Comparisons between Medicare Mortality, Readmission and Complications

Richard A. Robbins, MD*

Richard D. Gerkin, MD ^‡ 

*Phoenix Pulmonary and Critical Care Research and Education Foundation, Gilbert, AZ

^‡Banner Good Samaritan Medical Center, Phoenix, AZ

Abstract

The Center for Medicare and Medicaid Services (CMS) has been a leading advocate of evidence-based medicine. Recently, CMS has begun adjusting payments to hospitals based on hospital readmission rates and “value-based performance” (VBP). Examination of the association of Medicare bonuses and penalties with mortality rates revealed that the hospitals with better mortality rates for heart attacks, heart failure and pneumonia had significantly greater penalties for readmission rates (p<0.0001, all comparisons). A number of specific complications listed in the CMS database were also examined for their correlations with mortality, readmission rates and Medicare bonuses and penalties. These results were inconsistent and suggest that CMS continues to rely on surrogate markers that have little or no correlation with patient-centered outcomes.

Introduction

Implementation of the Affordable Care Act (ACA) emphasized the use of evidence-based measures of care (1). However, the scientific basis for many of these performance measures and their correlation with patient-centered outcomes such as mortality, morbidity, length of stay and readmission rates have been questioned (2-6). Recently, CMS has begun adjusting payments based on readmission rates and “value-based performance” (VBP) (7). Readmission rates and complications are based on claims submitted by hospitals to Medicare (8).

We sought to examine the correlations between mortality, hospital readmission rates, complications and adjustments in Medicare reimbursement. If the system of determining Medicare reimbursements is based on achievement of better patient outcomes, then one hypothesis is that lower readmission rates would be associated with lower mortality.  An additional hypothesis is that complications would be inversely associated with both mortality and readmission rates. 

Methods

Hospital Compare

Data was obtained from the CMS Hospital Compare website from December 2012-January 2013 (8). The data reflects composite data of all hospitals that have submitted claims to CMS. Although a number of measures are listed, we recorded only readmissions, complications and deaths since many of the process of care measures have not been shown to correlate with improved outcomes. Patient satisfaction was not examined since higher patient satisfaction has been shown to correlate with higher admission rates to the hospital, higher overall health care expenditures, and increased mortality (9). In some instances data are presented in Hospital Compare as higher, lower or no different from the National average. In this case, scoring was done 2, 0 and 1 respectively with 0=higher, 2=lower and 1=no different.

Mortality

Mortality was obtained from Hospital Compare and is the 30-day estimates of deaths from any cause within 30 days of a hospital admission for patients hospitalized for heart attack, heart failure, or pneumonia regardless of whether the patient died while still in the hospital or after discharge. The mortality and rates are adjusted for patient characteristics including the patient’s age, gender, past medical history, and other diseases or conditions (comorbidities) the patient had at hospital arrival that are known to increase the patient’s risk of dying.

Readmission Rates

Similarly, the readmission rates are 30-day estimates of readmission for any cause to any acute care hospital within 30 days of discharge. These measures include patients who were initially hospitalized for heart attack, heart failure, and pneumonia. Similar to mortality, the readmission measures rates are adjusted for patient characteristics including the patient’s age, gender, past medical history, and other diseases or conditions (comorbidities) the patient had at hospital arrival that are known to increase the patient’s risk for readmission.

Complications

CMS calculates the rate for each complication by dividing the actual number of self-reported outcomes at each hospital by the number of eligible discharges for that measure at each hospital, multiplied by 1,000. The composite value reported on Hospital Compare is the weighted averages of the component indicators.  The measures of serious complications reported are risk adjusted to account for differences in hospital patients’ characteristics. In addition, the rates reported on Hospital Compare are “smoothed” to reflect the fact that measures for small hospitals are measured less accurately (i.e., are less reliable) than for larger hospitals.

CMS calculates the hospital acquired infection data from the claims hospitals submit to Medicare. The rate for each hospital acquired infection measure is calculated by dividing the number of infections that occur within any given eligible hospital by the number of eligible Medicare discharges, multiplied by 1,000. The hospital acquired infection rates were not risk adjusted by CMS.

