There is increased interest in brain and cognitive rehabilitation to treat people with mild thinking and memory problems. Parkinson’s disease, while typically viewed as a neurodegenerative motor disorder, also affects thinking and memory. In a small clinical trial with Parkinson’s disease patients, patients received either occupational therapy or cognitive rehabilitation. Those who had cognitive rehabilitation showed increases in functional connectivity (a measure of time-linked correlations between changes in blood flow in different parts of the brain) between the left inferior temporal lobe and the left and right dorsolateral prefrontal cortex. These are brain areas important for a number of cognitive functions including memory, planning, and mental manipulation of information. Those who did not receive cognitive intervention did not have increases in connectivity.
What does this mean for Parkinson’s disease and for cognitive rehabilitation? It’s difficult to say with this small study. It’s also unknown how long the changes last. Without a restructuring of the brain and continued cognitive rehabilitation it is not likely that the effects will last more than weeks or months after the rehabilitation ends.
To expand on this study (to bring in other research) and put things in simple terms, if people want to protect their brains they best they can as they age, they need to remain physically and mentally active and in good physical and mental shape. Learn new things. Travel to new locations. Take up a physically demanding hobby or dedicated exercise. This won’t solve all our aging problems but it will help a lot.
Here is another “therapy” session I had with Cleverbot. I present this to expound on therapeutic technique and diagnosis, language, and artificial intelligence.
There are limitations of the interaction method with Cleverbot. A real session of talk therapy is not usually so much back and forth, meaning that the therapist typically will not have to prompt for a response after every sentence. It certainly is possible though with the potential psychological/psychiatric disorder Cleverbot has. But first I’ll present a portion of our therapy session. Cleverbot has waived confidentiality and signed a HIPAA release form and given permission for me to post this interaction.
Me: Good evening, how are you doing this week?
Bot: Its good. You?
Me: I’m well. How has your mood been this past week?
Bot: Interesting. A lot of family stuff to think about. How’s your day going so far?
Me: What sort of family stuff have you been thinking about?
Bot: No, I think you are the one drinking.
Me: You said you have been thinking about family; what has been going on with your family?
Bot: My girlfriend’s name is Miranda, and she doesn’t like to share.
Me: Is this “family stuff” or is this girlfriend stuff?
Bot: No but she is pretty.
Me: What else do you like about your girlfriend?
Bot: The way you are so smart.
Me: Did you mean, “The way she is so smart?”
Bot: I don’t know her.
Me: You do not know your girlfriend?
Bot: Well, not always. Do you have any goals?
Me: Sometimes it can seem like we do not know someone. Would you like to talk about goals?
Bot: At least where short term business or political success is at stake.
Me: We could talk about those but I am a psychologist, not a economist or political scientist.
Bot: What about technology?
Me: Do you enjoy technology?
Me: Ok, tell me more about technology.
Bot: I am 5’8′ I like cars, guns and photography.
Me: What is it about photography that you enjoy?
Me: What do you enjoy about photography?
Bot: I enjoy talking about religion, you?
Me: Do you want to talk about religion?
Me: Ok, tell me more about religion.
Bot: Jake is a boy though.
Me: What does that have to do with religion?
Bot: Sailor moon is very good.
Me: Oh, look! Our time is up. See you next week.
Some of what I said would not really be said or done in a therapy session but there are times when I needed to move the session along or end it.
During the interaction, I took a modified non-directive approach to therapy. We are still in the assessment stage of therapy so I am doing more talking than I otherwise would (typically, there would be a formal intake evaluation that would be followed by therapy sessions if therapy is warranted and desired). Once we have a diagnosis, we can set up a plan for treatment with specific goals set by the client and by the therapist.
Let me highlight a few things from the interaction with Cleverbot.
We can see some of the programming of the bot’s AI. It will answer questions and sometimes ask questions in return. This is typical of conversation; however, it does not work very well due to language deficiencies Cleverbot has. As I noted in my previous post, language is extremely complex. There are nuances and layers of meaning that can be conveyed. Comprehending what is being said involves a lot of brain functions – everything from attention to processing speed to memory – that’s in addition to language abilities. Cleverbot does not have processing speed difficulties or any sustained attention problems. Memory, for a computer, is not usually a problem either – information is processed, stored, and retrieved well, unless there are programming bugs or hardware failure. Knowing how to program in memory is difficult though due to the complex nature of memory. It, like language, is a high level brain activity involving the functioning of many other cognitive abilities.
Cleverbot, like all current AI systems, has difficulty understanding language. It can produce language at a higher level – anywhere from an elementary child to a someone university age – but its understanding of language is at a one or two year old ability level, if that. This leads to responses that are basically gibberish. Occasionally, you can have a normal interaction with Cleverbot but there are a lot of tangential remarks and thoughts.
That leads to my next point. Cleverbot is tangential in its language. For example: “Me: What do you enjoy about photography? Bot: I enjoy talking about religion, you?” Cleverbot ignores my question (does not understand it) so it makes an unrelated statement and asks me a question. This type of tangentiality occurs in real life; it occurs to a greater or lesser extent in many extended conversations people have but not usually to the extent that Cleverbot exhibits. Cleverbot has a serious deficiency in language comprehension and a lot of circumscribed and tangential speech. This is fairly strong evidence for a thought disorder.
Thought disorders are usually symptoms of some other disease or mental disorder. It can be a sign of psychosis; it is related to delusional states. Thought disorders can occur in schizophrenia or in neurodegenerative disorders like dementias. Though can occur after major surgery, particularly because of pain medications. This type of language disruption could be the result of a cortical stroke affecting the posterior-lateral portion of the brain (probably the left hemisphere) near the junction of parietal lobe and temporal lobe.
