to drain from the gallbladder. Affected individuals may have no symptoms or may experience signs and symptoms of liver disease, such as yellow discoloration of the skin and eyes, itching, and abdominal pain.

Spontaneous bacterial peritonitis (SBP) is the development of a bacterial infection in the peritoneum, despite the absence of an obvious source for the infection. It is specifically an infection of the ascitic fluid – an increased volume of peritoneal fluid. Ascites is most commonly a complication of cirrhosis of the liver. It can also occur in patients with nephrotic syndrome. SBP has a high mortality rate.

<span class="mw-page-title-main">Hepatorenal syndrome</span> Human disease

Hepatorenal syndrome is a life-threatening medical condition that consists of rapid deterioration in kidney function in individuals with cirrhosis or fulminant liver failure. HRS is usually fatal unless a liver transplant is performed, although various treatments, such as dialysis, can prevent advancement of the condition.

<span class="mw-page-title-main">Liver biopsy</span>

Liver biopsy is the biopsy from the liver. It is a medical test that is done to aid diagnosis of liver disease, to assess the severity of known liver disease, and to monitor the progress of treatment.

The Model for End-Stage Liver Disease, or MELD, is a scoring system for assessing the severity of chronic liver disease. It was initially developed to predict mortality within three months of surgery in patients who had undergone a transjugular intrahepatic portosystemic shunt (TIPS) procedure, and was subsequently found to be useful in determining prognosis and prioritizing for receipt of a liver transplant. This score is now used by the United Network for Organ Sharing (UNOS) and Eurotransplant for prioritizing allocation of liver transplants instead of the older Child-Pugh score.

<span class="mw-page-title-main">Metabolic dysfunction–associated steatotic liver disease</span> Excessive fat buildup in the liver with other metabolic disease

Metabolic dysfunction–associated steatotic liver disease (MASLD) is the name adopted in 2023 for the condition previously known as non-alcoholic fatty liver disease (NAFLD). This condition is diagnosed when there is excessive fat build-up in the liver, and at least one metabolic risk factor. When there is also moderate alcohol use, the term MetALD is used, and these are differentiated from alcoholic liver disease (ALD) when this is the sole cause of steatotic liver disease. The terms non-alcoholic fatty liver (NAFL) and non-alcoholic steatohepatitis have been used to describe different severities, with the latter indicating the presence of further liver inflammation. NAFL is less dangerous than NASH and usually does not progress towards it, but this progression may eventually lead to complications such as cirrhosis, liver cancer, liver failure, or cardiovascular disease.

<span class="mw-page-title-main">Cirrhosis</span> Chronic disease of the liver, characterized by fibrosis

Cirrhosis, also known as liver cirrhosis or hepatic cirrhosis, and end-stage liver disease, is the impaired liver function caused by the formation of scar tissue known as fibrosis due to damage caused by liver disease. Damage to the liver leads to repair of liver tissue and subsequent formation of scar tissue. Over time, scar tissue can replace normal functioning tissue, leading to the impaired liver function of cirrhosis. The disease typically develops slowly over months or years. Early symptoms may include tiredness, weakness, loss of appetite, unexplained weight loss, nausea and vomiting, and discomfort in the right upper quadrant of the abdomen. As the disease worsens, symptoms may include itchiness, swelling in the lower legs, fluid build-up in the abdomen, jaundice, bruising easily, and the development of spider-like blood vessels in the skin. The fluid build-up in the abdomen may develop into spontaneous infections. More serious complications include hepatic encephalopathy, bleeding from dilated veins in the esophagus, stomach, or intestines, and liver cancer.

In transplantation medicine, the Milan criteria are set of criteria applied in consideration of patients with cirrhosis and hepatocellular carcinoma (HCC) for liver transplantation with intent to cure their disease. Their significance derives from a landmark 1996 study in 48 patients by Mazzaferro et al which showed that selecting cases for transplantation according to specific strict criteria led to improved overall and disease-free survival at a four-year time point. These same criteria have since been adopted by the Organ Procurement and Transplantation Network (OPTN) in the evaluation of patients for potential transplantation.The threshold Milan criteria are as follows:

Thomas D. Schiano is an American specialist in liver transplantation, intestinal transplantation and in the diagnosis and treatment of acute and chronic liver disease. He serves as associate editor for the journals Hepatology and Liver Transplantation and has published more than 200 peer-reviewed articles and abstracts and more than 20 book chapters.