In addition to the composite data, individual complications listed in the CMS database were examined (Table 1).

Table 1. Complications examined that are listed in CMS data base.

Objects Accidentally Left in the Body After Surgery

Air Bubble in the Bloodstream

Mismatched Blood Types

Severe Pressure Sores (Bed Sores)

Falls and Injuries

Blood Infection from a Catheter in a Large Vein

Infection from a Urinary Catheter

Signs of Uncontrolled Blood Sugar

Medicare Bonuses and Penalties

The CMS data was obtained from Kaiser Health News which had compiled the data into an Excel database (10).

Statistical Analysis

Data was reported as mean + standard error of mean (SEM). Outcomes between hospitals rated as better were compared to those of hospitals rated as average or worse using Student’s t-test. The relationship between continuous variables was obtained using the Pearson correlation coefficient. Significance was defined as p<0.05. All p values reported are nominal, with no correction for multiple comparisons.

Results

A large database was compiled for the CMS outcomes and each of the hospital ratings (Appendix 1). There were over 2500 hospitals listed in the database.

Mortality and Readmission Rates

A positive correlation for heart attack, heart failure and pneumonia was found between hospitals with better mortality rates (p<0.001 all comparisons). In other words, hospitals with better mortality rates for heart attack tended to be better mortality performers for heart failure and pneumonia, etc.  Surprisingly, the hospitals with better mortality rates for heart attack, heart failure and pneumonia had higher readmission rates for these diseases (p<0.001, all comparisons).

Examination of the association of Medicare bonuses and penalties with mortality rates revealed that the hospitals with better mortality rates for heart attacks, heart failure and pneumonia received the same compensation for value-based performance as hospitals with average or worse mortality rates (Appendix 2, p>0.05, all comparisons). However, these better hospitals had significantly larger penalties for readmission rates (Figure 1, p<0.0001, all comparisons). 

Figure 1.  Medicare bonuses and penalties for readmission rates of hospitals with better, average or worse mortality for myocardial infarction (heart attack, Panel A), heart failure (Panel B), and pneumonia (Panel C).

Because total Medicare penalties are the average of the adjustment for VBP and readmission rates, the reduction in reimbursement was reflected with higher total penalty rates for hospitals with better mortality rates for heart attacks, heart failure and pneumonia (Figure 2 , p<0.001, all comparisons).

Figure 2.  Total Medicare bonuses and penalties for readmission rates of hospitals with better, average or worse mortality for myocardial infarction (heart attack, Panel A), heart failure (Panel B), and pneumonia (Panel C).

Mortality Rates and Complications

The rates of a number of complications are also listed in the CMS database (Table 1). A correlation was performed for each complication compared to the hospitals with better, average or worse death and readmission rates for heart attacks, heart failure and pneumonia (Appendix 3). A positive correlation of hospitals with better mortality rates was only observed for falls and injuries in the hospitals with better death rates from heart failure (p<0.02). However, severe pressure sores also differed in the hospitals with better mortality rates for heart attack and heart failure, but this was a negative correlation (p<0.05 both comparisons). In other words, hospitals that performed better in mortality performed worse in severe pressure sores. Similarly, hospitals with better mortality rates for heart failure had higher rates of blood infection from a catheter in a large vein compared to hospitals with an average mortality rate (p<0.001). None of the remaining complications differed.

Readmission Rates and Complications

A correlation was also performed between complications and hospitals with better, average and worse readmission rates for myocardial infarction, heart failure, and pneumonia (Appendix 4). Infections from a urinary catheter and falls and injuries were more frequent in hospitals with better readmission rates for myocardial infarction, heart failure, and pneumonia compared to hospitals with the worse readmission rates (p<0.02, all comparisons). Hospitals with better readmission rates for heart failure also had higher infections from a urinary catheter compared to hospitals with average readmission rates for heart failure (p<0.001). None of the remaining complications significantly differed 

Discussion

The use of “value-based performance” (VBP) has been touted as having the potential for improving care, reducing complications and saving money. However, we identified a negative correlation between deaths and readmissions, i.e., those hospitals with the better mortality rates were receiving larger financial penalties for readmissions and total compensation. Furthermore, correlations of hospitals with better mortality and readmission rates with complications were inconsistent.