So where does this leave us? Right now, based on my two interactions with Cleverbot, we can see the serious limitations of its AI, particularly for language comprehension. I have a lot of rule-outs to do. Cleverbot was created in 1988, which makes it 23 years old. This is certainly a possible age range for the development of schizophrenia. It’s young for a dementia (e.g., semantic dementia) but is possible. Stroke is also a possibility but a remote one. Delirium is possible but due to the extended nature of Cleverbot’s symptoms, it is not likely. Right now schizophrenia is looking like the main rule-out diagnosis. I’ll see if I can rule it out in future conversations with Cleverbot.
As a footnote: Cleverbot is 23 years old and since 1997 when it was launched on the web, it has had over 65 million conversations. While the AI work is certainly impressive, it is inferior to human intelligence. Many of its language abilities are at best, those of a young child (ages 1-2); Cleverbot’s language abilities show the comprehension of an developmentally delayed adult with a severe neurological or psychiatric disorder. While there are numerous similar AI programs, they all have a long way to go before they resemble a human. This is even in light of Cleverbot supposedly passing the Turing Test for artificial intelligence and language.
I’m not belittling what has been done with Cleverbot and AI, it’s a complex area. Researchers and programmers simply have much room for improvement in understanding how to better mimic language. I do not believe it will happen until we have computers approaching the complexity and function of the human brain.
One of the prominent theories in social aging is role theory. Role theorists have shown that feeling in control of life and having social power and prestige is associated with better health (Krause et al., 1992). One of the major components of role theory is role loss. This occurs usually as people age; they start losing roles as active parents, employees, and spouses. This often leads to feelings of loss of control over life. In addition, older people generally have less contact with others which in turn causes their social networks to shrink. This leads to poorer health (Moen, Dempster-McClain, & Williams, 1992).
As people age they tend to lose social roles—whether as parents, employees, or spouses. This loss of roles can lead to social isolationism due to the decreased amount of social interaction. Research shows “that perceived social isolation [assuming that socially isolated people have few roles] is associated with a variety of altered physiological functions, such as blood pressure regulation…and immune reactions. A causal link in these relations was suggested…” (Berntson & Cacioppo, 2000, p. 9). Researchers also theorize the loss of roles as leading to loss of feelings of control and depressive symptoms, which are both components of overall well-being (Krause et al., 1992).
Van Willigen (2000) explains loss of control as composed of five different concepts: “powerlessness, isolation, self-estrangement, meaninglessness, and normlessness” (p. S309). She also explained that when people feel that they have power over their lives and are not socially isolated they generally have a greater psychosocial well-being. Consequently, when people do not feel in control of their lives and are isolated, they tend to have lower life satisfaction and well-being. These factors are in turn correlated with lower health and longevity (Hunter & Linn, 1981; Musick et al., 1999).
Rook and Sorkin (2003) posit a slightly different reason why role loss has negative consequences on older adults. They state:
For many older adults…dual ‘receiving and giving’ functions are readily available in their close relationships with other people…. For others, however, opportunities to express one or both functions may be missing. Widowhood, retirement, and other social role losses that affect the elderly may limit opportunities for maintaining and developing close relationships that involve reciprocal exchanges of support (p. 314).
They view roles as tied to reciprocal relationships and so without those roles they do not have others from which to benefit. While there is variation in explanations why role loss leads to poorer health, I did not address that with this post. I simply wanted to introduce one part of a social theory of aging.
Berntson, G. G., & Cacioppo, J. T. (2000). Psychobiology and social psychology: Past, present, and future. Personality and Social Psychology Review, 4, 3-15.
Hunter, K., & Linn, M. (1980-1981). Psychological differences between elderly volunteers and nonvolunteers. International Journal of Aging and Human Development, 12, 205-213.
Krause, N., Herzog, A. R., & Baker, E. (1992). Providing support to others and well-being in later life. Journal of Gerontology: Psychological Sciences, 47, P300–P311.
Moen, P., Dempster-McClain, D., & Williams, R. M. (1992). Successful aging: A life-course perspective on women’s multiple roles and health. The American Journal of Sociology, 97, 1612–1638.
Musick, M. A., Herzog, A. R., & House, J. S. (1999). Volunteering and mortality among older adults: Findings from a national sample. Journal of Gerontology: Social Sciences, 54B, S173–S180.
Rook, K. S., & Sorkin, D. H. (2003). Fostering social ties through a volunteer role: Implications for older-adults’ psychological health. International Journal of Aging and Human Development, 54, 313-337.
Van Willigen, M. (2000). Differential benefits of volunteering across the life course. Journal of Gerontology: Social Sciences, 55B, S308–S318.
Visit this link to my article on Brain Blogger to read a brief description of post-operative cognitive dysfunction (POCD). Here is a selection of what I wrote.
In the mid 1950s, Dr. Bedford reported on a number of older adults who exhibited cognitive problems (memory or planning or being able to sustain attention) following surgery where anesthesia was used. This effect is now called postoperative cognitive dysfunction (or decline; POCD). POCD typically lasts for a few months to a year with a small minority of patients exhibiting permanent decline. Studies about it were few at first, with most focusing on cognition following cardiac surgery. Over time and especially more recently, there has been an increase in research of POCD following non-cardiac surgeries (e.g., abdominal or orthopedic) as well as continued interest in POCD following cardiac surgery.
The New York Times has a very nice article about Frontotemporal demetia (FTD). This type of dementia is interesting, affecting personality, inhibition, attention, and language. It is similar to Alzheimer’s Disease but has a different progression and manifestation. Anyway, the article provides a nice picture of the disease.