The United Kingdom Model for End-Stage Liver Disease or UKELD is a medical scoring system used to predict the prognosis of patients with chronic liver disease. It is used in the United Kingdom to help determine the need for liver transplantation. It was developed from the MELD score, incorporating the serum sodium level.

A liver support system or diachysis is a type of therapeutic device to assist in performing the functions of the liver. Such systems focus either on removing the accumulating toxins, or providing additional replacement of the metabolic functions of the liver through the inclusion of hepatocytes to the device. This system is in trial to help people with acute liver failure (ALF) or acute-on-chronic liver failure.

<span class="mw-page-title-main">Text nailing</span>

Text Nailing (TN) is an information extraction method of semi-automatically extracting structured information from unstructured documents. The method allows a human to interactively review small blobs of text out of a large collection of documents, to identify potentially informative expressions. The identified expressions can be used then to enhance computational methods that rely on text as well as advanced natural language processing (NLP) techniques. TN combines two concepts: 1) human-interaction with narrative text to identify highly prevalent non-negated expressions, and 2) conversion of all expressions and notes into non-negated alphabetical-only representations to create homogeneous representations.

References

  1. ↑ Kartoun, Uri; Corey, Kathleen E; Simon, Tracey G; Zheng, Hui; Aggarwal, Rahul; Ng, Kenney; Shaw, Stanley Y (2017). "The MELD-Plus: A generalizable prediction risk score in cirrhosis". PLOS ONE. 12 (10): e0186301. Bibcode:2017PLoSO..1286301K. doi: 10.1371/journal.pone.0186301 . PMC   5656314 . PMID   29069090.
  2. ↑ Zou, Hui (December 2006). "The Adaptive Lasso and Its Oracle Properties". Journal of the American Statistical Association. 101 (476): 1418–1429. CiteSeerX   10.1.1.710.7720 . doi:10.1198/016214506000000735. S2CID   13998761.
  3. ↑ MELD-Plus Calculator github.com
  4. ↑ "MELD Score (Model For End-Stage Liver Disease) (12 and older)". MDCalc.
  5. ↑ "MELD calculator - OPTN".
  6. ↑ "MELD Score - Age above 12 years".
  7. ↑ "MELD Na". 19 October 2011.
  8. ↑ "Developing a New Score: How Machine Learning Improves Risk Prediction". 2017-11-17.
  9. ↑ "Harvard researchers develop predictive model for cirrhosis outcomes".
  10. ↑ "IBM taps machine learning to predict cirrhosis mortality rates".
  11. ↑ "Harvard, IBM researchers develop prediction model for cirrhosis outcomes". 31 October 2017.
  12. ↑ "Snapshot of Science for October 2017 - Massachusetts General Hospital, Boston, MA".
  13. ↑ Kartoun, Uri (December 2019). "MELD-plus". European Journal of Gastroenterology & Hepatology. 31 (12): 1603. doi:10.1097/MEG.0000000000001563. PMID   31688253. S2CID   207894016.
  14. ↑ "Semana Digestiva - 2020". semanadigestiva.pt.
  15. ↑ Oliveira, António; Carvão, Joana; Abreu, Nelia; Vitor Pereira; Ladeira, Nuno; Jasmins, Luis (2019). "O Papel DOS Scores de Babs e Meld-Plus Em Doentes Com Encefalopatia Hepática". Figshare. doi:10.6084/m9.figshare.11324060.v1.{{cite journal}}: Cite journal requires |journal= (help)
  16. ↑ Tudoroiu, Marian-Irinel; Constantin, Georgiana; Pâslaru, Liliana; Iacob, Speranţa; Gheorghe, Cristian; Popescu, Irinel; Tomescu, Dana; Simona Gheorghe, Liliana (2018). "The Combination of Serum Cystatin C, Urinary Kidney Injury Molecule-1 and MELD plus Score Predicts Early Acute Kidney Injury after Liver Transplantation". Surgery, Gastroenterology and Oncology. 23 (2): 121. doi: 10.21614/sgo-23-2-121 .