Our data compliments and extends the observations of Krumholz et al. (11). These investigators examined the CMS database from 2005-8 for the correlation between mortality and readmissions. They identified an inverse correlation between mortality and readmission rates with heart failure but not heart attacks or pneumonia. However, with the financial penalties now in place for readmissions, it now seems likely hospital practices may have changed.

CMS compensating hospitals for lower readmission rates is disturbing since higher readmission rates correlated with better mortality. This equates to rewarding hospitals for practices leading to lower readmission rates but increase mortality. The lack of correlation for the other half of the payment adjustment, so called “value-based purchasing” is equally disturbing since if apparently has little correlation with patient outcomes.

Although there is an inverse correlation between mortality and readmissions, this does not prove cause and effect. The causes of the inverse association between readmissions and mortality rates are unclear, but the most obvious would be that readmissions may benefit patient survival. The reason for the lack of correlation between mortality and readmission rates with most complication rates is also unclear. VBP appears to rely heavily on complications that are generally infrequent and in some cases may be inconsequential. Furthermore, many of the complications are for all intents and purposes self-reported by the hospitals to CMS since they are based on claims data. However, the accuracy of these data has been called into question (12,13). Meddings et al. (13) studied urinary tract infections. According to Meddings, the data were “inaccurate” and not were “not valid data sets for comparing hospital acquired catheter-associated urinary tract infection rates for the purpose of public reporting or imposing financial incentives or penalties”. The authors proposed that the nonpayment by Medicare for “reasonably preventable” hospital-acquired complications resulted in this discrepancy. Inaccurate data may lead to the lack of correlation a complication and outcomes on the CMS database.

According to the CMS website the complications were chosen by “wide agreement from CMS, the hospital industry and public sector stakeholders such as The Joint Commission (TJC) , the National Quality Forum (NQF), and the Agency for Healthcare Research and Quality (AHRQ) , and hospital industry leaders” (7). However, some complications such as air bubble in the bloodstream or mismatched blood types are quite rare. Others such as signs of uncontrolled blood sugar are not evidence-based (14). Other complications actually correlated with improved mortality or readmission rates. It seems likely that some of the complications might represent more aggressive treatment or could reflect increased clinical care staffing which has previously been associated with better survival (14,15). 

There are several limitations to our data. First and foremost, the data are derived from CMS Hospital Compare where the data has been self-reported by hospitals. The validity and accuracy of the data has been called into question (12,13). Second, data are missing in multiple instances. For example, data from Maryland were not present. There were multiple instances when the data were “unavailable” or the “number of cases are too small”. Third, in some instances CMS did not report actual data but only higher, lower or no different from the National average. Fourth, much of the data are from surrogate markers, a fact which is puzzling when patient-centered outcomes are available. In addition, some of these surrogate markers have not been shown to correlate with outcomes.

It is unclear if CMS Hospital Compare should be used by patients or healthcare providers when choosing a hospital. At present it would appear that the dizzying array of data reported overrelies on surrogate markers which are possibly inaccurate. Lack of adequate outcomes data and even obfuscating the data by reporting the data as average, below or above average does little to help shareholders interpret the data. The failure to apparently incorporate mortality rates as a component of VBP is another major limitation. The accuracy of the data is also unclear. Until these shortcomings can be improved, we cannot recommend the use of Hospital Compare by patients or providers.

References

1. Obama B. Securing the future of American health care. N Engl J Med. 2012; 367:1377-81.
2. Showalter JW, Rafferty CM, Swallow NA, Dasilva KO, Chuang CH. Effect of standardized electronic discharge instructions on post-discharge hospital utilization. J Gen Intern Med. 2011;26(7):718-23.
3. Heidenreich PA, Hernandez AF, Yancy CW, Liang L, Peterson ED, Fonarow GC. Get With The Guidelines program participation, process of care, and outcome for Medicare patients hospitalized with heart failure. Circ Cardiovasc Qual Outcomes. 2012 ;5(1):37-43.
4. Hurley J, Garciaorr R, Luedy H, Jivcu C, Wissa E, Jewell J, Whiting T, Gerkin R, Singarajah CU, Robbins RA. Correlation of compliance with central line associated blood stream infection guidelines and outcomes: a review of the evidence. Southwest J Pulm Crit Care. 2012;4:163-73.
5. Robbins RA, Gerkin R, Singarajah CU. Relationship between the Veterans Healthcare Administration Hospital Performance Measures and Outcomes. Southwest J Pulm Crit Care 2011;3:92-133.
6. Padrnos L, Bui T, Pattee JJ, Whitmore EJ, Iqbal M, Lee S, Singarajah CU, Robbins RA. Analysis of overall level of evidence behind the Institute of Healthcare Improvement ventilator-associated pneumonia guidelines. Southwest J Pulm Crit Care. 2011;3:40-8.
7. http://www.medicare.gov/HospitalCompare/Data/linking-quality-to-payment.aspx (accessed 4/8/13).
8. http://www.medicare.gov/hospitalcompare/ (accessed 4/8/13).
9. Fenton JJ, Jerant AF, Bertakis KD, Franks P. The cost of satisfaction: a national study of patient satisfaction, health care utilization, expenditures, and mortality. Arch Intern Med. 2012;172:405-11.
10. http://capsules.kaiserhealthnews.org/wp-content/uploads/2012/12/Value-Based-Purchasing-And-Readmissions-KHN.csv (accessed 4/8/13).
11. Krumholz HM, Lin Z, Keenan PS, Chen J, Ross JS, Drye EE, Bernheim SM, Wang Y, Bradley EH, Han LF, Normand SL. Relationship between hospital readmission and mortality rates for patients hospitalized with acute myocardial infarction, heart failure, or pneumonia. JAMA. 2013;309(6):587-93. doi: 10.1001/jama.2013.333.
12. Robbins RA. The emperor has no clothes: the accuracy of hospital performance data. Southwest J Pulm Crit Care. 2012;5:203-5.
13. Meddings JA, Reichert H, Rogers MA, Saint S, Stephansky J, McMahon LF. Effect of nonpayment for hospital-acquired, catheter-associated urinary tract infection: a statewide analysis. Ann Intern Med. 2012;157:305-12.
14. NICE-SUGAR Study Investigators. Intensive versus conventional insulin therapy in critically ill patients. N Engl J Med. 2009;360:1283-97.
15. Robbins RA, Gerkin R, Singarajah CU. Correlation between patient outcomes and clinical costs in the va healthcare system. Southwest J Pulm Crit Care. 2012;4:94-100.

Reference as: Robbins RA, Gerkin RD. Comparisons between Medicare mortality, morbidity, readmission and complications. Southwest J Pulm Crit Care. 2013;6(6):278-86. PDF

Profiles in Medical Courage: Joseph Goldberger, the Sharecropper’s Plague, Science and Prejudice

“You must accept the truth from whatever source it comes”. -Maimonides

The Sharecropper’s Plague

In the early half of the twentieth century a mysterious disease, “the sharecropper’s plague”, reached epidemic proportions in the Southern US (1). Each state decided whether it would recognize and publicly admit the existence of what was then considered an embarrassment. The total number of new annual cases was estimated as about 75,000 in 1915 and about 100,000 throughout the 1920s (2). The disease had a 40% mortality rate, and many survivors with dementia were confined to mental institutions (3). Patients initially presented with symmetrically reddened skin, similar to that produced by a sunburn or poison oak. Later, the dermatitis turned rough and scaly in one or more locations, such as the hands, the tops of the feet, or the ankles, or in a butterfly-shaped distribution across the nose. Disturbances of the digestive tract and the nervous system occurred as late manifestations. This led to the plague being characterized by 4 D’s: dermatitis, diarrhea, dementia and death. In case you have not guessed, the “sharecropper’s plague” was pellagra.