  17. ↑ "IBM Explorys EHR Database Bibliography". ibm.com. Retrieved 24 September 2023.
  18. 1 2 Kartoun, Uri (2020). "Is MELD-Plus Advantageous for Patients with Low MELD-Na Scores?". Transplantation. 104 (6): e182. doi: 10.1097/TP.0000000000003207 . PMID   32433233. S2CID   218768238.
  19. ↑ Kim, W. R.; Mannalithara, A.; Heimbach, J. K.; Kamath, P. S.; Asrani, S. K.; Biggins, S. W.; Wood, N. L.; Gentry, S. E.; Kwong, A. J. (2021). "MELD 3.0: The Model for End-Stage Liver Disease Updated for the Modern Era". Gastroenterology. 161 (6): 1887–1895.e4. doi:10.1053/j.gastro.2021.08.050. PMC   8608337 . PMID   34481845.
  20. ↑ Ge, J.; Kim, W. R.; Lai, J. C.; Kwong, A. J. (2022). ""Beyond MELD" - Emerging strategies and technologies for improving mortality prediction, organ allocation and outcomes in liver transplantation". Journal of Hepatology. 76 (6): 1318–1329. doi:10.1016/j.jhep.2022.03.003. PMC   10286631 . PMID   35589253. S2CID   248851536.
  21. ↑ Kartoun, Uri (2022). "Towards Optimally Replacing the Current Version of MELD". Journal of Hepatology. 78 (3): S0168–8278(22)02946-4. doi:10.1016/j.jhep.2022.07.013. PMID   35870703. S2CID   250944543.
  22. ↑ "Meeting agenda" (PDF). optn.transplant.hrsa.gov. 2014.
  23. ↑ Kim, W. Ray; Biggins, Scott W.; Kremers, Walter K.; Wiesner, Russell H.; Kamath, Patrick S.; Benson, Joanne T.; Edwards, Erick; Therneau, Terry M. (4 September 2008). "Hyponatremia and Mortality among Patients on the Liver-Transplant Waiting List". New England Journal of Medicine. 359 (10): 1018–1026. doi:10.1056/NEJMoa0801209. PMC   4374557 . PMID   18768945.
  24. ↑ Kartoun, Uri (2019). "Toward an accelerated adoption of data-driven findings in medicine". Medicine, Health Care and Philosophy. 22 (1): 153–157. doi:10.1007/s11019-018-9845-y. PMID   29882052. S2CID   46973857.
  25. ↑ Sacleux, Sophie-Caroline; Samuel, Didier (26 June 2019). "A Critical Review of MELD as a Reliable Tool for Transplant Prioritization". Seminars in Liver Disease. 39 (4): 403–413. doi:10.1055/s-0039-1688750. PMID   31242526. S2CID   195694211.
  26. ↑ "OPTN Liver and Intestinal Organ Transplantation Committee Meeting Summary" (PDF). October 22, 2019.
  27. ↑ Bertsimas, Dimitris; Kung, Jerry; Trichakis, Nikolaos; Wang, Yuchen; Hirose, Ryutaro; Vagefi, Parsia A. (6 December 2018). "Development and validation of an optimized prediction of mortality for candidates awaiting liver transplantation". American Journal of Transplantation. 19 (4): 1109–1118. doi: 10.1111/ajt.15172 . hdl: 1721.1/140776 . PMID   30411495.
  28. ↑ Mazumder, N. R.; Atiemo, K.; Kappus, M.; Cullaro, G.; Harinstein, M. E.; Ladner, D.; Verna, E.; Lai, J.; Levitsky, J. (2020). "A Comprehensive Review of Outcome Predictors in Low MELD Patients". Transplantation. 104 (2): 242–250. doi:10.1097/TP.0000000000002956. PMC   6994330 . PMID   31517785.
  29. ↑ Chen, Jonathan H; Asch, Steven M (2017). "Machine Learning and Prediction in Medicine — Beyond the Peak of Inflated Expectations". New England Journal of Medicine. 376 (26): 2507–2509. doi:10.1056/NEJMp1702071. PMC   5953825 . PMID   28657867.
  30. ↑ "kartoun/meld-plus". GitHub. 2018-01-07.
This page is based on this Wikipedia article
Text is available under the CC BY-SA 4.0 license; additional terms may apply.
Images, videos and audio are available under their respective licenses.