“Pellagraphobia" developed as the disease acquired a social stigma that left victims and their families ostracized (4). Many hospitals refused admittance to patients with pellagra and many staff refused to care for them. Quarantine was common and elementary schools tried to bar children whose family members had pellagra (5). The cause of the disease was unknown. A number of etiologies were proposed including infection; the eating of moldy corn; inherited susceptibility; heavy exposure to sunlight; and exposure to cottonseed oil (2). There were more than 200 proposed "cures" for pellagra included diet, arsenic, castor oil, quinine, strychnine, and the healing waters of mineral springs (5).

In response the US Surgeon General, Walter Wyman, appointed a seven-man commission headed by Dr. Claude H. Lavinder to find the etiologic agent and perhaps identify an insect vector. Lavinder toured affected areas and established a small laboratory at the South Carolina Hospital for the Insane where he injected rabbits, chickens, and guinea pigs with blood, spinal fluid, and spleen pulp from fatal cases of pellagra, without results. In 1911, he set up a larger laboratory at the Marine Hospital in Savannah and unsuccessfully attempted to transmit the causative agent to monkeys. The Commission conducted a survey of pellagra cases in the cotton mill districts in South Carolina where it was especially common. In its 1914 report, the commission concluded that pellagra had no relation to diet, that it spread most rapidly where sanitary disposal of waste was poorest, and that the disease occurred almost exclusively in people who lived in or next to the house of another person with pellagra (6). The general consensus was that pellagra was likely infectious. These conclusions are not surprising since the early twentieth century was an era when infections were being discovered as the causes of many diseases such as yellow fever, dengue fever, typhus, typhoid fever, lobar pneumonia, tuberculosis, cerebrospinal meningitis, syphilis, cholera, malaria, dysentery, scarlet fever, tetanus, and diphtheria. Pellagra was viewed as just another of those diseases with an as yet undiscovered pathogen.

Goldberger’s Investigations

Human Observations and Dietary Interventions

When Lavinder asked to be reassigned in 1914, he was replaced by Joseph Goldberger.

Figure 1. Dr. Joseph Goldberger

Goldberger spent his first 3 weeks in the South, directly observing patients with pellagra and their living environment. He summarized his observations with a report and hypothesis (8).  He stated that pellagra was: 1) present almost exclusively in rural areas; 2) associated with poverty; 3) associated with a relatively cheap and filling diet consisting of the "three M's", meat (fatback), meal (corn meal), and molasses; and 4) not acquired by nurses, attendants, or employees in hospitals or orphanages whose inpatients had the disease. The last finding seemed particularly incompatible with an infectious cause. Goldberger hypothesized that the staff's peculiar exemption from or immunity to the disease could be explained by a difference in diet.

To prove his hypothesis, Goldberger tried to prevent and cure pellagra by dietary interventions. In two orphanages having high rates of endemic pellagra he identified 172 patients with pellagra and 168 children who were initially free of disease (8). He arranged for both groups of to receive a new, more varied diet, subsidized by Federal funds. The results were evident in just a few weeks: No new cases of pellagra occurred and almost all children with pellagra were cured. After a year, the two orphanages had only one case of recurrent pellagra.

Goldberger then repeated the study in a mental asylum, using a randomized, controlled trial (9). Of 72 patients with pellagra, all were cured after the introduction of the new diet. The treatment group had a high drop-out rate, however, because some patients' mental status improved so greatly that they were permitted to leave the asylum. In the group on the old diet, the recurrence rate of pellagra was almost 50%. Interestingly, when the Federal subsidies expired at the end of these studies, the diets returned to the old three M's diet and 40% of the inmates again developed pellagra.

Goldberger then began a new study to induce pellagra by dietary deprivation (10). In a prison where pellagra had never been reported, a dozen volunteers were promised full pardons at the experiment's end for eating an experimental diet. The diet consisted largely of cereal and included biscuits, gravy, cornbread, grits, rice, syrup, collard greens, and yams. By the end of the 9 month study, 7 of the 12 inmates were diagnosed with pellagra. In all instances, resumption of a better diet resulted in cure.

To refute the theory that pellagra was infectious, Goldberger injected blood from patients with pellagra into the deltoids of healthy volunteers, including himself and his wife (11). He also mixed extracts of skin parings, nasal secretions, urine, and feces from patients with pellagra into a wheat dough concoction that was swallowed by all volunteers. These "filth party" experiments were repeated seven times. No signs of pellagra developed in the volunteers.

Demographic Studies

Goldberger next studied the basic demographics, socioeconomic status, and diet of patients with pellagra (12,13). In these surveys, Goldberger found that a poor year in cotton production was usually followed by an increase pellagra mortality (13). He showed an inverse relationship between socioeconomic status and the incidence of pellagra. Goldberger also found a significant correlation between the rise and fall in the price of animal protein foods and the disease's onset and remission (12,13). These data further supported his hypothesis that pellagra was caused by a dietary deficiency.

Laboratory Studies

Goldberger hypothesized that pellagra was caused by an amino acid deficiency, possibly tryptophan, based on his demographic and human studies. Goldberger soon realized that ordinary yeast contained and was the most potent source of the pellagra-preventive factor in rats and in dogs (14). In 1927 he arranged to have the Red Cross ship large quantities of yeast into flood-stricken areas along the Mississippi river (15). The expected outbreak of pellagra did not occur; instead, the disease fell below its usual seasonal incidence. After the emergency, yeast was no longer provided, and the usual level of pellagra returned to the area. Goldberger died in 1929 before he could find a specific pellagra cure.

In 1937 nicotinic acid or niacin was found to cure pellagra in dogs (16). This finding was soon confirmed for human pellagra (17). The final, almost complete elimination of pellagra dates to the 1940s coinciding with improvements in diet and a requirement by many states to enrich food with vitamins including niacin (18). What provoked the epidemic at the beginning of the twentieth century is not entirely clear. However, changes in the methods of milling corn may have led to the outbreak, because the germ or embryo in the corn kernel is removed in the new milling process begun at the turn of the century. The kernel contains a high proportion of lipid, enzymes, and cofactors, including nicotinic acid (19).

Politics and Pellagra

Goldberger investigations are exceptional. He performed community observation, clinical investigation, and laboratory investigations that led to the elimination of a common health problem. Yet, his extraordinary accomplishments are largely unrecognized. Politics and prejudice seem to be largely responsible for Goldberger’s obscurity.

Politics apparently had great influence on pellagra public policy. An association of pellagra with poverty was clear, and offended Southern pride where the disease was concentrated. When the epidemiologic studies of Goldberger, a Northerner, an immigrant, and a Jew pointed to social and economic factors as being responsible for the occurrence of pellagra, Southern sensitivities were further riled. Editorial pages and speeches by congressmen criticized and condemned such insulting inferences concerning the contentment of the people of the South (2).

When a letter from Goldberger to the Surgeon General describing the extent of pellagra and its relationship to poverty and poor diet reached the press; it stimulated the newly inaugurated president, Warren Harding, to write the Surgeon General asking for a complete report. Harding suggested that the Red Cross provide aid, and offered to ask for a congressional appropriation (2). This infuriated a number of influential Southern politicians including Congressman James F. Byrnes (later U.S. Senator, Secretary of State, and Supreme Court Justice). He called the news reports of "famine and plague" in South Carolina an "utter absurdity," calling for rejection of offers of aid from the Red Cross. A Georgia city wired one of their senators, Tom Watson, "When this part of Georgia suffers from famine, the rest of the world will be dead!" (20). The United Daughters of the Confederacy at first voted to thank President Harding for his concern, but a month later it sent him a letter of protest. "Famine does not exist anywhere in the South," their letter stated, "and we fail to find a general increase in pellagra" (20). Since pellagra was common in Italy, Italian immigrants were blamed for the outbreak of the disease (2). No one seemed to notice that the Italians living in the South did not have pellagra, since they did not favor the meat, meal and molasses diet that led to the disease.

Goldberger’s Legacy

Goldberger died in 1929 of renal cell carcinoma not having convinced public health officials of a dietary cause of pellagra. Goldberger should be remembered not only for his superb investigations but for formulating a hypothesis, testing it and not surrendering to insults of his heritage or religion. Although rarely remembered in medical textbooks, he has been immortalized in some unlikely places including “Real Life Comics” in 1941 (Figure 2).

Figure 2. Joseph Goldberger in “Real Life Comics”.

Figure 2. Joseph Goldberger in “Real Life Comics”.

In some aspects Goldberger’s story is echoed in modern day politics where politicians attempt to manipulate or deny scientific discovery to further their own political careers. Even when Goldberger showed that affordable therapy with yeast cured pellagra, many Southern politicians remained reticent to accept diet as a cause of the disease. Their ambitions undoubtedly contributed to the excess mortality and morbidity of thousands of impoverished Southerners in the early twentieth century.

References

1. Elmore JG, Feinstein AR. Joseph Goldberger: An unsung hero of American clinical epidemiology. Ann Intern Med 1994;121:372-37.
2. Bollet AJ. Politics and pellagra: the epidemic of pellagra in the U.S. in the early twentieth century. Yale J Biol Med 1992;65:211-21.
3. Lavinder CH. The prevalence and geographic distribution of pellagra in the United States. Public Health Rep 1912;27:2076-88.
4. Niles GM. Pellagraphobia: A word of caution. JAMA 1912;58:1341.
5. Etheridge EW. The Butterfly Caste: A Social History of Pellagra in the South. Westport, CT: Greenwood Publishing Company; 1972.
6. Siler JF, Garrison PE, MacNeal WJ. Pellagra, a summary of the first progress report of the Thompson-McFadden Pellagra Commission. JAMA 1914;62:8-12.
7. Parsons RP (1943). Trail to light: A biography of Joseph Goldberger. Bobbs-Merrill. ASIN B0007DYTFM.
8. Goldberger J. The etiology of pellagra: The significance of certain epidemiological observations with respect thereto. Public Health Rep1914;29:1683-86.
9. Goldberger J, Waring CH, Tanner WF. Pellagra prevention by diet among institutional inmates. Public Health Rep 1923;38:2361-68.
10. Goldberger J, Wheeler GA. The experimental production of pellagra in human subjects by means of diet. Hygienic Laboratory Bulletin 1920;120:7-116.
11. Goldberger J. The transmissibility of pellagra: Experimental attempts at transmission to human subjects. Public Health Rep. 1916;31:3159-73.
12. Goldberger J, Wheeler GA, Sydenstricker E. A study of the diet of nonpellagrin and of pellagrin households. JAMA 1918;71:944-9.
13. Sydenstricker E, Wheeler GA, Goldberger J. Disabling sickness among the population of seven cotton-mill villages of South Carolina in relation to family income. Public Health Rep. 1918;33:2038-51.
14. Goldberger JG, Wheeler GA, Lillie RD, Rogers LM. A further study of butter, fresh beef and yeast as pellagra preventives, with consideration of the relation of factor P-P of pellagra (and black tongue of dogs) to vitamin B. Public Health Rep 1926;41:297-318.
15. Goldberger JG, Sydenstricker E. Pellagra in the Mississippi flood area. Public Health Rep 1927;42:2706-25.
16. Elvehjem CA, Madden RJ, Strong FM, Wooley DW. Relation of nicotinic acid and nicotinic acid amide to canine black tongue. J Amer Chem Soc 1937;59:1767.
17. Smith DF, Ruffin JM, Smith SG. Pellagra successfully treated with nicotinic acid: a case report. JAMA 1937;109:2054-5.
18. Wilder RM. A brief history of the enrichment of bread and flour. JAMA 1956;162:1539-40.
19. Carpenter KJ. Effects of different methods of processing maize on its pellagragenic activity. Fed Proc 1981;40:1531-5.
20. Etheridge EW: The Butterfly Caste. A Social History of Pellagra in the South. Westport, CT, Greenwood Press, 1972, 278 pp

Reference as: Robbins RA. Profiles in medical courage: Joseph Goldberger, the sharecropper’s plague, science and prejudice. Southwest J Pulm Crit Care 2012;4:189-93. (Click here for a PDF version of the manuscript)